Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
5b13b4a949 |
3
.gitignore
vendored
3
.gitignore
vendored
@@ -35,6 +35,3 @@ nltk_data/
|
||||
tika-server*.jar*
|
||||
cl100k_base.tiktoken
|
||||
libssl*.deb
|
||||
|
||||
sandbox/lib/seccomp_python/target
|
||||
sandbox/lib/seccomp_nodejs/target
|
||||
|
||||
14
README.md
14
README.md
@@ -334,13 +334,7 @@ step6: Log In to the Frontend Interface.
|
||||
## License
|
||||
This project is licensed under the Apache License 2.0. For details, see the LICENSE file.
|
||||
|
||||
## Community & Support
|
||||
|
||||
Join our community to ask questions, share your work, and connect with fellow developers.
|
||||
|
||||
- **GitHub Issues**: Report bugs, request features, or track known issues via [GitHub Issues](https://github.com/SuanmoSuanyangTechnology/MemoryBear/issues).
|
||||
- **GitHub Pull Requests**: Contribute code improvements or fixes through [Pull Requests](https://github.com/SuanmoSuanyangTechnology/MemoryBear/pulls).
|
||||
- **GitHub Discussions**: Ask questions, share ideas, and engage with the community in [GitHub Discussions](https://github.com/SuanmoSuanyangTechnology/MemoryBear/discussions).
|
||||
- **WeChat**: Scan the QR code below to join our WeChat community group.
|
||||
- 
|
||||
- **Contact**: If you are interested in contributing or collaborating, feel free to reach out at tianyou_hubm@redbearai.com
|
||||
## Acknowledgements & Community
|
||||
- Feedback & Issues: Please submit an Issue in the repository for bug reports or discussions.
|
||||
- Contributions Welcome: When submitting a Pull Request, please create a feature branch and follow conventional commit message guidelines.
|
||||
- Contact: If you are interested in contributing or collaborating, feel free to reach out at tianyou_hubm@redbearai.com
|
||||
@@ -1,25 +0,0 @@
|
||||
from pydantic import BaseModel, Field
|
||||
from sqlalchemy import TypeDecorator, JSON
|
||||
|
||||
|
||||
class PydanticType(TypeDecorator):
|
||||
impl = JSON
|
||||
|
||||
def __init__(self, pydantic_model: type[BaseModel]):
|
||||
super().__init__()
|
||||
self.model = pydantic_model
|
||||
|
||||
def process_bind_param(self, value, dialect):
|
||||
# 入库：Model -> dict
|
||||
if value is None:
|
||||
return None
|
||||
if isinstance(value, self.model):
|
||||
return value.dict()
|
||||
return value # 已经是 dict 也放行
|
||||
|
||||
def process_result_value(self, value, dialect):
|
||||
# 出库：dict -> Model
|
||||
if value is None:
|
||||
return None
|
||||
# return self.model.parse_obj(value) # pydantic v1
|
||||
return self.model.model_validate(value) # pydantic v2
|
||||
11
api/app/cache/__init__.py
vendored
11
api/app/cache/__init__.py
vendored
@@ -1,11 +0,0 @@
|
||||
"""
|
||||
Cache 缓存模块
|
||||
|
||||
提供各种缓存功能的统一入口
|
||||
"""
|
||||
from .memory import EmotionMemoryCache, ImplicitMemoryCache
|
||||
|
||||
__all__ = [
|
||||
"EmotionMemoryCache",
|
||||
"ImplicitMemoryCache",
|
||||
]
|
||||
12
api/app/cache/memory/__init__.py
vendored
12
api/app/cache/memory/__init__.py
vendored
@@ -1,12 +0,0 @@
|
||||
"""
|
||||
Memory 缓存模块
|
||||
|
||||
提供记忆系统相关的缓存功能
|
||||
"""
|
||||
from .emotion_memory import EmotionMemoryCache
|
||||
from .implicit_memory import ImplicitMemoryCache
|
||||
|
||||
__all__ = [
|
||||
"EmotionMemoryCache",
|
||||
"ImplicitMemoryCache",
|
||||
]
|
||||
134
api/app/cache/memory/emotion_memory.py
vendored
134
api/app/cache/memory/emotion_memory.py
vendored
@@ -1,134 +0,0 @@
|
||||
"""
|
||||
Emotion Suggestions Cache
|
||||
|
||||
情绪个性化建议缓存模块
|
||||
用于缓存用户的情绪个性化建议数据
|
||||
"""
|
||||
import json
|
||||
import logging
|
||||
from typing import Optional, Dict, Any
|
||||
from datetime import datetime
|
||||
|
||||
from app.aioRedis import aio_redis
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class EmotionMemoryCache:
|
||||
"""情绪建议缓存类"""
|
||||
|
||||
# Key 前缀
|
||||
PREFIX = "cache:memory:emotion_memory"
|
||||
|
||||
@classmethod
|
||||
def _get_key(cls, *parts: str) -> str:
|
||||
"""生成 Redis key
|
||||
|
||||
Args:
|
||||
*parts: key 的各个部分
|
||||
|
||||
Returns:
|
||||
完整的 Redis key
|
||||
"""
|
||||
return ":".join([cls.PREFIX] + list(parts))
|
||||
|
||||
@classmethod
|
||||
async def set_emotion_suggestions(
|
||||
cls,
|
||||
user_id: str,
|
||||
suggestions_data: Dict[str, Any],
|
||||
expire: int = 86400
|
||||
) -> bool:
|
||||
"""设置用户情绪建议缓存
|
||||
|
||||
Args:
|
||||
user_id: 用户ID（end_user_id）
|
||||
suggestions_data: 建议数据字典，包含：
|
||||
- health_summary: 健康状态摘要
|
||||
- suggestions: 建议列表
|
||||
- generated_at: 生成时间（可选）
|
||||
expire: 过期时间（秒），默认24小时（86400秒）
|
||||
|
||||
Returns:
|
||||
是否设置成功
|
||||
"""
|
||||
try:
|
||||
key = cls._get_key("suggestions", user_id)
|
||||
|
||||
# 添加生成时间戳
|
||||
if "generated_at" not in suggestions_data:
|
||||
suggestions_data["generated_at"] = datetime.now().isoformat()
|
||||
|
||||
# 添加缓存标记
|
||||
suggestions_data["cached"] = True
|
||||
|
||||
value = json.dumps(suggestions_data, ensure_ascii=False)
|
||||
await aio_redis.set(key, value, ex=expire)
|
||||
logger.info(f"设置情绪建议缓存成功: {key}, 过期时间: {expire}秒")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"设置情绪建议缓存失败: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
async def get_emotion_suggestions(cls, user_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""获取用户情绪建议缓存
|
||||
|
||||
Args:
|
||||
user_id: 用户ID（end_user_id）
|
||||
|
||||
Returns:
|
||||
建议数据字典，如果不存在或已过期返回 None
|
||||
"""
|
||||
try:
|
||||
key = cls._get_key("suggestions", user_id)
|
||||
value = await aio_redis.get(key)
|
||||
|
||||
if value:
|
||||
data = json.loads(value)
|
||||
logger.info(f"成功获取情绪建议缓存: {key}")
|
||||
return data
|
||||
|
||||
logger.info(f"情绪建议缓存不存在或已过期: {key}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"获取情绪建议缓存失败: {e}", exc_info=True)
|
||||
return None
|
||||
|
||||
@classmethod
|
||||
async def delete_emotion_suggestions(cls, user_id: str) -> bool:
|
||||
"""删除用户情绪建议缓存
|
||||
|
||||
Args:
|
||||
user_id: 用户ID（end_user_id）
|
||||
|
||||
Returns:
|
||||
是否删除成功
|
||||
"""
|
||||
try:
|
||||
key = cls._get_key("suggestions", user_id)
|
||||
result = await aio_redis.delete(key)
|
||||
logger.info(f"删除情绪建议缓存: {key}, 结果: {result}")
|
||||
return result > 0
|
||||
except Exception as e:
|
||||
logger.error(f"删除情绪建议缓存失败: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
async def get_suggestions_ttl(cls, user_id: str) -> int:
|
||||
"""获取情绪建议缓存的剩余过期时间
|
||||
|
||||
Args:
|
||||
user_id: 用户ID（end_user_id）
|
||||
|
||||
Returns:
|
||||
剩余秒数，-1表示永不过期，-2表示key不存在
|
||||
"""
|
||||
try:
|
||||
key = cls._get_key("suggestions", user_id)
|
||||
ttl = await aio_redis.ttl(key)
|
||||
logger.debug(f"情绪建议缓存TTL: {key} = {ttl}秒")
|
||||
return ttl
|
||||
except Exception as e:
|
||||
logger.error(f"获取情绪建议缓存TTL失败: {e}")
|
||||
return -2
|
||||
136
api/app/cache/memory/implicit_memory.py
vendored
136
api/app/cache/memory/implicit_memory.py
vendored
@@ -1,136 +0,0 @@
|
||||
"""
|
||||
Implicit Memory Profile Cache
|
||||
|
||||
隐式记忆用户画像缓存模块
|
||||
用于缓存用户的完整画像数据（偏好标签、四维画像、兴趣领域、行为习惯）
|
||||
"""
|
||||
import json
|
||||
import logging
|
||||
from typing import Optional, Dict, Any
|
||||
from datetime import datetime
|
||||
|
||||
from app.aioRedis import aio_redis
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ImplicitMemoryCache:
|
||||
"""隐式记忆用户画像缓存类"""
|
||||
|
||||
# Key 前缀
|
||||
PREFIX = "cache:memory:implicit_memory"
|
||||
|
||||
@classmethod
|
||||
def _get_key(cls, *parts: str) -> str:
|
||||
"""生成 Redis key
|
||||
|
||||
Args:
|
||||
*parts: key 的各个部分
|
||||
|
||||
Returns:
|
||||
完整的 Redis key
|
||||
"""
|
||||
return ":".join([cls.PREFIX] + list(parts))
|
||||
|
||||
@classmethod
|
||||
async def set_user_profile(
|
||||
cls,
|
||||
user_id: str,
|
||||
profile_data: Dict[str, Any],
|
||||
expire: int = 86400
|
||||
) -> bool:
|
||||
"""设置用户完整画像缓存
|
||||
|
||||
Args:
|
||||
user_id: 用户ID（end_user_id）
|
||||
profile_data: 画像数据字典，包含：
|
||||
- preferences: 偏好标签列表
|
||||
- portrait: 四维画像对象
|
||||
- interest_areas: 兴趣领域分布对象
|
||||
- habits: 行为习惯列表
|
||||
- generated_at: 生成时间（可选）
|
||||
expire: 过期时间（秒），默认24小时（86400秒）
|
||||
|
||||
Returns:
|
||||
是否设置成功
|
||||
"""
|
||||
try:
|
||||
key = cls._get_key("profile", user_id)
|
||||
|
||||
# 添加生成时间戳
|
||||
if "generated_at" not in profile_data:
|
||||
profile_data["generated_at"] = datetime.now().isoformat()
|
||||
|
||||
# 添加缓存标记
|
||||
profile_data["cached"] = True
|
||||
|
||||
value = json.dumps(profile_data, ensure_ascii=False)
|
||||
await aio_redis.set(key, value, ex=expire)
|
||||
logger.info(f"设置用户画像缓存成功: {key}, 过期时间: {expire}秒")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"设置用户画像缓存失败: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
async def get_user_profile(cls, user_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""获取用户完整画像缓存
|
||||
|
||||
Args:
|
||||
user_id: 用户ID（end_user_id）
|
||||
|
||||
Returns:
|
||||
画像数据字典，如果不存在或已过期返回 None
|
||||
"""
|
||||
try:
|
||||
key = cls._get_key("profile", user_id)
|
||||
value = await aio_redis.get(key)
|
||||
|
||||
if value:
|
||||
data = json.loads(value)
|
||||
logger.info(f"成功获取用户画像缓存: {key}")
|
||||
return data
|
||||
|
||||
logger.info(f"用户画像缓存不存在或已过期: {key}")
|
||||
return None
|
||||
except Exception as e:
|
||||
logger.error(f"获取用户画像缓存失败: {e}", exc_info=True)
|
||||
return None
|
||||
|
||||
@classmethod
|
||||
async def delete_user_profile(cls, user_id: str) -> bool:
|
||||
"""删除用户完整画像缓存
|
||||
|
||||
Args:
|
||||
user_id: 用户ID（end_user_id）
|
||||
|
||||
Returns:
|
||||
是否删除成功
|
||||
"""
|
||||
try:
|
||||
key = cls._get_key("profile", user_id)
|
||||
result = await aio_redis.delete(key)
|
||||
logger.info(f"删除用户画像缓存: {key}, 结果: {result}")
|
||||
return result > 0
|
||||
except Exception as e:
|
||||
logger.error(f"删除用户画像缓存失败: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
async def get_profile_ttl(cls, user_id: str) -> int:
|
||||
"""获取用户画像缓存的剩余过期时间
|
||||
|
||||
Args:
|
||||
user_id: 用户ID（end_user_id）
|
||||
|
||||
Returns:
|
||||
剩余秒数，-1表示永不过期，-2表示key不存在
|
||||
"""
|
||||
try:
|
||||
key = cls._get_key("profile", user_id)
|
||||
ttl = await aio_redis.ttl(key)
|
||||
logger.debug(f"用户画像缓存TTL: {key} = {ttl}秒")
|
||||
return ttl
|
||||
except Exception as e:
|
||||
logger.error(f"获取用户画像缓存TTL失败: {e}")
|
||||
return -2
|
||||
@@ -1,5 +1,4 @@
|
||||
import os
|
||||
import platform
|
||||
from datetime import timedelta
|
||||
from urllib.parse import quote
|
||||
|
||||
@@ -15,12 +14,27 @@ celery_app = Celery(
|
||||
backend=f"redis://:{quote(settings.REDIS_PASSWORD)}@{settings.REDIS_HOST}:{settings.REDIS_PORT}/{settings.CELERY_BACKEND}",
|
||||
)
|
||||
|
||||
# Default queue for unrouted tasks
|
||||
celery_app.conf.task_default_queue = 'memory_tasks'
|
||||
# 配置使用本地队列，避免与远程 worker 冲突
|
||||
celery_app.conf.task_default_queue = 'localhost_test_wyl'
|
||||
celery_app.conf.task_default_exchange = 'localhost_test_wyl'
|
||||
celery_app.conf.task_default_routing_key = 'localhost_test_wyl'
|
||||
|
||||
# macOS 兼容性配置
|
||||
if platform.system() == 'Darwin':
|
||||
import platform
|
||||
|
||||
if platform.system() == 'Darwin': # macOS
|
||||
# 设置环境变量解决 fork 问题
|
||||
os.environ.setdefault('OBJC_DISABLE_INITIALIZE_FORK_SAFETY', 'YES')
|
||||
|
||||
# 使用 solo 池避免多进程问题
|
||||
celery_app.conf.worker_pool = 'solo'
|
||||
|
||||
# 设置唯一的节点名称
|
||||
import socket
|
||||
import time
|
||||
hostname = socket.gethostname()
|
||||
timestamp = int(time.time())
|
||||
celery_app.conf.worker_name = f"celery@{hostname}-{timestamp}"
|
||||
|
||||
# Celery 配置
|
||||
celery_app.conf.update(
|
||||
@@ -38,54 +52,47 @@ celery_app.conf.update(
|
||||
task_ignore_result=False,
|
||||
|
||||
# 超时设置
|
||||
task_time_limit=1800, # 30分钟硬超时
|
||||
task_soft_time_limit=1500, # 25分钟软超时
|
||||
task_time_limit=30 * 60, # 30 分钟硬超时
|
||||
task_soft_time_limit=25 * 60, # 25 分钟软超时
|
||||
|
||||
# Worker 设置 (per-worker settings are in docker-compose command line)
|
||||
worker_prefetch_multiplier=1, # Don't hoard tasks, fairer distribution
|
||||
# Worker 设置 - 针对 macOS 优化
|
||||
worker_prefetch_multiplier=1, # 减少预取任务数，避免内存堆积
|
||||
worker_max_tasks_per_child=10, # 大幅减少每个 worker 执行的任务数，频繁重启防止内存泄漏
|
||||
worker_max_memory_per_child=200000, # 200MB 内存限制，超过后重启 worker
|
||||
|
||||
# 结果过期时间
|
||||
result_expires=3600, # 结果保存1小时
|
||||
result_expires=3600, # 结果保存 1 小时
|
||||
|
||||
# 任务确认设置
|
||||
task_acks_late=True,
|
||||
task_reject_on_worker_lost=True,
|
||||
worker_disable_rate_limits=True,
|
||||
task_acks_late=True, # 任务完成后才确认，避免任务丢失
|
||||
worker_disable_rate_limits=True, # 禁用速率限制
|
||||
|
||||
# FLower setting
|
||||
worker_send_task_events=True,
|
||||
task_send_sent_event=True,
|
||||
|
||||
# task routing
|
||||
task_routes={
|
||||
# Memory tasks → memory_tasks queue (threads worker)
|
||||
'app.core.memory.agent.read_message_priority': {'queue': 'memory_tasks'},
|
||||
'app.core.memory.agent.read_message': {'queue': 'memory_tasks'},
|
||||
'app.core.memory.agent.write_message': {'queue': 'memory_tasks'},
|
||||
|
||||
# Document tasks → document_tasks queue (prefork worker)
|
||||
'app.core.rag.tasks.parse_document': {'queue': 'document_tasks'},
|
||||
'app.core.rag.tasks.build_graphrag_for_kb': {'queue': 'document_tasks'},
|
||||
|
||||
# Beat/periodic tasks → document_tasks queue (prefork worker)
|
||||
'app.tasks.workspace_reflection_task': {'queue': 'document_tasks'},
|
||||
'app.tasks.regenerate_memory_cache': {'queue': 'document_tasks'},
|
||||
'app.tasks.run_forgetting_cycle_task': {'queue': 'document_tasks'},
|
||||
'app.controllers.memory_storage_controller.search_all': {'queue': 'document_tasks'},
|
||||
},
|
||||
# 任务路由（可选，用于不同队列）
|
||||
# task_routes={
|
||||
# 'app.core.rag.tasks.parse_document': {'queue': 'document_processing'},
|
||||
# 'app.core.memory.agent.read_message': {'queue': 'memory_processing'},
|
||||
# 'app.core.memory.agent.write_message': {'queue': 'memory_processing'},
|
||||
# 'tasks.process_item': {'queue': 'default'},
|
||||
# },
|
||||
)
|
||||
|
||||
# 自动发现任务模块
|
||||
celery_app.autodiscover_tasks(['app'])
|
||||
|
||||
# Celery Beat schedule for periodic tasks
|
||||
reflection_schedule = timedelta(seconds=settings.REFLECTION_INTERVAL_SECONDS)
|
||||
health_schedule = timedelta(seconds=settings.HEALTH_CHECK_SECONDS)
|
||||
memory_increment_schedule = timedelta(hours=settings.MEMORY_INCREMENT_INTERVAL_HOURS)
|
||||
memory_cache_regeneration_schedule = timedelta(hours=settings.MEMORY_CACHE_REGENERATION_HOURS)
|
||||
workspace_reflection_schedule = timedelta(seconds=30) # 每30秒运行一次settings.REFLECTION_INTERVAL_TIME
|
||||
forgetting_cycle_schedule = timedelta(hours=24) # 每24小时运行一次遗忘周期
|
||||
|
||||
# 构建定时任务配置
|
||||
beat_schedule_config = {
|
||||
|
||||
# "check-read-service": {
|
||||
# "task": "app.core.memory.agent.health.check_read_service",
|
||||
# "schedule": health_schedule,
|
||||
# "args": (),
|
||||
# },
|
||||
"run-workspace-reflection": {
|
||||
"task": "app.tasks.workspace_reflection_task",
|
||||
"schedule": workspace_reflection_schedule,
|
||||
@@ -96,13 +103,6 @@ beat_schedule_config = {
|
||||
"schedule": memory_cache_regeneration_schedule,
|
||||
"args": (),
|
||||
},
|
||||
"run-forgetting-cycle": {
|
||||
"task": "app.tasks.run_forgetting_cycle_task",
|
||||
"schedule": forgetting_cycle_schedule,
|
||||
"kwargs": {
|
||||
"config_id": None, # 使用默认配置，可以通过环境变量配置
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
# 如果配置了默认工作空间ID，则添加记忆总量统计任务
|
||||
|
||||
@@ -3,12 +3,6 @@ Celery Worker 入口点
|
||||
用于启动 Celery Worker: celery -A app.celery_worker worker --loglevel=info
|
||||
"""
|
||||
from app.celery_app import celery_app
|
||||
from app.core.logging_config import LoggingConfig, get_logger
|
||||
|
||||
# Initialize logging system for Celery worker
|
||||
LoggingConfig.setup_logging()
|
||||
logger = get_logger(__name__)
|
||||
logger.info("Celery worker logging initialized")
|
||||
|
||||
# 导入任务模块以注册任务
|
||||
import app.tasks
|
||||
|
||||
@@ -4,48 +4,37 @@
|
||||
认证方式: JWT Token
|
||||
"""
|
||||
from fastapi import APIRouter
|
||||
|
||||
from . import (
|
||||
api_key_controller,
|
||||
app_controller,
|
||||
auth_controller,
|
||||
chunk_controller,
|
||||
document_controller,
|
||||
emotion_config_controller,
|
||||
emotion_controller,
|
||||
file_controller,
|
||||
file_storage_controller,
|
||||
home_page_controller,
|
||||
implicit_memory_controller,
|
||||
knowledge_controller,
|
||||
knowledgeshare_controller,
|
||||
memory_agent_controller,
|
||||
memory_dashboard_controller,
|
||||
memory_episodic_controller,
|
||||
memory_explicit_controller,
|
||||
memory_forget_controller,
|
||||
memory_reflection_controller,
|
||||
memory_short_term_controller,
|
||||
memory_storage_controller,
|
||||
model_controller,
|
||||
multi_agent_controller,
|
||||
prompt_optimizer_controller,
|
||||
public_share_controller,
|
||||
release_share_controller,
|
||||
setup_controller,
|
||||
task_controller,
|
||||
test_controller,
|
||||
tool_controller,
|
||||
upload_controller,
|
||||
user_controller,
|
||||
user_memory_controllers,
|
||||
workflow_controller,
|
||||
auth_controller,
|
||||
workspace_controller,
|
||||
memory_forget_controller,
|
||||
home_page_controller,
|
||||
memory_perceptual_controller,
|
||||
memory_working_controller,
|
||||
setup_controller,
|
||||
file_controller,
|
||||
document_controller,
|
||||
knowledge_controller,
|
||||
chunk_controller,
|
||||
knowledgeshare_controller,
|
||||
app_controller,
|
||||
upload_controller,
|
||||
memory_agent_controller,
|
||||
memory_dashboard_controller,
|
||||
memory_storage_controller,
|
||||
memory_dashboard_controller,
|
||||
memory_reflection_controller,
|
||||
api_key_controller,
|
||||
release_share_controller,
|
||||
public_share_controller,
|
||||
multi_agent_controller,
|
||||
workflow_controller,
|
||||
emotion_controller,
|
||||
emotion_config_controller,
|
||||
prompt_optimizer_controller,
|
||||
tool_controller,
|
||||
)
|
||||
from . import user_memory_controllers
|
||||
|
||||
# 创建管理端 API 路由器
|
||||
manager_router = APIRouter()
|
||||
@@ -70,8 +59,6 @@ manager_router.include_router(memory_agent_controller.router)
|
||||
manager_router.include_router(memory_dashboard_controller.router)
|
||||
manager_router.include_router(memory_storage_controller.router)
|
||||
manager_router.include_router(user_memory_controllers.router)
|
||||
manager_router.include_router(memory_episodic_controller.router)
|
||||
manager_router.include_router(memory_explicit_controller.router)
|
||||
manager_router.include_router(api_key_controller.router)
|
||||
manager_router.include_router(release_share_controller.router)
|
||||
manager_router.include_router(public_share_controller.router) # 公开路由（无需认证）
|
||||
@@ -82,13 +69,6 @@ manager_router.include_router(emotion_controller.router)
|
||||
manager_router.include_router(emotion_config_controller.router)
|
||||
manager_router.include_router(prompt_optimizer_controller.router)
|
||||
manager_router.include_router(memory_reflection_controller.router)
|
||||
manager_router.include_router(memory_short_term_controller.router)
|
||||
manager_router.include_router(tool_controller.router)
|
||||
manager_router.include_router(memory_forget_controller.router)
|
||||
manager_router.include_router(home_page_controller.router)
|
||||
manager_router.include_router(implicit_memory_controller.router)
|
||||
manager_router.include_router(memory_perceptual_controller.router)
|
||||
manager_router.include_router(memory_working_controller.router)
|
||||
manager_router.include_router(file_storage_controller.router)
|
||||
|
||||
__all__ = ["manager_router"]
|
||||
|
||||
@@ -7,20 +7,19 @@ from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.error_codes import BizCode
|
||||
from app.core.logging_config import get_business_logger
|
||||
from app.core.response_utils import success, fail
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user, cur_workspace_access_guard
|
||||
from app.models import User
|
||||
from app.models.app_model import AppType
|
||||
from app.models.app_model import AppType, App
|
||||
from app.repositories import knowledge_repository
|
||||
from app.repositories.end_user_repository import EndUserRepository
|
||||
from app.schemas import app_schema
|
||||
from app.schemas.response_schema import PageData, PageMeta
|
||||
from app.schemas.workflow_schema import WorkflowConfig as WorkflowConfigSchema
|
||||
from app.schemas.workflow_schema import WorkflowConfigUpdate
|
||||
from app.services import app_service, workspace_service
|
||||
from app.services.agent_config_helper import enrich_agent_config
|
||||
from app.services.app_service import AppService
|
||||
from app.schemas.workflow_schema import WorkflowConfig as WorkflowConfigSchema
|
||||
from app.services.workflow_service import WorkflowService, get_workflow_service
|
||||
|
||||
router = APIRouter(prefix="/apps", tags=["Apps"])
|
||||
@@ -30,9 +29,9 @@ logger = get_business_logger()
|
||||
@router.post("", summary="创建应用（可选创建 Agent 配置）")
|
||||
@cur_workspace_access_guard()
|
||||
def create_app(
|
||||
payload: app_schema.AppCreate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
payload: app_schema.AppCreate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
app = app_service.create_app(db, user_id=current_user.id, workspace_id=workspace_id, data=payload)
|
||||
@@ -42,34 +41,22 @@ def create_app(
|
||||
@router.get("", summary="应用列表（分页）")
|
||||
@cur_workspace_access_guard()
|
||||
def list_apps(
|
||||
type: str | None = None,
|
||||
visibility: str | None = None,
|
||||
status: str | None = None,
|
||||
search: str | None = None,
|
||||
include_shared: bool = True,
|
||||
page: int = 1,
|
||||
pagesize: int = 10,
|
||||
ids: Optional[str] = None,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
type: str | None = None,
|
||||
visibility: str | None = None,
|
||||
status: str | None = None,
|
||||
search: str | None = None,
|
||||
include_shared: bool = True,
|
||||
page: int = 1,
|
||||
pagesize: int = 10,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""列出应用
|
||||
|
||||
- 默认包含本工作空间的应用和分享给本工作空间的应用
|
||||
- 设置 include_shared=false 可以只查看本工作空间的应用
|
||||
- 当提供 ids 参数时，按逗号分割获取指定应用，不分页
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
service = app_service.AppService(db)
|
||||
|
||||
# 当 ids 存在且不为 None 时，根据 ids 获取应用
|
||||
if ids is not None:
|
||||
app_ids = [id.strip() for id in ids.split(',') if id.strip()]
|
||||
items_orm = app_service.get_apps_by_ids(db, app_ids, workspace_id)
|
||||
items = [service._convert_to_schema(app, workspace_id) for app in items_orm]
|
||||
return success(data=items)
|
||||
|
||||
# 正常分页查询
|
||||
items_orm, total = app_service.list_apps(
|
||||
db,
|
||||
workspace_id=workspace_id,
|
||||
@@ -82,17 +69,18 @@ def list_apps(
|
||||
pagesize=pagesize,
|
||||
)
|
||||
|
||||
# 使用 AppService 的转换方法来设置 is_shared 字段
|
||||
service = app_service.AppService(db)
|
||||
items = [service._convert_to_schema(app, workspace_id) for app in items_orm]
|
||||
meta = PageMeta(page=page, pagesize=pagesize, total=total, hasnext=(page * pagesize) < total)
|
||||
return success(data=PageData(page=meta, items=items))
|
||||
|
||||
|
||||
@router.get("/{app_id}", summary="获取应用详情")
|
||||
@cur_workspace_access_guard()
|
||||
def get_app(
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""获取应用详细信息
|
||||
|
||||
@@ -111,10 +99,10 @@ def get_app(
|
||||
@router.put("/{app_id}", summary="更新应用基本信息")
|
||||
@cur_workspace_access_guard()
|
||||
def update_app(
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.AppUpdate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.AppUpdate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
app = app_service.update_app(db, app_id=app_id, data=payload, workspace_id=workspace_id)
|
||||
@@ -124,9 +112,9 @@ def update_app(
|
||||
@router.delete("/{app_id}", summary="删除应用")
|
||||
@cur_workspace_access_guard()
|
||||
def delete_app(
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""删除应用
|
||||
|
||||
@@ -153,10 +141,10 @@ def delete_app(
|
||||
@router.post("/{app_id}/copy", summary="复制应用")
|
||||
@cur_workspace_access_guard()
|
||||
def copy_app(
|
||||
app_id: uuid.UUID,
|
||||
new_name: Optional[str] = None,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
new_name: Optional[str] = None,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""复制应用（包括基础信息和配置）
|
||||
|
||||
@@ -190,10 +178,10 @@ def copy_app(
|
||||
@router.put("/{app_id}/config", summary="更新 Agent 配置")
|
||||
@cur_workspace_access_guard()
|
||||
def update_agent_config(
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.AgentConfigUpdate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.AgentConfigUpdate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
cfg = app_service.update_agent_config(db, app_id=app_id, data=payload, workspace_id=workspace_id)
|
||||
@@ -204,9 +192,9 @@ def update_agent_config(
|
||||
@router.get("/{app_id}/config", summary="获取 Agent 配置")
|
||||
@cur_workspace_access_guard()
|
||||
def get_agent_config(
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
cfg = app_service.get_agent_config(db, app_id=app_id, workspace_id=workspace_id)
|
||||
@@ -218,10 +206,10 @@ def get_agent_config(
|
||||
@router.post("/{app_id}/publish", summary="发布应用（生成不可变快照）")
|
||||
@cur_workspace_access_guard()
|
||||
def publish_app(
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.PublishRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.PublishRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
release = app_service.publish(
|
||||
@@ -229,7 +217,7 @@ def publish_app(
|
||||
app_id=app_id,
|
||||
publisher_id=current_user.id,
|
||||
workspace_id=workspace_id,
|
||||
version_name=payload.version_name,
|
||||
version_name = payload.version_name,
|
||||
release_notes=payload.release_notes
|
||||
)
|
||||
return success(data=app_schema.AppRelease.model_validate(release))
|
||||
@@ -238,9 +226,9 @@ def publish_app(
|
||||
@router.get("/{app_id}/release", summary="获取当前发布版本")
|
||||
@cur_workspace_access_guard()
|
||||
def get_current_release(
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
release = app_service.get_current_release(db, app_id=app_id, workspace_id=workspace_id)
|
||||
@@ -252,9 +240,9 @@ def get_current_release(
|
||||
@router.get("/{app_id}/releases", summary="列出历史发布版本（倒序）")
|
||||
@cur_workspace_access_guard()
|
||||
def list_releases(
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
releases = app_service.list_releases(db, app_id=app_id, workspace_id=workspace_id)
|
||||
@@ -265,10 +253,10 @@ def list_releases(
|
||||
@router.post("/{app_id}/rollback/{version}", summary="回滚到指定版本")
|
||||
@cur_workspace_access_guard()
|
||||
def rollback(
|
||||
app_id: uuid.UUID,
|
||||
version: int,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
version: int,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
release = app_service.rollback(db, app_id=app_id, version=version, workspace_id=workspace_id)
|
||||
@@ -278,10 +266,10 @@ def rollback(
|
||||
@router.post("/{app_id}/share", summary="分享应用到其他工作空间")
|
||||
@cur_workspace_access_guard()
|
||||
def share_app(
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.AppShareCreate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.AppShareCreate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""分享应用到其他工作空间
|
||||
|
||||
@@ -306,10 +294,10 @@ def share_app(
|
||||
@router.delete("/{app_id}/share/{target_workspace_id}", summary="取消应用分享")
|
||||
@cur_workspace_access_guard()
|
||||
def unshare_app(
|
||||
app_id: uuid.UUID,
|
||||
target_workspace_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
target_workspace_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""取消应用分享
|
||||
|
||||
@@ -330,9 +318,9 @@ def unshare_app(
|
||||
@router.get("/{app_id}/shares", summary="列出应用的分享记录")
|
||||
@cur_workspace_access_guard()
|
||||
def list_app_shares(
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""列出应用的所有分享记录
|
||||
|
||||
@@ -349,15 +337,14 @@ def list_app_shares(
|
||||
data = [app_schema.AppShare.model_validate(s) for s in shares]
|
||||
return success(data=data)
|
||||
|
||||
|
||||
@router.post("/{app_id}/draft/run", summary="试运行 Agent（使用当前草稿配置）")
|
||||
@cur_workspace_access_guard()
|
||||
async def draft_run(
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.DraftRunRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
workflow_service: Annotated[WorkflowService, Depends(get_workflow_service)] = None
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.DraftRunRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
workflow_service: Annotated[WorkflowService, Depends(get_workflow_service)] = None
|
||||
):
|
||||
"""
|
||||
试运行 Agent，使用当前的草稿配置（未发布的配置）
|
||||
@@ -374,7 +361,7 @@ async def draft_run(
|
||||
workspace_id=workspace_id,
|
||||
user=current_user
|
||||
)
|
||||
if storage_type is None:
|
||||
if storage_type is None:
|
||||
storage_type = 'neo4j'
|
||||
user_rag_memory_id = ''
|
||||
if workspace_id:
|
||||
@@ -384,9 +371,10 @@ async def draft_run(
|
||||
name="USER_RAG_MERORY",
|
||||
workspace_id=workspace_id
|
||||
)
|
||||
if knowledge:
|
||||
if knowledge:
|
||||
user_rag_memory_id = str(knowledge.id)
|
||||
|
||||
|
||||
# 提前验证和准备（在流式响应开始前完成）
|
||||
from app.services.app_service import AppService
|
||||
from app.services.multi_agent_service import MultiAgentService
|
||||
@@ -406,22 +394,13 @@ async def draft_run(
|
||||
# 只读操作，允许访问共享应用
|
||||
service._validate_app_accessible(app, workspace_id)
|
||||
|
||||
if payload.user_id is None:
|
||||
end_user_repo = EndUserRepository(db)
|
||||
new_end_user = end_user_repo.get_or_create_end_user(
|
||||
app_id=app_id,
|
||||
other_id=str(current_user.id),
|
||||
original_user_id=str(current_user.id) # Save original user_id to other_id
|
||||
)
|
||||
payload.user_id = str(new_end_user.id)
|
||||
|
||||
# 处理会话ID（创建或验证）
|
||||
conversation_id = await draft_service._ensure_conversation(
|
||||
conversation_id=payload.conversation_id,
|
||||
app_id=app_id,
|
||||
workspace_id=workspace_id,
|
||||
user_id=payload.user_id
|
||||
)
|
||||
conversation_id=payload.conversation_id,
|
||||
app_id=app_id,
|
||||
workspace_id=workspace_id,
|
||||
user_id=payload.user_id
|
||||
)
|
||||
payload.conversation_id = conversation_id
|
||||
|
||||
if app.type == AppType.AGENT:
|
||||
@@ -445,16 +424,17 @@ async def draft_run(
|
||||
if payload.stream:
|
||||
async def event_generator():
|
||||
|
||||
|
||||
async for event in draft_service.run_stream(
|
||||
agent_config=agent_cfg,
|
||||
model_config=model_config,
|
||||
message=payload.message,
|
||||
workspace_id=workspace_id,
|
||||
conversation_id=payload.conversation_id,
|
||||
user_id=payload.user_id or str(current_user.id),
|
||||
variables=payload.variables,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
agent_config=agent_cfg,
|
||||
model_config=model_config,
|
||||
message=payload.message,
|
||||
workspace_id=workspace_id,
|
||||
conversation_id=payload.conversation_id,
|
||||
user_id=payload.user_id or str(current_user.id),
|
||||
variables=payload.variables,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
):
|
||||
yield event
|
||||
|
||||
@@ -526,7 +506,7 @@ async def draft_run(
|
||||
multi_agent_request = MultiAgentRunRequest(
|
||||
message=payload.message,
|
||||
conversation_id=payload.conversation_id,
|
||||
user_id=payload.user_id or str(current_user.id),
|
||||
user_id=payload.user_id,
|
||||
variables=payload.variables or {},
|
||||
use_llm_routing=True # 默认启用 LLM 路由
|
||||
)
|
||||
@@ -548,10 +528,10 @@ async def draft_run(
|
||||
|
||||
# 调用多智能体服务的流式方法
|
||||
async for event in multiservice.run_stream(
|
||||
app_id=app_id,
|
||||
request=multi_agent_request,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
app_id=app_id,
|
||||
request=multi_agent_request,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
|
||||
):
|
||||
yield event
|
||||
@@ -591,7 +571,7 @@ async def draft_run(
|
||||
data=result,
|
||||
msg="多 Agent 任务执行成功"
|
||||
)
|
||||
elif app.type == AppType.WORKFLOW: # 工作流
|
||||
elif app.type == AppType.WORKFLOW: #工作流
|
||||
config = workflow_service.check_config(app_id)
|
||||
# 3. 流式返回
|
||||
if payload.stream:
|
||||
@@ -612,18 +592,17 @@ async def draft_run(
|
||||
data: <json_data>
|
||||
"""
|
||||
import json
|
||||
|
||||
|
||||
# 调用工作流服务的流式方法
|
||||
async for event in workflow_service.run_stream(
|
||||
app_id=app_id,
|
||||
payload=payload,
|
||||
config=config,
|
||||
workspace_id=current_user.current_workspace_id
|
||||
config=config
|
||||
):
|
||||
# 提取事件类型和数据
|
||||
event_type = event.get("event", "message")
|
||||
event_data = event.get("data", {})
|
||||
|
||||
|
||||
# 转换为标准 SSE 格式（字符串）
|
||||
sse_message = f"event: {event_type}\ndata: {json.dumps(event_data)}\n\n"
|
||||
yield sse_message
|
||||
@@ -648,7 +627,7 @@ async def draft_run(
|
||||
}
|
||||
)
|
||||
|
||||
result = await workflow_service.run(app_id, payload, config, current_user.current_workspace_id)
|
||||
result = await workflow_service.run(app_id, payload,config)
|
||||
|
||||
logger.debug(
|
||||
"工作流试运行返回结果",
|
||||
@@ -661,20 +640,16 @@ async def draft_run(
|
||||
data=result,
|
||||
msg="工作流任务执行成功"
|
||||
)
|
||||
else:
|
||||
return fail(
|
||||
msg="未知应用类型",
|
||||
code=422
|
||||
)
|
||||
|
||||
|
||||
|
||||
@router.post("/{app_id}/draft/run/compare", summary="多模型对比试运行")
|
||||
@cur_workspace_access_guard()
|
||||
async def draft_run_compare(
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.DraftRunCompareRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
app_id: uuid.UUID,
|
||||
payload: app_schema.DraftRunCompareRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
多模型对比试运行
|
||||
@@ -699,7 +674,7 @@ async def draft_run_compare(
|
||||
workspace_id=workspace_id,
|
||||
user=current_user
|
||||
)
|
||||
if storage_type is None:
|
||||
if storage_type is None:
|
||||
storage_type = 'neo4j'
|
||||
user_rag_memory_id = ''
|
||||
if workspace_id:
|
||||
@@ -708,7 +683,7 @@ async def draft_run_compare(
|
||||
name="USER_RAG_MERORY",
|
||||
workspace_id=workspace_id
|
||||
)
|
||||
if knowledge:
|
||||
if knowledge:
|
||||
user_rag_memory_id = str(knowledge.id)
|
||||
|
||||
logger.info(
|
||||
@@ -753,23 +728,9 @@ async def draft_run_compare(
|
||||
from app.core.exceptions import ResourceNotFoundException
|
||||
raise ResourceNotFoundException("模型配置", str(model_item.model_config_id))
|
||||
|
||||
# 获取 agent_cfg.model_parameters，如果是 ModelParameters 对象则转为字典
|
||||
agent_model_params = agent_cfg.model_parameters
|
||||
if hasattr(agent_model_params, 'model_dump'):
|
||||
agent_model_params = agent_model_params.model_dump()
|
||||
elif not isinstance(agent_model_params, dict):
|
||||
agent_model_params = {}
|
||||
|
||||
# 获取 model_item.model_parameters，如果是 ModelParameters 对象则转为字典
|
||||
item_model_params = model_item.model_parameters
|
||||
if hasattr(item_model_params, 'model_dump'):
|
||||
item_model_params = item_model_params.model_dump()
|
||||
elif not isinstance(item_model_params, dict):
|
||||
item_model_params = {}
|
||||
|
||||
merged_parameters = {
|
||||
**(agent_model_params or {}),
|
||||
**(item_model_params or {})
|
||||
**(agent_cfg.model_parameters or {}),
|
||||
**(model_item.model_parameters or {})
|
||||
}
|
||||
|
||||
model_configs.append({
|
||||
@@ -786,19 +747,19 @@ async def draft_run_compare(
|
||||
from app.services.draft_run_service import DraftRunService
|
||||
draft_service = DraftRunService(db)
|
||||
async for event in draft_service.run_compare_stream(
|
||||
agent_config=agent_cfg,
|
||||
models=model_configs,
|
||||
message=payload.message,
|
||||
workspace_id=workspace_id,
|
||||
conversation_id=payload.conversation_id,
|
||||
user_id=payload.user_id or str(current_user.id),
|
||||
variables=payload.variables,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
web_search=True,
|
||||
memory=True,
|
||||
parallel=payload.parallel,
|
||||
timeout=payload.timeout or 60
|
||||
agent_config=agent_cfg,
|
||||
models=model_configs,
|
||||
message=payload.message,
|
||||
workspace_id=workspace_id,
|
||||
conversation_id=payload.conversation_id,
|
||||
user_id=payload.user_id or str(current_user.id),
|
||||
variables=payload.variables,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
web_search=True,
|
||||
memory=True,
|
||||
parallel=payload.parallel,
|
||||
timeout=payload.timeout or 60
|
||||
):
|
||||
yield event
|
||||
|
||||
@@ -860,56 +821,15 @@ async def get_workflow_config(
|
||||
# 配置总是存在（不存在时返回默认模板）
|
||||
return success(data=WorkflowConfigSchema.model_validate(cfg))
|
||||
|
||||
|
||||
@router.put("/{app_id}/workflow", summary="更新 Workflow 配置")
|
||||
@cur_workspace_access_guard()
|
||||
async def update_workflow_config(
|
||||
app_id: uuid.UUID,
|
||||
payload: WorkflowConfigUpdate,
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)]
|
||||
app_id: uuid.UUID,
|
||||
payload: WorkflowConfigUpdate,
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)]
|
||||
):
|
||||
workspace_id = current_user.current_workspace_id
|
||||
cfg = app_service.update_workflow_config(db, app_id=app_id, data=payload, workspace_id=workspace_id)
|
||||
return success(data=WorkflowConfigSchema.model_validate(cfg))
|
||||
|
||||
|
||||
@router.get("/{app_id}/statistics", summary="应用统计数据")
|
||||
@cur_workspace_access_guard()
|
||||
def get_app_statistics(
|
||||
app_id: uuid.UUID,
|
||||
start_date: int,
|
||||
end_date: int,
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user),
|
||||
):
|
||||
"""获取应用统计数据
|
||||
|
||||
Args:
|
||||
app_id: 应用ID
|
||||
start_date: 开始时间戳（毫秒）
|
||||
end_date: 结束时间戳（毫秒）
|
||||
|
||||
Returns:
|
||||
- daily_conversations: 每日会话数统计
|
||||
- total_conversations: 总会话数
|
||||
- daily_new_users: 每日新增用户数
|
||||
- total_new_users: 总新增用户数
|
||||
- daily_api_calls: 每日API调用次数
|
||||
- total_api_calls: 总API调用次数
|
||||
- daily_tokens: 每日token消耗
|
||||
- total_tokens: 总token消耗
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
from app.services.app_statistics_service import AppStatisticsService
|
||||
stats_service = AppStatisticsService(db)
|
||||
|
||||
result = stats_service.get_app_statistics(
|
||||
app_id=app_id,
|
||||
workspace_id=workspace_id,
|
||||
start_date=start_date,
|
||||
end_date=end_date
|
||||
)
|
||||
|
||||
return success(data=result)
|
||||
|
||||
@@ -1,28 +1,24 @@
|
||||
import os
|
||||
from typing import Any, Optional
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, status, Query
|
||||
from fastapi.encoders import jsonable_encoder
|
||||
from sqlalchemy.orm import Session
|
||||
from sqlalchemy import func
|
||||
|
||||
from app.core.config import settings
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.rag.common.settings import kg_retriever
|
||||
from app.core.rag.llm.chat_model import Base
|
||||
from app.core.rag.llm.cv_model import QWenCV
|
||||
from app.core.rag.llm.embedding_model import OpenAIEmbed
|
||||
from app.core.rag.models.chunk import DocumentChunk
|
||||
from app.core.rag.vdb.elasticsearch.elasticsearch_vector import ElasticSearchVectorFactory
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.core.rag.llm.cv_model import QWenCV
|
||||
from app.dependencies import get_current_user
|
||||
from app.models import knowledge_model, knowledgeshare_model
|
||||
from app.models.document_model import Document
|
||||
from app.models.user_model import User
|
||||
from app.models.document_model import Document
|
||||
from app.models import knowledge_model, knowledgeshare_model
|
||||
from app.core.rag.models.chunk import DocumentChunk
|
||||
from app.schemas import chunk_schema
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.core.response_utils import success
|
||||
from app.services import knowledge_service, document_service, file_service, knowledgeshare_service
|
||||
from app.core.rag.vdb.elasticsearch.elasticsearch_vector import ElasticSearchVectorFactory
|
||||
from app.core.logging_config import get_api_logger
|
||||
|
||||
# Obtain a dedicated API logger
|
||||
api_logger = get_api_logger()
|
||||
@@ -145,7 +141,7 @@ async def get_preview_chunks(
|
||||
}
|
||||
}
|
||||
api_logger.info(f"Querying the document block preview list successful: total={total}, returned={len(chunks)} records")
|
||||
return success(data=jsonable_encoder(result), msg="Querying the document block preview list succeeded")
|
||||
return success(data=result, msg="Querying the document block preview list succeeded")
|
||||
|
||||
|
||||
@router.get("/{kb_id}/{document_id}/chunks", response_model=ApiResponse)
|
||||
@@ -203,7 +199,7 @@ async def get_chunks(
|
||||
"has_next": True if page * pagesize < total else False
|
||||
}
|
||||
}
|
||||
return success(data=jsonable_encoder(result), msg="Query of document chunk list succeeded")
|
||||
return success(data=result, msg="Query of document chunk list succeeded")
|
||||
|
||||
|
||||
@router.post("/{kb_id}/{document_id}/chunk", response_model=ApiResponse)
|
||||
@@ -264,7 +260,7 @@ async def create_chunk(
|
||||
db_document.chunk_num += 1
|
||||
db.commit()
|
||||
|
||||
return success(data=jsonable_encoder(chunk), msg="Document chunk creation successful")
|
||||
return success(data=chunk, msg="Document chunk creation successful")
|
||||
|
||||
|
||||
@router.get("/{kb_id}/{document_id}/{doc_id}", response_model=ApiResponse)
|
||||
@@ -291,7 +287,7 @@ async def get_chunk(
|
||||
vector_service = ElasticSearchVectorFactory().init_vector(knowledge=db_knowledge)
|
||||
total, items = vector_service.get_by_segment(doc_id=doc_id)
|
||||
if total:
|
||||
return success(data=jsonable_encoder(items[0]), msg="Document chunk query successful")
|
||||
return success(data=items[0], msg="Document chunk query successful")
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
@@ -328,7 +324,7 @@ async def update_chunk(
|
||||
chunk = items[0]
|
||||
chunk.page_content = content
|
||||
vector_service.update_by_segment(chunk)
|
||||
return success(data=jsonable_encoder(chunk), msg="The document chunk has been successfully updated")
|
||||
return success(data=chunk, msg="The document chunk has been successfully updated")
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
@@ -393,41 +389,36 @@ async def retrieve_chunks(
|
||||
knowledge_model.Knowledge.chunk_num > 0,
|
||||
knowledge_model.Knowledge.status == 1
|
||||
]
|
||||
private_items = knowledge_service.get_chunked_knowledgeids(
|
||||
existing_ids = knowledge_service.get_chunded_knowledgeids(
|
||||
db=db,
|
||||
filters=filters,
|
||||
current_user=current_user
|
||||
)
|
||||
private_kb_ids = [item[0] for item in private_items]
|
||||
private_workspace_ids = [item[1] for item in private_items]
|
||||
filters = [
|
||||
knowledge_model.Knowledge.id.in_(retrieve_data.kb_ids),
|
||||
knowledge_model.Knowledge.permission_id == knowledge_model.PermissionType.Share,
|
||||
knowledge_model.Knowledge.chunk_num > 0,
|
||||
knowledge_model.Knowledge.status == 1
|
||||
]
|
||||
items = knowledge_service.get_chunked_knowledgeids(
|
||||
share_ids = knowledge_service.get_chunded_knowledgeids(
|
||||
db=db,
|
||||
filters=filters,
|
||||
current_user=current_user
|
||||
)
|
||||
if items:
|
||||
if share_ids:
|
||||
filters = [
|
||||
knowledgeshare_model.KnowledgeShare.target_kb_id.in_(retrieve_data.kb_ids)
|
||||
]
|
||||
share_items = knowledgeshare_service.get_source_kb_ids_by_target_kb_id(
|
||||
items = knowledgeshare_service.get_source_kb_ids_by_target_kb_id(
|
||||
db=db,
|
||||
filters=filters,
|
||||
current_user=current_user
|
||||
)
|
||||
share_kb_ids = [item[0] for item in share_items]
|
||||
share_workspace_ids = [item[1] for item in share_items]
|
||||
private_kb_ids.extend(share_kb_ids)
|
||||
private_workspace_ids.extend(share_workspace_ids)
|
||||
if not private_kb_ids:
|
||||
existing_ids.extend(items)
|
||||
if not existing_ids:
|
||||
return success(data=[], msg="retrieval successful")
|
||||
kb_id = private_kb_ids[0]
|
||||
uuid_strs = [f"Vector_index_{kb_id}_Node".lower() for kb_id in private_kb_ids]
|
||||
kb_id = existing_ids[0]
|
||||
uuid_strs = [f"Vector_index_{kb_id}_Node".lower() for kb_id in existing_ids]
|
||||
indices = ",".join(uuid_strs)
|
||||
db_knowledge = knowledge_service.get_knowledge_by_id(db, knowledge_id=kb_id, current_user=current_user)
|
||||
if not db_knowledge:
|
||||
@@ -457,21 +448,4 @@ async def retrieve_chunks(
|
||||
seen_ids.add(doc.metadata["doc_id"])
|
||||
unique_rs.append(doc)
|
||||
rs = vector_service.rerank(query=retrieve_data.query, docs=unique_rs, top_k=retrieve_data.top_k)
|
||||
if retrieve_data.retrieve_type == chunk_schema.RetrieveType.Graph:
|
||||
kb_ids = [str(kb_id) for kb_id in private_kb_ids]
|
||||
workspace_ids = [str(workspace_id) for workspace_id in private_workspace_ids]
|
||||
# Prepare to configure chat_mdl、embedding_model、vision_model information
|
||||
chat_model = Base(
|
||||
key=db_knowledge.llm.api_keys[0].api_key,
|
||||
model_name=db_knowledge.llm.api_keys[0].model_name,
|
||||
base_url=db_knowledge.llm.api_keys[0].api_base
|
||||
)
|
||||
embedding_model = OpenAIEmbed(
|
||||
key=db_knowledge.embedding.api_keys[0].api_key,
|
||||
model_name=db_knowledge.embedding.api_keys[0].model_name,
|
||||
base_url=db_knowledge.embedding.api_keys[0].api_base
|
||||
)
|
||||
doc = kg_retriever.retrieval(question=retrieve_data.query, workspace_ids=workspace_ids, kb_ids= kb_ids, emb_mdl=embedding_model, llm=chat_model)
|
||||
if doc:
|
||||
rs.insert(0, doc)
|
||||
return success(data=jsonable_encoder(rs), msg="retrieval successful")
|
||||
return success(data=rs, msg="retrieval successful")
|
||||
@@ -1,26 +1,23 @@
|
||||
import datetime
|
||||
import os
|
||||
from typing import Optional
|
||||
import datetime
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, status, Query
|
||||
from fastapi.encoders import jsonable_encoder
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.celery_app import celery_app
|
||||
from app.controllers import file_controller
|
||||
from app.core.config import settings
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.rag.vdb.elasticsearch.elasticsearch_vector import ElasticSearchVectorFactory
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models import document_model
|
||||
from app.models.user_model import User
|
||||
from app.models import document_model
|
||||
from app.schemas import document_schema
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.core.response_utils import success
|
||||
from app.services import document_service, file_service, knowledge_service
|
||||
|
||||
from app.controllers import file_controller
|
||||
from app.celery_app import celery_app
|
||||
from app.core.rag.vdb.elasticsearch.elasticsearch_vector import ElasticSearchVectorFactory
|
||||
from app.core.logging_config import get_api_logger
|
||||
|
||||
# Obtain a dedicated API logger
|
||||
api_logger = get_api_logger()
|
||||
@@ -109,7 +106,7 @@ async def get_documents(
|
||||
"has_next": True if page * pagesize < total else False
|
||||
}
|
||||
}
|
||||
return success(data=jsonable_encoder(result), msg="Query of document list succeeded")
|
||||
return success(data=result, msg="Query of document list succeeded")
|
||||
|
||||
|
||||
@router.post("/document", response_model=ApiResponse)
|
||||
@@ -127,7 +124,7 @@ async def create_document(
|
||||
api_logger.debug(f"Start creating a document: {create_data.file_name}")
|
||||
db_document = document_service.create_document(db=db, document=create_data, current_user=current_user)
|
||||
api_logger.info(f"Document created successfully: {db_document.file_name} (ID: {db_document.id})")
|
||||
return success(data=jsonable_encoder(document_schema.Document.model_validate(db_document)), msg="Document creation successful")
|
||||
return success(data=document_schema.Document.model_validate(db_document), msg="Document creation successful")
|
||||
except Exception as e:
|
||||
api_logger.error(f"Document creation failed: {create_data.file_name} - {str(e)}")
|
||||
raise
|
||||
@@ -156,7 +153,7 @@ async def get_document(
|
||||
)
|
||||
|
||||
api_logger.info(f"Document query successful: {db_document.file_name} (ID: {db_document.id})")
|
||||
return success(data=jsonable_encoder(document_schema.Document.model_validate(db_document)), msg="Successfully obtained document information")
|
||||
return success(data=document_schema.Document.model_validate(db_document), msg="Successfully obtained document information")
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
@@ -224,7 +221,7 @@ async def update_document(
|
||||
)
|
||||
|
||||
# 5. Return the updated document
|
||||
return success(data=jsonable_encoder(document_schema.Document.model_validate(db_document)), msg="Document information updated successfully")
|
||||
return success(data=document_schema.Document.model_validate(db_document), msg="Document information updated successfully")
|
||||
|
||||
|
||||
@router.delete("/{document_id}", response_model=ApiResponse)
|
||||
|
||||
@@ -7,13 +7,11 @@ Routes:
|
||||
GET /memory/config/emotion - 获取情绪引擎配置
|
||||
POST /memory/config/emotion - 更新情绪引擎配置
|
||||
"""
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Depends, Query, HTTPException, status
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import Optional, Union
|
||||
from typing import Optional
|
||||
from sqlalchemy.orm import Session
|
||||
from uuid import UUID
|
||||
|
||||
from app.core.response_utils import success
|
||||
from app.dependencies import get_current_user
|
||||
@@ -22,7 +20,6 @@ from app.schemas.response_schema import ApiResponse
|
||||
from app.services.emotion_config_service import EmotionConfigService
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.db import get_db
|
||||
from app.utils.config_utils import resolve_config_id
|
||||
|
||||
# 获取API专用日志器
|
||||
api_logger = get_api_logger()
|
||||
@@ -35,11 +32,11 @@ router = APIRouter(
|
||||
|
||||
class EmotionConfigQuery(BaseModel):
|
||||
"""情绪配置查询请求模型"""
|
||||
config_id: UUID = Field(..., description="配置ID")
|
||||
config_id: int = Field(..., description="配置ID")
|
||||
|
||||
class EmotionConfigUpdate(BaseModel):
|
||||
"""情绪配置更新请求模型"""
|
||||
config_id: Union[uuid.UUID, int, str]= Field(..., description="配置ID")
|
||||
config_id: int = Field(..., description="配置ID")
|
||||
emotion_enabled: bool = Field(..., description="是否启用情绪提取")
|
||||
emotion_model_id: Optional[str] = Field(None, description="情绪分析专用模型ID")
|
||||
emotion_extract_keywords: bool = Field(..., description="是否提取情绪关键词")
|
||||
@@ -48,7 +45,7 @@ class EmotionConfigUpdate(BaseModel):
|
||||
|
||||
@router.get("/read_config", response_model=ApiResponse)
|
||||
def get_emotion_config(
|
||||
config_id: UUID|int = Query(..., description="配置ID"),
|
||||
config_id: int = Query(..., description="配置ID"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user),
|
||||
):
|
||||
@@ -81,7 +78,7 @@ def get_emotion_config(
|
||||
f"用户 {current_user.username} 请求获取情绪配置",
|
||||
extra={"config_id": config_id}
|
||||
)
|
||||
config_id=resolve_config_id(config_id, db)
|
||||
|
||||
# 初始化服务
|
||||
config_service = EmotionConfigService(db)
|
||||
|
||||
@@ -160,7 +157,6 @@ def update_emotion_config(
|
||||
}
|
||||
}
|
||||
"""
|
||||
config.config_id=resolve_config_id(config.config_id, db)
|
||||
try:
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 请求更新情绪配置",
|
||||
|
||||
@@ -18,20 +18,19 @@ from app.models.user_model import User
|
||||
from app.schemas.emotion_schema import (
|
||||
EmotionHealthRequest,
|
||||
EmotionSuggestionsRequest,
|
||||
EmotionGenerateSuggestionsRequest,
|
||||
EmotionTagsRequest,
|
||||
EmotionWordcloudRequest,
|
||||
)
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services.emotion_analytics_service import EmotionAnalyticsService
|
||||
from fastapi import APIRouter, Depends, HTTPException, status,Header
|
||||
from fastapi import APIRouter, Depends, HTTPException, status
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
# 获取API专用日志器
|
||||
api_logger = get_api_logger()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/memory/emotion-memory",
|
||||
prefix="/memory/emotion",
|
||||
tags=["Emotion Analysis"],
|
||||
dependencies=[Depends(get_current_user)] # 所有路由都需要认证
|
||||
)
|
||||
@@ -45,7 +44,6 @@ emotion_service = EmotionAnalyticsService()
|
||||
@router.post("/tags", response_model=ApiResponse)
|
||||
async def get_emotion_tags(
|
||||
request: EmotionTagsRequest,
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
current_user: User = Depends(get_current_user),
|
||||
):
|
||||
|
||||
@@ -53,38 +51,38 @@ async def get_emotion_tags(
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 请求获取情绪标签统计",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"group_id": request.group_id,
|
||||
"emotion_type": request.emotion_type,
|
||||
"start_date": request.start_date,
|
||||
"end_date": request.end_date,
|
||||
"limit": request.limit
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
# 调用服务层
|
||||
data = await emotion_service.get_emotion_tags(
|
||||
end_user_id=request.end_user_id,
|
||||
end_user_id=request.group_id,
|
||||
emotion_type=request.emotion_type,
|
||||
start_date=request.start_date,
|
||||
end_date=request.end_date,
|
||||
limit=request.limit
|
||||
)
|
||||
|
||||
|
||||
api_logger.info(
|
||||
"情绪标签统计获取成功",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"group_id": request.group_id,
|
||||
"total_count": data.get("total_count", 0),
|
||||
"tags_count": len(data.get("tags", []))
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
return success(data=data, msg="情绪标签获取成功")
|
||||
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(
|
||||
f"获取情绪标签统计失败: {str(e)}",
|
||||
extra={"end_user_id": request.end_user_id},
|
||||
extra={"group_id": request.group_id},
|
||||
exc_info=True
|
||||
)
|
||||
raise HTTPException(
|
||||
@@ -97,7 +95,6 @@ async def get_emotion_tags(
|
||||
@router.post("/wordcloud", response_model=ApiResponse)
|
||||
async def get_emotion_wordcloud(
|
||||
request: EmotionWordcloudRequest,
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
current_user: User = Depends(get_current_user),
|
||||
):
|
||||
|
||||
@@ -105,33 +102,33 @@ async def get_emotion_wordcloud(
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 请求获取情绪词云数据",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"group_id": request.group_id,
|
||||
"emotion_type": request.emotion_type,
|
||||
"limit": request.limit
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
# 调用服务层
|
||||
data = await emotion_service.get_emotion_wordcloud(
|
||||
end_user_id=request.end_user_id,
|
||||
end_user_id=request.group_id,
|
||||
emotion_type=request.emotion_type,
|
||||
limit=request.limit
|
||||
)
|
||||
|
||||
|
||||
api_logger.info(
|
||||
"情绪词云数据获取成功",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"group_id": request.group_id,
|
||||
"total_keywords": data.get("total_keywords", 0)
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
return success(data=data, msg="情绪词云获取成功")
|
||||
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(
|
||||
f"获取情绪词云数据失败: {str(e)}",
|
||||
extra={"end_user_id": request.end_user_id},
|
||||
extra={"group_id": request.group_id},
|
||||
exc_info=True
|
||||
)
|
||||
raise HTTPException(
|
||||
@@ -144,7 +141,6 @@ async def get_emotion_wordcloud(
|
||||
@router.post("/health", response_model=ApiResponse)
|
||||
async def get_emotion_health(
|
||||
request: EmotionHealthRequest,
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
current_user: User = Depends(get_current_user),
|
||||
):
|
||||
|
||||
@@ -155,38 +151,38 @@ async def get_emotion_health(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail="时间范围参数无效，必须是 7d、30d 或 90d"
|
||||
)
|
||||
|
||||
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 请求获取情绪健康指数",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"group_id": request.group_id,
|
||||
"time_range": request.time_range
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
# 调用服务层
|
||||
data = await emotion_service.calculate_emotion_health_index(
|
||||
end_user_id=request.end_user_id,
|
||||
end_user_id=request.group_id,
|
||||
time_range=request.time_range
|
||||
)
|
||||
|
||||
|
||||
api_logger.info(
|
||||
"情绪健康指数获取成功",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"group_id": request.group_id,
|
||||
"health_score": data.get("health_score", 0),
|
||||
"level": data.get("level", "未知")
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
return success(data=data, msg="情绪健康指数获取成功")
|
||||
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
api_logger.error(
|
||||
f"获取情绪健康指数失败: {str(e)}",
|
||||
extra={"end_user_id": request.end_user_id},
|
||||
extra={"group_id": request.group_id},
|
||||
exc_info=True
|
||||
)
|
||||
raise HTTPException(
|
||||
@@ -199,125 +195,75 @@ async def get_emotion_health(
|
||||
@router.post("/suggestions", response_model=ApiResponse)
|
||||
async def get_emotion_suggestions(
|
||||
request: EmotionSuggestionsRequest,
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user),
|
||||
):
|
||||
"""获取个性化情绪建议（从缓存读取）
|
||||
|
||||
"""获取个性化情绪建议
|
||||
|
||||
Args:
|
||||
request: 包含 end_user_id 和可选的 config_id
|
||||
request: 包含 group_id 和可选的 config_id
|
||||
db: 数据库会话
|
||||
current_user: 当前用户
|
||||
|
||||
|
||||
Returns:
|
||||
缓存的个性化情绪建议响应
|
||||
个性化情绪建议响应
|
||||
"""
|
||||
try:
|
||||
# 验证 config_id（如果提供）
|
||||
# 获取终端用户关联的配置
|
||||
config_id = request.config_id
|
||||
if config_id is None:
|
||||
# 如果没有提供 config_id，尝试获取用户关联的配置
|
||||
try:
|
||||
from app.services.memory_agent_service import (
|
||||
get_end_user_connected_config,
|
||||
)
|
||||
connected_config = get_end_user_connected_config(request.group_id, db)
|
||||
config_id = connected_config.get("memory_config_id")
|
||||
except ValueError as e:
|
||||
return fail(BizCode.INVALID_PARAMETER, "无法获取用户关联的配置", str(e))
|
||||
else:
|
||||
# 如果提供了 config_id，验证其有效性
|
||||
from app.services.memory_config_service import MemoryConfigService
|
||||
try:
|
||||
config_service = MemoryConfigService(db)
|
||||
config = config_service.get_config_by_id(config_id)
|
||||
if not config:
|
||||
return fail(BizCode.INVALID_PARAMETER, "配置ID无效", f"配置 {config_id} 不存在")
|
||||
except Exception as e:
|
||||
return fail(BizCode.INVALID_PARAMETER, "配置ID验证失败", str(e))
|
||||
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 请求获取个性化情绪建议（缓存）",
|
||||
f"用户 {current_user.username} 请求获取个性化情绪建议",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"config_id": request.config_id
|
||||
"group_id": request.group_id,
|
||||
"config_id": config_id
|
||||
}
|
||||
)
|
||||
|
||||
# 从缓存获取建议
|
||||
data = await emotion_service.get_cached_suggestions(
|
||||
end_user_id=request.end_user_id,
|
||||
|
||||
# 调用服务层
|
||||
data = await emotion_service.generate_emotion_suggestions(
|
||||
end_user_id=request.group_id,
|
||||
db=db
|
||||
)
|
||||
|
||||
if data is None:
|
||||
# 缓存不存在或已过期
|
||||
api_logger.info(
|
||||
f"用户 {request.end_user_id} 的建议缓存不存在或已过期",
|
||||
extra={"end_user_id": request.end_user_id}
|
||||
)
|
||||
return fail(
|
||||
BizCode.NOT_FOUND,
|
||||
"建议缓存不存在或已过期，请右上角刷新生成新建议",
|
||||
""
|
||||
)
|
||||
|
||||
|
||||
api_logger.info(
|
||||
"个性化建议获取成功（缓存）",
|
||||
"个性化建议获取成功",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"group_id": request.group_id,
|
||||
"suggestions_count": len(data.get("suggestions", []))
|
||||
}
|
||||
)
|
||||
|
||||
return success(data=data, msg="个性化建议获取成功（缓存）")
|
||||
|
||||
|
||||
return success(data=data, msg="个性化建议获取成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(
|
||||
f"获取个性化建议失败: {str(e)}",
|
||||
extra={"end_user_id": request.end_user_id},
|
||||
extra={"group_id": request.group_id},
|
||||
exc_info=True
|
||||
)
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"获取个性化建议失败: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
@router.post("/generate_suggestions", response_model=ApiResponse)
|
||||
async def generate_emotion_suggestions(
|
||||
request: EmotionGenerateSuggestionsRequest,
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user),
|
||||
):
|
||||
"""生成个性化情绪建议（调用LLM并缓存）
|
||||
|
||||
Args:
|
||||
request: 包含 end_user_id
|
||||
db: 数据库会话
|
||||
current_user: 当前用户
|
||||
|
||||
Returns:
|
||||
新生成的个性化情绪建议响应
|
||||
"""
|
||||
try:
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 请求生成个性化情绪建议",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id
|
||||
}
|
||||
)
|
||||
|
||||
# 调用服务层生成建议
|
||||
data = await emotion_service.generate_emotion_suggestions(
|
||||
end_user_id=request.end_user_id,
|
||||
db=db
|
||||
)
|
||||
|
||||
# 保存到缓存
|
||||
await emotion_service.save_suggestions_cache(
|
||||
end_user_id=request.end_user_id,
|
||||
suggestions_data=data,
|
||||
db=db,
|
||||
expires_hours=24
|
||||
)
|
||||
|
||||
api_logger.info(
|
||||
"个性化建议生成成功",
|
||||
extra={
|
||||
"end_user_id": request.end_user_id,
|
||||
"suggestions_count": len(data.get("suggestions", []))
|
||||
}
|
||||
)
|
||||
|
||||
return success(data=data, msg="个性化建议生成成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(
|
||||
f"生成个性化建议失败: {str(e)}",
|
||||
extra={"end_user_id": request.end_user_id},
|
||||
exc_info=True
|
||||
)
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"生成个性化建议失败: {str(e)}"
|
||||
)
|
||||
|
||||
@@ -1,25 +1,22 @@
|
||||
import os
|
||||
from typing import Any, Optional
|
||||
from pathlib import Path
|
||||
import shutil
|
||||
from typing import Any, Optional
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, status, File, UploadFile, Query
|
||||
from fastapi.encoders import jsonable_encoder
|
||||
from fastapi.responses import FileResponse
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.config import settings
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models import file_model
|
||||
from app.models.user_model import User
|
||||
from app.models import file_model
|
||||
from app.schemas import file_schema, document_schema
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.core.response_utils import success
|
||||
from app.services import file_service, document_service
|
||||
|
||||
from app.core.logging_config import get_api_logger
|
||||
|
||||
# Obtain a dedicated API logger
|
||||
api_logger = get_api_logger()
|
||||
@@ -96,11 +93,11 @@ async def get_files(
|
||||
"has_next": True if page * pagesize < total else False
|
||||
}
|
||||
}
|
||||
return success(data=jsonable_encoder(result), msg="Query of file list succeeded")
|
||||
return success(data=result, msg="Query of file list succeeded")
|
||||
|
||||
|
||||
@router.post("/folder", response_model=ApiResponse)
|
||||
async def create_folder(
|
||||
def create_folder(
|
||||
kb_id: uuid.UUID,
|
||||
parent_id: uuid.UUID,
|
||||
folder_name: str = '/',
|
||||
@@ -124,7 +121,7 @@ async def create_folder(
|
||||
)
|
||||
db_file = file_service.create_file(db=db, file=create_folder, current_user=current_user)
|
||||
api_logger.info(f"Folder created successfully: {db_file.file_name} (ID: {db_file.id})")
|
||||
return success(data=jsonable_encoder(file_schema.File.model_validate(db_file)), msg="Folder creation successful")
|
||||
return success(data=file_schema.File.model_validate(db_file), msg="Folder creation successful")
|
||||
except Exception as e:
|
||||
api_logger.error(f"Folder creation failed: {folder_name} - {str(e)}")
|
||||
raise
|
||||
@@ -210,7 +207,7 @@ async def upload_file(
|
||||
db_document = document_service.create_document(db=db, document=create_data, current_user=current_user)
|
||||
|
||||
api_logger.info(f"File upload successfully: {file.filename} (file_id: {db_file.id}, document_id: {db_document.id})")
|
||||
return success(data=jsonable_encoder(document_schema.Document.model_validate(db_document)), msg="File upload successful")
|
||||
return success(data=document_schema.Document.model_validate(db_document), msg="File upload successful")
|
||||
|
||||
|
||||
@router.post("/customtext", response_model=ApiResponse)
|
||||
@@ -291,7 +288,7 @@ async def custom_text(
|
||||
db_document = document_service.create_document(db=db, document=create_document_data, current_user=current_user)
|
||||
|
||||
api_logger.info(f"custom text upload successfully: {create_data.title} (file_id: {db_file.id}, document_id: {db_document.id})")
|
||||
return success(data=jsonable_encoder(document_schema.Document.model_validate(db_document)), msg="custom text upload successful")
|
||||
return success(data=document_schema.Document.model_validate(db_document), msg="custom text upload successful")
|
||||
|
||||
|
||||
@router.get("/{file_id}", response_model=Any)
|
||||
@@ -365,7 +362,7 @@ async def update_file(
|
||||
# 2. Update fields (only update non-null fields)
|
||||
api_logger.debug(f"Start updating the file fields: {file_id}")
|
||||
updated_fields = []
|
||||
for field, value in update_data.dict(exclude_unset=True).items():
|
||||
for field, value in update_data.items():
|
||||
if hasattr(db_file, field):
|
||||
old_value = getattr(db_file, field)
|
||||
if old_value != value:
|
||||
@@ -390,7 +387,7 @@ async def update_file(
|
||||
)
|
||||
|
||||
# 4. Return the updated file
|
||||
return success(data=jsonable_encoder(file_schema.File.model_validate(db_file)), msg="File information updated successfully")
|
||||
return success(data=file_schema.File.model_validate(db_file), msg="File information updated successfully")
|
||||
|
||||
|
||||
@router.delete("/{file_id}", response_model=ApiResponse)
|
||||
|
||||
@@ -1,499 +0,0 @@
|
||||
"""
|
||||
File storage controller module.
|
||||
|
||||
This module provides API endpoints for file storage operations using the
|
||||
configurable storage backend. It is a new controller that does not modify
|
||||
the existing file_controller.py.
|
||||
|
||||
Routes:
|
||||
POST /storage/files - Upload a file
|
||||
GET /storage/files/{file_id} - Download a file
|
||||
DELETE /storage/files/{file_id} - Delete a file
|
||||
"""
|
||||
|
||||
import os
|
||||
import uuid
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status
|
||||
from fastapi.responses import FileResponse, RedirectResponse
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.config import settings
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import success
|
||||
from app.core.storage import LocalStorage
|
||||
from app.core.storage.url_signer import generate_signed_url, verify_signed_url
|
||||
from app.core.storage_exceptions import (
|
||||
StorageDeleteError,
|
||||
StorageUploadError,
|
||||
)
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.file_metadata_model import FileMetadata
|
||||
from app.models.user_model import User
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services.file_storage_service import (
|
||||
FileStorageService,
|
||||
generate_file_key,
|
||||
get_file_storage_service,
|
||||
)
|
||||
|
||||
api_logger = get_api_logger()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/storage",
|
||||
tags=["storage"]
|
||||
)
|
||||
|
||||
|
||||
@router.post("/files", response_model=ApiResponse)
|
||||
async def upload_file(
|
||||
file: UploadFile = File(...),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user),
|
||||
storage_service: FileStorageService = Depends(get_file_storage_service),
|
||||
):
|
||||
"""
|
||||
Upload a file to the configured storage backend.
|
||||
"""
|
||||
tenant_id = current_user.tenant_id
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
api_logger.info(
|
||||
f"Storage upload request: tenant_id={tenant_id}, workspace_id={workspace_id}, "
|
||||
f"filename={file.filename}, username={current_user.username}"
|
||||
)
|
||||
|
||||
# Read file contents
|
||||
contents = await file.read()
|
||||
file_size = len(contents)
|
||||
|
||||
# Validate file size
|
||||
if file_size == 0:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail="The file is empty."
|
||||
)
|
||||
|
||||
if file_size > settings.MAX_FILE_SIZE:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail=f"The file size exceeds the {settings.MAX_FILE_SIZE} byte limit"
|
||||
)
|
||||
|
||||
# Extract file extension
|
||||
_, file_extension = os.path.splitext(file.filename)
|
||||
file_ext = file_extension.lower()
|
||||
|
||||
# Generate file_id and file_key
|
||||
file_id = uuid.uuid4()
|
||||
file_key = generate_file_key(
|
||||
tenant_id=tenant_id,
|
||||
workspace_id=workspace_id,
|
||||
file_id=file_id,
|
||||
file_ext=file_ext,
|
||||
)
|
||||
|
||||
# Create file metadata record with pending status
|
||||
file_metadata = FileMetadata(
|
||||
id=file_id,
|
||||
tenant_id=tenant_id,
|
||||
workspace_id=workspace_id,
|
||||
file_key=file_key,
|
||||
file_name=file.filename,
|
||||
file_ext=file_ext,
|
||||
file_size=file_size,
|
||||
content_type=file.content_type,
|
||||
status="pending",
|
||||
)
|
||||
db.add(file_metadata)
|
||||
db.commit()
|
||||
db.refresh(file_metadata)
|
||||
|
||||
# Upload file to storage backend
|
||||
try:
|
||||
await storage_service.upload_file(
|
||||
tenant_id=tenant_id,
|
||||
workspace_id=workspace_id,
|
||||
file_id=file_id,
|
||||
file_ext=file_ext,
|
||||
content=contents,
|
||||
content_type=file.content_type,
|
||||
)
|
||||
# Update status to completed
|
||||
file_metadata.status = "completed"
|
||||
db.commit()
|
||||
api_logger.info(f"File uploaded to storage: file_key={file_key}")
|
||||
except StorageUploadError as e:
|
||||
# Update status to failed
|
||||
file_metadata.status = "failed"
|
||||
db.commit()
|
||||
api_logger.error(f"Storage upload failed: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"File storage failed: {str(e)}"
|
||||
)
|
||||
|
||||
api_logger.info(f"File upload successful: {file.filename} (file_id: {file_id})")
|
||||
|
||||
return success(
|
||||
data={"file_id": str(file_id), "file_key": file_key},
|
||||
msg="File upload successful"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/files/{file_id}", response_model=Any)
|
||||
async def download_file(
|
||||
file_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user),
|
||||
storage_service: FileStorageService = Depends(get_file_storage_service),
|
||||
) -> Any:
|
||||
"""
|
||||
Download a file from the configured storage backend.
|
||||
"""
|
||||
api_logger.info(f"Storage download request: file_id={file_id}")
|
||||
|
||||
# Query file metadata from database
|
||||
file_metadata = db.query(FileMetadata).filter(FileMetadata.id == file_id).first()
|
||||
if not file_metadata:
|
||||
api_logger.warning(f"File not found in database: file_id={file_id}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="The file does not exist"
|
||||
)
|
||||
|
||||
if file_metadata.status != "completed":
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail=f"File upload not completed, status: {file_metadata.status}"
|
||||
)
|
||||
|
||||
file_key = file_metadata.file_key
|
||||
storage = storage_service.storage
|
||||
|
||||
if isinstance(storage, LocalStorage):
|
||||
full_path = storage._get_full_path(file_key)
|
||||
|
||||
if not full_path.exists():
|
||||
api_logger.warning(f"File not found on disk: file_key={file_key}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="File not found (possibly deleted)"
|
||||
)
|
||||
|
||||
api_logger.info(f"Serving local file: file_key={file_key}")
|
||||
return FileResponse(
|
||||
path=str(full_path),
|
||||
filename=file_metadata.file_name,
|
||||
media_type=file_metadata.content_type or "application/octet-stream"
|
||||
)
|
||||
else:
|
||||
try:
|
||||
presigned_url = await storage_service.get_file_url(file_key, expires=3600)
|
||||
api_logger.info(f"Redirecting to presigned URL: file_key={file_key}")
|
||||
return RedirectResponse(url=presigned_url, status_code=status.HTTP_302_FOUND)
|
||||
except FileNotFoundError:
|
||||
api_logger.warning(f"File not found in remote storage: file_key={file_key}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="File not found in storage"
|
||||
)
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to get presigned URL: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"Failed to retrieve file: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
@router.delete("/files/{file_id}", response_model=ApiResponse)
|
||||
async def delete_file(
|
||||
file_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user),
|
||||
storage_service: FileStorageService = Depends(get_file_storage_service),
|
||||
):
|
||||
"""
|
||||
Delete a file from the configured storage backend.
|
||||
"""
|
||||
api_logger.info(
|
||||
f"Storage delete request: file_id={file_id}, username={current_user.username}"
|
||||
)
|
||||
|
||||
# Query file metadata from database
|
||||
file_metadata = db.query(FileMetadata).filter(FileMetadata.id == file_id).first()
|
||||
if not file_metadata:
|
||||
api_logger.warning(f"File not found in database: file_id={file_id}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="The file does not exist"
|
||||
)
|
||||
|
||||
file_key = file_metadata.file_key
|
||||
|
||||
# Delete file from storage
|
||||
try:
|
||||
deleted = await storage_service.delete_file(file_key)
|
||||
if deleted:
|
||||
api_logger.info(f"File deleted from storage: file_key={file_key}")
|
||||
else:
|
||||
api_logger.info(f"File did not exist in storage: file_key={file_key}")
|
||||
except StorageDeleteError as e:
|
||||
api_logger.error(f"Storage delete failed: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"Failed to delete file from storage: {str(e)}"
|
||||
)
|
||||
|
||||
# Delete database record
|
||||
try:
|
||||
db.delete(file_metadata)
|
||||
db.commit()
|
||||
api_logger.info(f"File record deleted from database: file_id={file_id}")
|
||||
except Exception as e:
|
||||
api_logger.error(f"Database delete failed: {e}")
|
||||
db.rollback()
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"Failed to delete file record: {str(e)}"
|
||||
)
|
||||
|
||||
return success(msg="File deleted successfully")
|
||||
|
||||
|
||||
@router.get("/files/{file_id}/url", response_model=ApiResponse)
|
||||
async def get_file_url(
|
||||
file_id: uuid.UUID,
|
||||
expires: int = None,
|
||||
permanent: bool = False,
|
||||
db: Session = Depends(get_db),
|
||||
storage_service: FileStorageService = Depends(get_file_storage_service),
|
||||
):
|
||||
"""
|
||||
Get an access URL for a file (no authentication required).
|
||||
|
||||
Args:
|
||||
file_id: The UUID of the file.
|
||||
expires: URL validity period in seconds (default from FILE_URL_EXPIRES env).
|
||||
permanent: If True, return a permanent URL without expiration.
|
||||
db: Database session.
|
||||
storage_service: The file storage service.
|
||||
|
||||
Returns:
|
||||
ApiResponse with the access URL.
|
||||
"""
|
||||
if expires is None:
|
||||
expires = settings.FILE_URL_EXPIRES
|
||||
|
||||
api_logger.info(f"Get file URL request: file_id={file_id}, expires={expires}, permanent={permanent}")
|
||||
|
||||
# Query file metadata from database
|
||||
file_metadata = db.query(FileMetadata).filter(FileMetadata.id == file_id).first()
|
||||
if not file_metadata:
|
||||
api_logger.warning(f"File not found in database: file_id={file_id}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="The file does not exist"
|
||||
)
|
||||
|
||||
if file_metadata.status != "completed":
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail=f"File upload not completed, status: {file_metadata.status}"
|
||||
)
|
||||
|
||||
file_key = file_metadata.file_key
|
||||
storage = storage_service.storage
|
||||
|
||||
try:
|
||||
if permanent:
|
||||
# Generate permanent URL (no expiration check)
|
||||
server_url = settings.FILE_LOCAL_SERVER_URL
|
||||
url = f"{server_url}/storage/permanent/{file_id}"
|
||||
return success(
|
||||
data={
|
||||
"url": url,
|
||||
"expires_in": None,
|
||||
"permanent": True,
|
||||
"file_name": file_metadata.file_name,
|
||||
},
|
||||
msg="Permanent file URL generated successfully"
|
||||
)
|
||||
|
||||
if isinstance(storage, LocalStorage):
|
||||
# For local storage, generate signed URL with expiration
|
||||
url = generate_signed_url(str(file_id), expires)
|
||||
else:
|
||||
# For remote storage (OSS/S3), get presigned URL
|
||||
url = await storage_service.get_file_url(file_key, expires=expires)
|
||||
|
||||
api_logger.info(f"Generated file URL: file_id={file_id}")
|
||||
return success(
|
||||
data={
|
||||
"url": url,
|
||||
"expires_in": expires,
|
||||
"permanent": False,
|
||||
"file_name": file_metadata.file_name,
|
||||
},
|
||||
msg="File URL generated successfully"
|
||||
)
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to generate file URL: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"Failed to generate file URL: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/public/{file_id}", response_model=Any)
|
||||
async def public_download_file(
|
||||
file_id: uuid.UUID,
|
||||
expires: int = 0,
|
||||
signature: str = "",
|
||||
db: Session = Depends(get_db),
|
||||
storage_service: FileStorageService = Depends(get_file_storage_service),
|
||||
) -> Any:
|
||||
"""
|
||||
Public file download endpoint with signature verification.
|
||||
|
||||
This endpoint allows downloading files without authentication,
|
||||
but requires a valid signature and non-expired timestamp.
|
||||
|
||||
Args:
|
||||
file_id: The UUID of the file.
|
||||
expires: Expiration timestamp.
|
||||
signature: HMAC signature for verification.
|
||||
db: Database session.
|
||||
storage_service: The file storage service.
|
||||
|
||||
Returns:
|
||||
FileResponse for the requested file.
|
||||
"""
|
||||
api_logger.info(f"Public download request: file_id={file_id}")
|
||||
|
||||
# Verify signature
|
||||
is_valid, error_msg = verify_signed_url(str(file_id), expires, signature)
|
||||
if not is_valid:
|
||||
api_logger.warning(f"Invalid signed URL: file_id={file_id}, error={error_msg}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_403_FORBIDDEN,
|
||||
detail=error_msg
|
||||
)
|
||||
|
||||
# Query file metadata from database
|
||||
file_metadata = db.query(FileMetadata).filter(FileMetadata.id == file_id).first()
|
||||
if not file_metadata:
|
||||
api_logger.warning(f"File not found in database: file_id={file_id}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="The file does not exist"
|
||||
)
|
||||
|
||||
if file_metadata.status != "completed":
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail=f"File upload not completed, status: {file_metadata.status}"
|
||||
)
|
||||
|
||||
file_key = file_metadata.file_key
|
||||
storage = storage_service.storage
|
||||
|
||||
if isinstance(storage, LocalStorage):
|
||||
full_path = storage._get_full_path(file_key)
|
||||
|
||||
if not full_path.exists():
|
||||
api_logger.warning(f"File not found on disk: file_key={file_key}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="File not found"
|
||||
)
|
||||
|
||||
api_logger.info(f"Serving public file: file_key={file_key}")
|
||||
return FileResponse(
|
||||
path=str(full_path),
|
||||
filename=file_metadata.file_name,
|
||||
media_type=file_metadata.content_type or "application/octet-stream"
|
||||
)
|
||||
else:
|
||||
# For remote storage, redirect to presigned URL
|
||||
try:
|
||||
presigned_url = await storage_service.get_file_url(file_key, expires=3600)
|
||||
return RedirectResponse(url=presigned_url, status_code=status.HTTP_302_FOUND)
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to get presigned URL: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"Failed to retrieve file: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/permanent/{file_id}", response_model=Any)
|
||||
async def permanent_download_file(
|
||||
file_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
storage_service: FileStorageService = Depends(get_file_storage_service),
|
||||
) -> Any:
|
||||
"""
|
||||
Permanent file download endpoint (no expiration, no signature required).
|
||||
|
||||
This endpoint allows downloading files without authentication or expiration.
|
||||
Use with caution as URLs are permanently accessible.
|
||||
|
||||
Args:
|
||||
file_id: The UUID of the file.
|
||||
db: Database session.
|
||||
storage_service: The file storage service.
|
||||
|
||||
Returns:
|
||||
FileResponse for the requested file.
|
||||
"""
|
||||
api_logger.info(f"Permanent download request: file_id={file_id}")
|
||||
|
||||
# Query file metadata from database
|
||||
file_metadata = db.query(FileMetadata).filter(FileMetadata.id == file_id).first()
|
||||
if not file_metadata:
|
||||
api_logger.warning(f"File not found in database: file_id={file_id}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="The file does not exist"
|
||||
)
|
||||
|
||||
if file_metadata.status != "completed":
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail=f"File upload not completed, status: {file_metadata.status}"
|
||||
)
|
||||
|
||||
file_key = file_metadata.file_key
|
||||
storage = storage_service.storage
|
||||
|
||||
if isinstance(storage, LocalStorage):
|
||||
full_path = storage._get_full_path(file_key)
|
||||
|
||||
if not full_path.exists():
|
||||
api_logger.warning(f"File not found on disk: file_key={file_key}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="File not found"
|
||||
)
|
||||
|
||||
api_logger.info(f"Serving permanent file: file_key={file_key}")
|
||||
return FileResponse(
|
||||
path=str(full_path),
|
||||
filename=file_metadata.file_name,
|
||||
media_type=file_metadata.content_type or "application/octet-stream"
|
||||
)
|
||||
else:
|
||||
# For remote storage, redirect to presigned URL with long expiration
|
||||
try:
|
||||
# Use a very long expiration (7 days max for most cloud providers)
|
||||
presigned_url = await storage_service.get_file_url(file_key, expires=604800)
|
||||
return RedirectResponse(url=presigned_url, status_code=status.HTTP_302_FOUND)
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to get presigned URL: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"Failed to retrieve file: {str(e)}"
|
||||
)
|
||||
@@ -1,44 +0,0 @@
|
||||
from fastapi import APIRouter, Depends
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.config import settings
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.user_model import User
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services.home_page_service import HomePageService
|
||||
|
||||
router = APIRouter(prefix="/home-page", tags=["Home Page"])
|
||||
|
||||
@router.get("/statistics", response_model=ApiResponse)
|
||||
def get_home_statistics(
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""获取首页统计数据"""
|
||||
statistics = HomePageService.get_home_statistics(db, current_user.tenant_id)
|
||||
return success(data=statistics, msg="统计数据获取成功")
|
||||
|
||||
@router.get("/workspaces", response_model=ApiResponse)
|
||||
def get_workspace_list(
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""获取工作空间列表"""
|
||||
workspace_list = HomePageService.get_workspace_list(db, current_user.tenant_id)
|
||||
return success(data=workspace_list, msg="工作空间列表获取成功")
|
||||
|
||||
@router.get("/version", response_model=ApiResponse)
|
||||
def get_system_version():
|
||||
"""获取系统版本号+说明"""
|
||||
current_version = settings.SYSTEM_VERSION
|
||||
version_info = HomePageService.load_version_introduction(current_version)
|
||||
return success(
|
||||
data={
|
||||
"version": current_version,
|
||||
"introduction": version_info.get("introduction"),
|
||||
"introduction_en": version_info.get("introduction_en")
|
||||
},
|
||||
msg="系统版本获取成功"
|
||||
)
|
||||
@@ -1,431 +0,0 @@
|
||||
from datetime import datetime
|
||||
from typing import Optional
|
||||
|
||||
from app.core.error_codes import BizCode
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import fail, success
|
||||
from app.db import get_db
|
||||
from app.dependencies import (
|
||||
cur_workspace_access_guard,
|
||||
get_current_user,
|
||||
)
|
||||
from app.models.user_model import User
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.schemas.implicit_memory_schema import GenerateProfileRequest
|
||||
from app.services.implicit_memory_service import ImplicitMemoryService
|
||||
from fastapi import APIRouter, Depends, Query
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
api_logger = get_api_logger()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/memory/implicit-memory",
|
||||
tags=["Implicit Memory"],
|
||||
)
|
||||
|
||||
|
||||
def handle_implicit_memory_error(e: Exception, operation: str, user_id: str = None) -> dict:
|
||||
"""
|
||||
Centralized error handling for implicit memory operations.
|
||||
|
||||
Args:
|
||||
e: The exception that occurred
|
||||
operation: Description of the operation that failed
|
||||
user_id: Optional user ID for logging context
|
||||
|
||||
Returns:
|
||||
Standardized error response
|
||||
"""
|
||||
error_context = f"user_id={user_id}" if user_id else "unknown user"
|
||||
|
||||
if isinstance(e, ValueError):
|
||||
if "user" in str(e).lower() and "not found" in str(e).lower():
|
||||
api_logger.warning(f"Invalid user ID for {operation}: {error_context}")
|
||||
return fail(BizCode.INVALID_USER_ID, "无效的用户ID", str(e))
|
||||
elif "insufficient" in str(e).lower() or "no data" in str(e).lower():
|
||||
api_logger.warning(f"Insufficient data for {operation}: {error_context}")
|
||||
return fail(BizCode.INSUFFICIENT_DATA, "数据不足，无法进行分析", str(e))
|
||||
else:
|
||||
api_logger.warning(f"Invalid parameters for {operation}: {error_context}")
|
||||
return fail(BizCode.INVALID_FILTER_PARAMS, "无效的参数", str(e))
|
||||
|
||||
elif isinstance(e, KeyError):
|
||||
api_logger.warning(f"Missing required data for {operation}: {error_context}")
|
||||
return fail(BizCode.INSUFFICIENT_DATA, "缺少必要的数据", str(e))
|
||||
|
||||
elif isinstance(e, (ConnectionError, TimeoutError)):
|
||||
api_logger.error(f"Service unavailable for {operation}: {error_context}")
|
||||
return fail(BizCode.SERVICE_UNAVAILABLE, "服务暂时不可用", str(e))
|
||||
|
||||
elif "analysis" in str(e).lower() or "llm" in str(e).lower():
|
||||
api_logger.error(f"Analysis failed for {operation}: {error_context}", exc_info=True)
|
||||
return fail(BizCode.ANALYSIS_FAILED, "分析处理失败", str(e))
|
||||
|
||||
elif "storage" in str(e).lower() or "database" in str(e).lower():
|
||||
api_logger.error(f"Storage error for {operation}: {error_context}", exc_info=True)
|
||||
return fail(BizCode.PROFILE_STORAGE_ERROR, "数据存储失败", str(e))
|
||||
|
||||
else:
|
||||
api_logger.error(f"Unexpected error for {operation}: {error_context}", exc_info=True)
|
||||
return fail(BizCode.INTERNAL_ERROR, f"{operation}失败", str(e))
|
||||
|
||||
|
||||
def validate_user_id(user_id: str) -> None:
|
||||
"""
|
||||
Validate user ID format and constraints.
|
||||
|
||||
Args:
|
||||
user_id: User ID to validate
|
||||
|
||||
Raises:
|
||||
ValueError: If user ID is invalid
|
||||
"""
|
||||
if not user_id or not user_id.strip():
|
||||
raise ValueError("User ID cannot be empty")
|
||||
|
||||
if len(user_id.strip()) < 1:
|
||||
raise ValueError("User ID is too short")
|
||||
|
||||
|
||||
def validate_date_range(start_date: Optional[datetime], end_date: Optional[datetime]) -> None:
|
||||
"""
|
||||
Validate date range parameters.
|
||||
|
||||
Args:
|
||||
start_date: Start date
|
||||
end_date: End date
|
||||
|
||||
Raises:
|
||||
ValueError: If date range is invalid
|
||||
"""
|
||||
if (start_date and not end_date) or (end_date and not start_date):
|
||||
raise ValueError("Both start_date and end_date must be provided together")
|
||||
|
||||
if start_date and end_date and start_date >= end_date:
|
||||
raise ValueError("start_date must be before end_date")
|
||||
|
||||
if start_date and start_date > datetime.now():
|
||||
raise ValueError("start_date cannot be in the future")
|
||||
|
||||
|
||||
def validate_confidence_threshold(threshold: float) -> None:
|
||||
"""
|
||||
Validate confidence threshold parameter.
|
||||
|
||||
Args:
|
||||
threshold: Confidence threshold to validate
|
||||
|
||||
Raises:
|
||||
ValueError: If threshold is invalid
|
||||
"""
|
||||
if not 0.0 <= threshold <= 1.0:
|
||||
raise ValueError("confidence_threshold must be between 0.0 and 1.0")
|
||||
|
||||
|
||||
@router.get("/preferences/{end_user_id}", response_model=ApiResponse)
|
||||
@cur_workspace_access_guard()
|
||||
async def get_preference_tags(
|
||||
end_user_id: str,
|
||||
confidence_threshold: float = Query(0.5, ge=0.0, le=1.0, description="Minimum confidence threshold"),
|
||||
tag_category: Optional[str] = Query(None, description="Filter by tag category"),
|
||||
start_date: Optional[datetime] = Query(None, description="Filter start date"),
|
||||
end_date: Optional[datetime] = Query(None, description="Filter end date"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
) -> ApiResponse:
|
||||
"""
|
||||
Get user preference tags from cache.
|
||||
|
||||
Args:
|
||||
end_user_id: Target end user ID
|
||||
confidence_threshold: Minimum confidence score (0.0-1.0)
|
||||
tag_category: Optional category filter
|
||||
start_date: Optional start date filter
|
||||
end_date: Optional end date filter
|
||||
|
||||
Returns:
|
||||
List of preference tags from cache
|
||||
"""
|
||||
api_logger.info(f"Preference tags requested for user: {end_user_id} (from cache)")
|
||||
|
||||
try:
|
||||
# Validate inputs
|
||||
validate_user_id(end_user_id)
|
||||
|
||||
# Create service with user-specific config
|
||||
service = ImplicitMemoryService(db=db, end_user_id=end_user_id)
|
||||
|
||||
# Get cached profile
|
||||
cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
|
||||
|
||||
if cached_profile is None:
|
||||
api_logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
|
||||
return fail(
|
||||
BizCode.NOT_FOUND,
|
||||
"画像缓存不存在或已过期，请右上角刷新生成新画像",
|
||||
""
|
||||
)
|
||||
|
||||
# Extract preferences from cache
|
||||
preferences = cached_profile.get("preferences", [])
|
||||
|
||||
# Apply filters (client-side filtering on cached data)
|
||||
filtered_preferences = []
|
||||
for pref in preferences:
|
||||
# Filter by confidence threshold
|
||||
if confidence_threshold is not None and pref.get("confidence_score", 0) < confidence_threshold:
|
||||
continue
|
||||
|
||||
# Filter by category if specified
|
||||
if tag_category and pref.get("category") != tag_category:
|
||||
continue
|
||||
|
||||
# Filter by date range if specified
|
||||
if start_date or end_date:
|
||||
created_at_ts = pref.get("created_at")
|
||||
if created_at_ts:
|
||||
created_at = datetime.fromtimestamp(created_at_ts / 1000)
|
||||
if start_date and created_at < start_date:
|
||||
continue
|
||||
if end_date and created_at > end_date:
|
||||
continue
|
||||
|
||||
filtered_preferences.append(pref)
|
||||
|
||||
api_logger.info(f"Retrieved {len(filtered_preferences)} preference tags for user: {end_user_id} (from cache)")
|
||||
return success(data=filtered_preferences, msg="偏好标签获取成功（缓存）")
|
||||
|
||||
except Exception as e:
|
||||
return handle_implicit_memory_error(e, "偏好标签获取", end_user_id)
|
||||
|
||||
|
||||
@router.get("/portrait/{end_user_id}", response_model=ApiResponse)
|
||||
@cur_workspace_access_guard()
|
||||
async def get_dimension_portrait(
|
||||
end_user_id: str,
|
||||
include_history: bool = Query(False, description="Include historical trends"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
) -> ApiResponse:
|
||||
"""
|
||||
Get user's four-dimension personality portrait from cache.
|
||||
|
||||
Args:
|
||||
end_user_id: Target end user ID
|
||||
include_history: Whether to include historical trend data (ignored for cached data)
|
||||
|
||||
Returns:
|
||||
Four-dimension personality portrait from cache
|
||||
"""
|
||||
api_logger.info(f"Dimension portrait requested for user: {end_user_id} (from cache)")
|
||||
|
||||
try:
|
||||
# Validate inputs
|
||||
validate_user_id(end_user_id)
|
||||
|
||||
# Create service with user-specific config
|
||||
service = ImplicitMemoryService(db=db, end_user_id=end_user_id)
|
||||
|
||||
# Get cached profile
|
||||
cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
|
||||
|
||||
if cached_profile is None:
|
||||
api_logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
|
||||
return fail(
|
||||
BizCode.NOT_FOUND,
|
||||
"画像缓存不存在或已过期，请右上角刷新生成新画像",
|
||||
""
|
||||
)
|
||||
|
||||
# Extract portrait from cache
|
||||
portrait = cached_profile.get("portrait", {})
|
||||
|
||||
api_logger.info(f"Dimension portrait retrieved for user: {end_user_id} (from cache)")
|
||||
return success(data=portrait, msg="四维画像获取成功（缓存）")
|
||||
|
||||
except Exception as e:
|
||||
return handle_implicit_memory_error(e, "四维画像获取", end_user_id)
|
||||
|
||||
|
||||
@router.get("/interest-areas/{end_user_id}", response_model=ApiResponse)
|
||||
@cur_workspace_access_guard()
|
||||
async def get_interest_area_distribution(
|
||||
end_user_id: str,
|
||||
include_trends: bool = Query(False, description="Include trend analysis"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
) -> ApiResponse:
|
||||
"""
|
||||
Get user's interest area distribution from cache.
|
||||
|
||||
Args:
|
||||
end_user_id: Target end user ID
|
||||
include_trends: Whether to include trend analysis data (ignored for cached data)
|
||||
|
||||
Returns:
|
||||
Interest area distribution from cache
|
||||
"""
|
||||
api_logger.info(f"Interest area distribution requested for user: {end_user_id} (from cache)")
|
||||
|
||||
try:
|
||||
# Validate inputs
|
||||
validate_user_id(end_user_id)
|
||||
|
||||
# Create service with user-specific config
|
||||
service = ImplicitMemoryService(db=db, end_user_id=end_user_id)
|
||||
|
||||
# Get cached profile
|
||||
cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
|
||||
|
||||
if cached_profile is None:
|
||||
api_logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
|
||||
return fail(
|
||||
BizCode.NOT_FOUND,
|
||||
"画像缓存不存在或已过期，请右上角刷新生成新画像",
|
||||
""
|
||||
)
|
||||
|
||||
# Extract interest areas from cache
|
||||
interest_areas = cached_profile.get("interest_areas", {})
|
||||
|
||||
api_logger.info(f"Interest area distribution retrieved for user: {end_user_id} (from cache)")
|
||||
return success(data=interest_areas, msg="兴趣领域分布获取成功（缓存）")
|
||||
|
||||
except Exception as e:
|
||||
return handle_implicit_memory_error(e, "兴趣领域分布获取", end_user_id)
|
||||
|
||||
|
||||
@router.get("/habits/{end_user_id}", response_model=ApiResponse)
|
||||
@cur_workspace_access_guard()
|
||||
async def get_behavior_habits(
|
||||
end_user_id: str,
|
||||
confidence_level: Optional[str] = Query(None, regex="^(high|medium|low)$", description="Filter by confidence level"),
|
||||
frequency_pattern: Optional[str] = Query(None, regex="^(daily|weekly|monthly|seasonal|occasional|event_triggered)$", description="Filter by frequency pattern"),
|
||||
time_period: Optional[str] = Query(None, regex="^(current|past)$", description="Filter by time period"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
) -> ApiResponse:
|
||||
"""
|
||||
Get user's behavioral habits from cache.
|
||||
|
||||
Args:
|
||||
end_user_id: Target end user ID
|
||||
confidence_level: Filter by confidence level (high, medium, low)
|
||||
frequency_pattern: Filter by frequency pattern (daily, weekly, monthly, seasonal, occasional, event_triggered)
|
||||
time_period: Filter by time period (current, past)
|
||||
|
||||
Returns:
|
||||
List of behavioral habits from cache
|
||||
"""
|
||||
api_logger.info(f"Behavior habits requested for user: {end_user_id} (from cache)")
|
||||
|
||||
try:
|
||||
# Validate inputs
|
||||
validate_user_id(end_user_id)
|
||||
|
||||
# Create service with user-specific config
|
||||
service = ImplicitMemoryService(db=db, end_user_id=end_user_id)
|
||||
|
||||
# Get cached profile
|
||||
cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
|
||||
|
||||
if cached_profile is None:
|
||||
api_logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
|
||||
return fail(
|
||||
BizCode.NOT_FOUND,
|
||||
"画像缓存不存在或已过期，请右上角刷新生成新画像",
|
||||
""
|
||||
)
|
||||
|
||||
# Extract habits from cache
|
||||
habits = cached_profile.get("habits", [])
|
||||
|
||||
# Apply filters (client-side filtering on cached data)
|
||||
filtered_habits = []
|
||||
for habit in habits:
|
||||
# Filter by confidence level
|
||||
if confidence_level:
|
||||
confidence_mapping = {
|
||||
"high": 85,
|
||||
"medium": 50,
|
||||
"low": 20
|
||||
}
|
||||
numerical_confidence = confidence_mapping.get(confidence_level.lower())
|
||||
if habit.get("confidence_level", 0) < numerical_confidence:
|
||||
continue
|
||||
|
||||
# Filter by frequency pattern
|
||||
if frequency_pattern and habit.get("frequency_pattern") != frequency_pattern:
|
||||
continue
|
||||
|
||||
# Filter by time period
|
||||
if time_period:
|
||||
is_current = habit.get("is_current", True)
|
||||
if time_period.lower() == "current" and not is_current:
|
||||
continue
|
||||
elif time_period.lower() == "past" and is_current:
|
||||
continue
|
||||
|
||||
filtered_habits.append(habit)
|
||||
|
||||
api_logger.info(f"Retrieved {len(filtered_habits)} behavior habits for user: {end_user_id} (from cache)")
|
||||
return success(data=filtered_habits, msg="行为习惯获取成功（缓存）")
|
||||
|
||||
except Exception as e:
|
||||
return handle_implicit_memory_error(e, "行为习惯获取", end_user_id)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@router.post("/generate_profile", response_model=ApiResponse)
|
||||
@cur_workspace_access_guard()
|
||||
async def generate_implicit_memory_profile(
|
||||
request: GenerateProfileRequest,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
) -> ApiResponse:
|
||||
"""
|
||||
Generate complete user profile (all 4 modules) and cache it.
|
||||
|
||||
Args:
|
||||
request: Generate profile request with end_user_id
|
||||
db: Database session
|
||||
current_user: Current authenticated user
|
||||
|
||||
Returns:
|
||||
Complete user profile with all modules
|
||||
"""
|
||||
end_user_id = request.end_user_id
|
||||
api_logger.info(f"Generate profile requested for user: {end_user_id}")
|
||||
|
||||
try:
|
||||
# Validate inputs
|
||||
validate_user_id(end_user_id)
|
||||
|
||||
# Create service with user-specific config
|
||||
service = ImplicitMemoryService(db=db, end_user_id=end_user_id)
|
||||
|
||||
# Generate complete profile (calls LLM for all 4 modules)
|
||||
api_logger.info(f"开始生成完整用户画像: user={end_user_id}")
|
||||
profile_data = await service.generate_complete_profile(user_id=end_user_id)
|
||||
|
||||
# Save to cache
|
||||
await service.save_profile_cache(
|
||||
end_user_id=end_user_id,
|
||||
profile_data=profile_data,
|
||||
db=db,
|
||||
expires_hours=168 # 7 days
|
||||
)
|
||||
|
||||
api_logger.info(f"用户画像生成并缓存成功: user={end_user_id}")
|
||||
|
||||
# Add metadata
|
||||
profile_data["end_user_id"] = end_user_id
|
||||
profile_data["cached"] = False
|
||||
|
||||
return success(data=profile_data, msg="用户画像生成成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"生成用户画像失败: user={end_user_id}, error={str(e)}", exc_info=True)
|
||||
return handle_implicit_memory_error(e, "用户画像生成", end_user_id)
|
||||
@@ -1,29 +1,26 @@
|
||||
from typing import Optional
|
||||
import datetime
|
||||
import json
|
||||
from typing import Optional
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, status, Query
|
||||
from fastapi.encoders import jsonable_encoder
|
||||
from sqlalchemy import or_
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.celery_app import celery_app
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.rag.common import settings
|
||||
from app.core.rag.llm.chat_model import Base
|
||||
from app.core.rag.nlp import rag_tokenizer, search
|
||||
from app.core.rag.prompts.generator import graph_entity_types
|
||||
from app.core.rag.vdb.elasticsearch.elasticsearch_vector import ElasticSearchVectorFactory
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models import knowledge_model
|
||||
from app.models.user_model import User
|
||||
from app.models import knowledge_model, document_model, file_model
|
||||
from app.schemas import knowledge_schema
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.core.response_utils import success
|
||||
from app.services import knowledge_service, document_service
|
||||
from app.services.model_service import ModelConfigService
|
||||
from app.core.rag.llm.chat_model import Base
|
||||
from app.core.rag.prompts.generator import graph_entity_types
|
||||
from app.core.rag.vdb.elasticsearch.elasticsearch_vector import ElasticSearchVectorFactory
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.rag.nlp import rag_tokenizer, search
|
||||
from app.core.rag.common import settings
|
||||
from app.celery_app import celery_app
|
||||
|
||||
# Obtain a dedicated API logger
|
||||
api_logger = get_api_logger()
|
||||
@@ -50,45 +47,6 @@ def get_parser_types():
|
||||
return success(msg="Successfully obtained the knowledge parser type", data=list(knowledge_model.ParserType))
|
||||
|
||||
|
||||
@router.get("/knowledge_graph_entity_types", response_model=ApiResponse)
|
||||
async def get_knowledge_graph_entity_types(
|
||||
llm_id: uuid.UUID,
|
||||
scenario: str,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
get knowledge graph entity types based on llm_id
|
||||
"""
|
||||
api_logger.info(f"Obtain details of the knowledge graph: llm_id={llm_id}, username: {current_user.username}")
|
||||
|
||||
try:
|
||||
# 1. Check whether the model exists
|
||||
api_logger.debug(f"Check whether the model exists: {llm_id}")
|
||||
config = ModelConfigService.get_model_by_id(db=db, model_id=llm_id)
|
||||
|
||||
if not config:
|
||||
api_logger.warning(
|
||||
f"The model does not exist or you do not have permission to access it: llm_id={llm_id}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="The model does not exist or you do not have permission to access it"
|
||||
)
|
||||
# 2. Prepare to configure chat_mdl information
|
||||
chat_model = Base(
|
||||
key=config.api_keys[0].api_key,
|
||||
model_name=config.api_keys[0].model_name,
|
||||
base_url=config.api_keys[0].api_base
|
||||
)
|
||||
response = graph_entity_types(chat_model, scenario)
|
||||
return success(data=response, msg="Successfully obtained knowledge graph entity types")
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
api_logger.error(f"get knowledge graph entity types failed: llm_id={llm_id} - {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
@router.get("/knowledges", response_model=ApiResponse)
|
||||
async def get_knowledges(
|
||||
parent_id: Optional[uuid.UUID] = Query(None, description="parent folder id"),
|
||||
@@ -172,7 +130,7 @@ async def get_knowledges(
|
||||
"has_next": True if page*pagesize < total else False
|
||||
}
|
||||
}
|
||||
return success(data=jsonable_encoder(result), msg="Query of knowledge base list successful")
|
||||
return success(data=result, msg="Query of knowledge base list successful")
|
||||
|
||||
|
||||
@router.post("/knowledge", response_model=ApiResponse)
|
||||
@@ -198,7 +156,7 @@ async def create_knowledge(
|
||||
)
|
||||
db_knowledge = knowledge_service.create_knowledge(db=db, knowledge=create_data, current_user=current_user)
|
||||
api_logger.info(f"The knowledge base has been successfully created: {db_knowledge.name} (ID: {db_knowledge.id})")
|
||||
return success(data=jsonable_encoder(knowledge_schema.Knowledge.model_validate(db_knowledge)), msg="The knowledge base has been successfully created")
|
||||
return success(data=knowledge_schema.Knowledge.model_validate(db_knowledge), msg="The knowledge base has been successfully created")
|
||||
except Exception as e:
|
||||
api_logger.error(f"The creation of the knowledge base failed: {create_data.name} - {str(e)}")
|
||||
raise
|
||||
@@ -227,7 +185,7 @@ async def get_knowledge(
|
||||
)
|
||||
|
||||
api_logger.info(f"Knowledge base query successful: {db_knowledge.name} (ID: {db_knowledge.id})")
|
||||
return success(data=jsonable_encoder(knowledge_schema.Knowledge.model_validate(db_knowledge)), msg="Successfully obtained knowledge base information")
|
||||
return success(data=knowledge_schema.Knowledge.model_validate(db_knowledge), msg="Successfully obtained knowledge base information")
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
@@ -244,7 +202,7 @@ async def update_knowledge(
|
||||
):
|
||||
api_logger.info(f"Update knowledge base request: knowledge_id={knowledge_id}, username: {current_user.username}")
|
||||
db_knowledge = await _update_knowledge(knowledge_id=knowledge_id, update_data=update_data, db=db, current_user=current_user)
|
||||
return success(data=jsonable_encoder(knowledge_schema.Knowledge.model_validate(db_knowledge)), msg="The knowledge base information has been successfully updated")
|
||||
return success(data=knowledge_schema.Knowledge.model_validate(db_knowledge), msg="The knowledge base information has been successfully updated")
|
||||
|
||||
|
||||
async def _update_knowledge(
|
||||
@@ -421,7 +379,7 @@ async def delete_knowledge_graph(
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
delete knowledge graph
|
||||
Soft-delete knowledge graph
|
||||
"""
|
||||
api_logger.info(f"Request to delete knowledge graph: knowledge_id={knowledge_id}, username: {current_user.username}")
|
||||
|
||||
@@ -484,3 +442,42 @@ async def rebuild_knowledge_graph(
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to rebuild knowledge graph: knowledge_id={knowledge_id} - {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
@router.get("/{knowledge_id}/knowledge_graph_entity_types", response_model=ApiResponse)
|
||||
async def get_knowledge_graph_entity_types(
|
||||
knowledge_id: uuid.UUID,
|
||||
scenario: str,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
get knowledge graph entity types based on knowledge_id
|
||||
"""
|
||||
api_logger.info(f"Obtain details of the knowledge graph: knowledge_id={knowledge_id}, username: {current_user.username}")
|
||||
|
||||
try:
|
||||
# 1. Check whether the knowledge base exists
|
||||
api_logger.debug(f"Check whether the knowledge base exists: {knowledge_id}")
|
||||
db_knowledge = knowledge_service.get_knowledge_by_id(db, knowledge_id=knowledge_id, current_user=current_user)
|
||||
|
||||
if not db_knowledge:
|
||||
api_logger.warning(
|
||||
f"The knowledge base does not exist or you do not have permission to access it: knowledge_id={knowledge_id}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail="The knowledge base does not exist or you do not have permission to access it"
|
||||
)
|
||||
# 2. Prepare to configure chat_mdl information
|
||||
chat_model = Base(
|
||||
key=db_knowledge.llm.api_keys[0].api_key,
|
||||
model_name=db_knowledge.llm.api_keys[0].model_name,
|
||||
base_url=db_knowledge.llm.api_keys[0].api_base
|
||||
)
|
||||
response = graph_entity_types(chat_model, scenario)
|
||||
return success(data=response, msg="Successfully obtained knowledge graph entity types")
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
api_logger.error(f"get knowledge graph entity types failed: knowledge_id={knowledge_id} - {str(e)}")
|
||||
raise
|
||||
|
||||
@@ -9,16 +9,14 @@ from app.db import get_db
|
||||
from app.dependencies import cur_workspace_access_guard, get_current_user
|
||||
from app.models import ModelApiKey
|
||||
from app.models.user_model import User
|
||||
from app.core.memory.agent.utils.session_tools import SessionService
|
||||
from app.core.memory.agent.utils.redis_tool import store
|
||||
from app.repositories import knowledge_repository, WorkspaceRepository
|
||||
from app.repositories import knowledge_repository
|
||||
from app.schemas.memory_agent_schema import UserInput, Write_UserInput
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services import task_service, workspace_service
|
||||
from app.services.memory_agent_service import MemoryAgentService
|
||||
from app.services.model_service import ModelConfigService
|
||||
from dotenv import load_dotenv
|
||||
from fastapi import APIRouter, Depends, File, Form, Query, UploadFile,Header
|
||||
from fastapi import APIRouter, Depends, File, Form, Query, UploadFile
|
||||
from sqlalchemy.orm import Session
|
||||
from starlette.responses import StreamingResponse
|
||||
|
||||
@@ -125,7 +123,7 @@ async def write_server(
|
||||
Write service endpoint - processes write operations synchronously
|
||||
|
||||
Args:
|
||||
user_input: Write request containing message and end_user_id
|
||||
user_input: Write request containing message and group_id
|
||||
|
||||
Returns:
|
||||
Response with write operation status
|
||||
@@ -160,18 +158,16 @@ async def write_server(
|
||||
api_logger.warning("workspace_id 为空，无法使用 rag 存储，将使用 neo4j 存储")
|
||||
storage_type = 'neo4j'
|
||||
|
||||
api_logger.info(f"Write service requested for group {user_input.end_user_id}, storage_type: {storage_type}, user_rag_memory_id: {user_rag_memory_id}")
|
||||
api_logger.info(f"Write service requested for group {user_input.group_id}, storage_type: {storage_type}, user_rag_memory_id: {user_rag_memory_id}")
|
||||
try:
|
||||
messages_list = memory_agent_service.get_messages_list(user_input)
|
||||
result = await memory_agent_service.write_memory(
|
||||
user_input.end_user_id,
|
||||
messages_list,
|
||||
user_input.group_id,
|
||||
user_input.message,
|
||||
config_id,
|
||||
db,
|
||||
storage_type,
|
||||
user_rag_memory_id
|
||||
)
|
||||
|
||||
return success(data=result, msg="写入成功")
|
||||
except BaseException as e:
|
||||
# Handle ExceptionGroup from TaskGroup (Python 3.11+) or BaseExceptionGroup
|
||||
@@ -195,7 +191,7 @@ async def write_server_async(
|
||||
Async write service endpoint - enqueues write processing to Celery
|
||||
|
||||
Args:
|
||||
user_input: Write request containing message and end_user_id
|
||||
user_input: Write request containing message and group_id
|
||||
|
||||
Returns:
|
||||
Task ID for tracking async operation
|
||||
@@ -223,12 +219,9 @@ async def write_server_async(
|
||||
if knowledge: user_rag_memory_id = str(knowledge.id)
|
||||
api_logger.info(f"Async write: storage_type={storage_type}, user_rag_memory_id={user_rag_memory_id}")
|
||||
try:
|
||||
# 获取标准化的消息列表
|
||||
messages_list = memory_agent_service.get_messages_list(user_input)
|
||||
|
||||
task = celery_app.send_task(
|
||||
"app.core.memory.agent.write_message",
|
||||
args=[user_input.end_user_id, messages_list, config_id, storage_type, user_rag_memory_id]
|
||||
args=[user_input.group_id, user_input.message, config_id, storage_type, user_rag_memory_id]
|
||||
)
|
||||
api_logger.info(f"Write task queued: {task.id}")
|
||||
|
||||
@@ -254,14 +247,16 @@ async def read_server(
|
||||
- "2": Direct answer based on context
|
||||
|
||||
Args:
|
||||
user_input: Read request with message, history, search_switch, and end_user_id
|
||||
user_input: Read request with message, history, search_switch, and group_id
|
||||
|
||||
Returns:
|
||||
Response with query answer
|
||||
"""
|
||||
config_id = user_input.config_id
|
||||
workspace_id = current_user.current_workspace_id
|
||||
api_logger.info(f"Read service: workspace_id={workspace_id}, config_id={config_id}")
|
||||
|
||||
# 获取 storage_type，如果为 None 则使用默认值
|
||||
storage_type = workspace_service.get_workspace_storage_type(
|
||||
db=db,
|
||||
workspace_id=workspace_id,
|
||||
@@ -276,13 +271,12 @@ async def read_server(
|
||||
name="USER_RAG_MERORY",
|
||||
workspace_id=workspace_id
|
||||
)
|
||||
if knowledge:
|
||||
user_rag_memory_id = str(knowledge.id)
|
||||
if knowledge: user_rag_memory_id = str(knowledge.id)
|
||||
|
||||
api_logger.info(f"Read service: group={user_input.end_user_id}, storage_type={storage_type}, user_rag_memory_id={user_rag_memory_id}, workspace_id={workspace_id}")
|
||||
api_logger.info(f"Read service: group={user_input.group_id}, storage_type={storage_type}, user_rag_memory_id={user_rag_memory_id}, workspace_id={workspace_id}")
|
||||
try:
|
||||
result = await memory_agent_service.read_memory(
|
||||
user_input.end_user_id,
|
||||
user_input.group_id,
|
||||
user_input.message,
|
||||
user_input.history,
|
||||
user_input.search_switch,
|
||||
@@ -291,22 +285,6 @@ async def read_server(
|
||||
storage_type,
|
||||
user_rag_memory_id
|
||||
)
|
||||
if str(user_input.search_switch) == "2":
|
||||
retrieve_info = result['answer']
|
||||
history = await SessionService(store).get_history(user_input.end_user_id, user_input.end_user_id, user_input.end_user_id)
|
||||
query = user_input.message
|
||||
|
||||
# 调用 memory_agent_service 的方法生成最终答案
|
||||
result['answer'] = await memory_agent_service.generate_summary_from_retrieve(
|
||||
end_user_id=user_input.end_user_id,
|
||||
retrieve_info=retrieve_info,
|
||||
history=history,
|
||||
query=query,
|
||||
config_id=config_id,
|
||||
db=db
|
||||
)
|
||||
if "信息不足，无法回答" in result['answer']:
|
||||
result['answer']=retrieve_info
|
||||
return success(data=result, msg="回复对话消息成功")
|
||||
except BaseException as e:
|
||||
# Handle ExceptionGroup from TaskGroup (Python 3.11+) or BaseExceptionGroup
|
||||
@@ -404,7 +382,7 @@ async def read_server_async(
|
||||
try:
|
||||
task = celery_app.send_task(
|
||||
"app.core.memory.agent.read_message",
|
||||
args=[user_input.end_user_id, user_input.message, user_input.history, user_input.search_switch,
|
||||
args=[user_input.group_id, user_input.message, user_input.history, user_input.search_switch,
|
||||
config_id, storage_type, user_rag_memory_id]
|
||||
)
|
||||
api_logger.info(f"Read task queued: {task.id}")
|
||||
@@ -448,7 +426,7 @@ async def get_read_task_result(
|
||||
return success(
|
||||
data={
|
||||
"result": task_result.get("result"),
|
||||
"end_user_id": task_result.get("end_user_id"),
|
||||
"group_id": task_result.get("group_id"),
|
||||
"elapsed_time": task_result.get("elapsed_time"),
|
||||
"task_id": task_id
|
||||
},
|
||||
@@ -525,7 +503,7 @@ async def get_write_task_result(
|
||||
return success(
|
||||
data={
|
||||
"result": task_result.get("result"),
|
||||
"end_user_id": task_result.get("end_user_id"),
|
||||
"group_id": task_result.get("group_id"),
|
||||
"elapsed_time": task_result.get("elapsed_time"),
|
||||
"task_id": task_id
|
||||
},
|
||||
@@ -579,30 +557,15 @@ async def status_type(
|
||||
Determine the type of user message (read or write)
|
||||
|
||||
Args:
|
||||
user_input: Request containing user message and end_user_id
|
||||
user_input: Request containing user message and group_id
|
||||
|
||||
Returns:
|
||||
Type classification result
|
||||
"""
|
||||
api_logger.info(f"Status type check requested for group {user_input.end_user_id}")
|
||||
api_logger.info(f"Status type check requested for group {user_input.group_id}")
|
||||
try:
|
||||
# 获取标准化的消息列表
|
||||
messages_list = memory_agent_service.get_messages_list(user_input)
|
||||
|
||||
# 将消息列表转换为字符串用于分类
|
||||
# 只取最后一条用户消息进行分类
|
||||
last_user_message = ""
|
||||
for msg in reversed(messages_list):
|
||||
if msg.get('role') == 'user':
|
||||
last_user_message = msg.get('content', '')
|
||||
break
|
||||
|
||||
if not last_user_message:
|
||||
# 如果没有用户消息，使用所有消息的内容
|
||||
last_user_message = " ".join([msg.get('content', '') for msg in messages_list])
|
||||
|
||||
result = await memory_agent_service.classify_message_type(
|
||||
last_user_message,
|
||||
user_input.message,
|
||||
user_input.config_id,
|
||||
db
|
||||
)
|
||||
@@ -625,7 +588,7 @@ async def get_knowledge_type_stats_api(
|
||||
会对缺失类型补 0，返回字典形式。
|
||||
可选按状态过滤。
|
||||
- 知识库类型根据当前用户的 current_workspace_id 过滤
|
||||
- memory 是 Neo4j 中 Chunk 的数量，根据 end_user_id (end_user_id) 过滤
|
||||
- memory 是 Neo4j 中 Chunk 的数量，根据 end_user_id (group_id) 过滤
|
||||
- 如果用户没有当前工作空间或未提供 end_user_id，对应的统计返回 0
|
||||
"""
|
||||
api_logger.info(f"Knowledge type stats requested for workspace_id: {current_user.current_workspace_id}, end_user_id: {end_user_id}")
|
||||
@@ -653,10 +616,8 @@ async def get_knowledge_type_stats_api(
|
||||
@router.get("/analytics/hot_memory_tags/by_user", response_model=ApiResponse)
|
||||
async def get_hot_memory_tags_by_user_api(
|
||||
end_user_id: Optional[str] = Query(None, description="用户ID（可选）"),
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
limit: int = Query(20, description="返回标签数量限制"),
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session=Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
获取指定用户的热门记忆标签
|
||||
@@ -667,22 +628,10 @@ async def get_hot_memory_tags_by_user_api(
|
||||
...
|
||||
]
|
||||
"""
|
||||
|
||||
workspace_id=current_user.current_workspace_id
|
||||
workspace_repo = WorkspaceRepository(db)
|
||||
workspace_models = workspace_repo.get_workspace_models_configs(workspace_id)
|
||||
|
||||
if workspace_models:
|
||||
model_id = workspace_models.get("llm", None)
|
||||
else:
|
||||
model_id = None
|
||||
|
||||
api_logger.info(f"Hot memory tags by user requested: end_user_id={end_user_id}")
|
||||
try:
|
||||
result = await memory_agent_service.get_hot_memory_tags_by_user(
|
||||
end_user_id=end_user_id,
|
||||
language_type=language_type,
|
||||
model_id=model_id,
|
||||
limit=limit
|
||||
)
|
||||
return success(data=result, msg="获取热门记忆标签成功")
|
||||
|
||||
@@ -1,14 +1,18 @@
|
||||
from fastapi import APIRouter, Depends, HTTPException, status, Query
|
||||
from sqlalchemy.orm import Session
|
||||
from typing import Optional
|
||||
from typing import List, Optional
|
||||
import uuid
|
||||
from app.repositories.end_user_repository import update_end_user_other_name
|
||||
import uuid
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.user_model import User
|
||||
from app.schemas.memory_agent_schema import End_User_Information
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.schemas.app_schema import App as AppSchema
|
||||
|
||||
from app.services import memory_dashboard_service, memory_storage_service, workspace_service
|
||||
from app.services.memory_agent_service import get_end_users_connected_configs_batch
|
||||
from app.core.logging_config import get_api_logger
|
||||
|
||||
# 获取API专用日志器
|
||||
@@ -39,7 +43,54 @@ def get_workspace_total_end_users(
|
||||
api_logger.info(f"成功获取最新用户总数: total_num={total_end_users.get('total_num', 0)}")
|
||||
return success(data=total_end_users, msg="用户数量获取成功")
|
||||
|
||||
@router.post("/update/end_users", response_model=ApiResponse)
|
||||
async def update_workspace_end_users(
|
||||
user_input: End_User_Information,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
更新工作空间的宿主信息
|
||||
"""
|
||||
username = user_input.end_user_name # 要更新的用户名
|
||||
end_user_input_id = user_input.id # 宿主ID
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
api_logger.info(f"用户 {current_user.username} 请求更新工作空间 {workspace_id} 的宿主信息")
|
||||
api_logger.info(f"更新参数: username={username}, end_user_id={end_user_input_id}")
|
||||
|
||||
try:
|
||||
# 导入更新函数
|
||||
from app.repositories.end_user_repository import update_end_user_other_name
|
||||
import uuid
|
||||
|
||||
# 转换 end_user_id 为 UUID 类型
|
||||
end_user_uuid = uuid.UUID(end_user_input_id)
|
||||
|
||||
# 直接更新数据库中的 other_name 字段
|
||||
updated_count = update_end_user_other_name(
|
||||
db=db,
|
||||
end_user_id=end_user_uuid,
|
||||
other_name=username
|
||||
)
|
||||
|
||||
api_logger.info(f"成功更新宿主 {end_user_input_id} 的 other_name 为: {username}")
|
||||
|
||||
return success(
|
||||
data={
|
||||
"updated_count": updated_count,
|
||||
"end_user_id": end_user_input_id,
|
||||
"updated_other_name": username
|
||||
},
|
||||
msg=f"成功更新 {updated_count} 个宿主的信息"
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"更新宿主信息失败: {str(e)}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail=f"更新宿主信息失败: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -49,134 +100,36 @@ async def get_workspace_end_users(
|
||||
current_user: User = Depends(get_current_user),
|
||||
):
|
||||
"""
|
||||
获取工作空间的宿主列表（高性能优化版本 v2）
|
||||
获取工作空间的宿主列表
|
||||
|
||||
优化策略：
|
||||
1. 批量查询 end_users（一次查询而非循环）
|
||||
2. 并发查询所有用户的记忆数量（Neo4j）
|
||||
3. RAG 模式使用批量查询（一次 SQL）
|
||||
4. 只返回必要字段减少数据传输
|
||||
5. 添加短期缓存减少重复查询
|
||||
6. 并发执行配置查询和记忆数量查询
|
||||
|
||||
返回格式：
|
||||
{
|
||||
"end_user": {"id": "uuid", "other_name": "名称"},
|
||||
"memory_num": {"total": 数量},
|
||||
"memory_config": {"memory_config_id": "id", "memory_config_name": "名称"}
|
||||
}
|
||||
返回格式与原 memory_list 接口中的 end_users 字段相同
|
||||
"""
|
||||
import asyncio
|
||||
import json
|
||||
from app.aioRedis import aio_redis_get, aio_redis_set
|
||||
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 尝试从缓存获取（30秒缓存）
|
||||
cache_key = f"end_users:workspace:{workspace_id}"
|
||||
try:
|
||||
cached_data = await aio_redis_get(cache_key)
|
||||
if cached_data:
|
||||
api_logger.info(f"从缓存获取宿主列表: workspace_id={workspace_id}")
|
||||
return success(data=json.loads(cached_data), msg="宿主列表获取成功")
|
||||
except Exception as e:
|
||||
api_logger.warning(f"Redis 缓存读取失败: {str(e)}")
|
||||
|
||||
# 获取当前空间类型
|
||||
current_workspace_type = memory_dashboard_service.get_current_workspace_type(db, workspace_id, current_user)
|
||||
api_logger.info(f"用户 {current_user.username} 请求获取工作空间 {workspace_id} 的宿主列表")
|
||||
|
||||
# 获取 end_users（已优化为批量查询）
|
||||
end_users = memory_dashboard_service.get_workspace_end_users(
|
||||
db=db,
|
||||
workspace_id=workspace_id,
|
||||
current_user=current_user
|
||||
)
|
||||
if not end_users:
|
||||
api_logger.info("工作空间下没有宿主")
|
||||
# 缓存空结果，避免重复查询
|
||||
try:
|
||||
await aio_redis_set(cache_key, json.dumps([]), expire=30)
|
||||
except Exception as e:
|
||||
api_logger.warning(f"Redis 缓存写入失败: {str(e)}")
|
||||
return success(data=[], msg="宿主列表获取成功")
|
||||
|
||||
end_user_ids = [str(user.id) for user in end_users]
|
||||
|
||||
# 并发执行两个独立的查询任务
|
||||
async def get_memory_configs():
|
||||
"""获取记忆配置（在线程池中执行同步查询）"""
|
||||
try:
|
||||
return await asyncio.to_thread(
|
||||
get_end_users_connected_configs_batch,
|
||||
end_user_ids, db
|
||||
)
|
||||
except Exception as e:
|
||||
api_logger.error(f"批量获取记忆配置失败: {str(e)}")
|
||||
return {}
|
||||
|
||||
async def get_memory_nums():
|
||||
"""获取记忆数量"""
|
||||
if current_workspace_type == "rag":
|
||||
# RAG 模式：批量查询
|
||||
try:
|
||||
chunk_map = await asyncio.to_thread(
|
||||
memory_dashboard_service.get_users_total_chunk_batch,
|
||||
end_user_ids, db, current_user
|
||||
)
|
||||
return {uid: {"total": count} for uid, count in chunk_map.items()}
|
||||
except Exception as e:
|
||||
api_logger.error(f"批量获取 RAG chunk 数量失败: {str(e)}")
|
||||
return {uid: {"total": 0} for uid in end_user_ids}
|
||||
|
||||
elif current_workspace_type == "neo4j":
|
||||
# Neo4j 模式：并发查询（带并发限制）
|
||||
# 使用信号量限制并发数，避免大量用户时压垮 Neo4j
|
||||
MAX_CONCURRENT_QUERIES = 10
|
||||
semaphore = asyncio.Semaphore(MAX_CONCURRENT_QUERIES)
|
||||
|
||||
async def get_neo4j_memory_num(end_user_id: str):
|
||||
async with semaphore:
|
||||
try:
|
||||
return await memory_storage_service.search_all(end_user_id)
|
||||
except Exception as e:
|
||||
api_logger.error(f"获取用户 {end_user_id} Neo4j 记忆数量失败: {str(e)}")
|
||||
return {"total": 0}
|
||||
|
||||
memory_nums_list = await asyncio.gather(*[get_neo4j_memory_num(uid) for uid in end_user_ids])
|
||||
return {end_user_ids[i]: memory_nums_list[i] for i in range(len(end_user_ids))}
|
||||
|
||||
return {uid: {"total": 0} for uid in end_user_ids}
|
||||
|
||||
# 并发执行配置查询和记忆数量查询
|
||||
memory_configs_map, memory_nums_map = await asyncio.gather(
|
||||
get_memory_configs(),
|
||||
get_memory_nums()
|
||||
)
|
||||
|
||||
# 构建结果（优化：使用列表推导式）
|
||||
result = []
|
||||
for end_user in end_users:
|
||||
user_id = str(end_user.id)
|
||||
config_info = memory_configs_map.get(user_id, {})
|
||||
result.append({
|
||||
'end_user': {
|
||||
'id': user_id,
|
||||
'other_name': end_user.other_name
|
||||
},
|
||||
'memory_num': memory_nums_map.get(user_id, {"total": 0}),
|
||||
'memory_config': {
|
||||
"memory_config_id": config_info.get("memory_config_id"),
|
||||
"memory_config_name": config_info.get("memory_config_name")
|
||||
memory_num = {}
|
||||
if current_workspace_type == "neo4j":
|
||||
# EndUser 是 Pydantic 模型，直接访问属性而不是使用 .get()
|
||||
memory_num = await memory_storage_service.search_all(str(end_user.id))
|
||||
elif current_workspace_type == "rag":
|
||||
memory_num = {
|
||||
"total":memory_dashboard_service.get_current_user_total_chunk(str(end_user.id), db, current_user)
|
||||
}
|
||||
})
|
||||
|
||||
# 写入缓存（30秒过期）
|
||||
try:
|
||||
await aio_redis_set(cache_key, json.dumps(result), expire=30)
|
||||
except Exception as e:
|
||||
api_logger.warning(f"Redis 缓存写入失败: {str(e)}")
|
||||
|
||||
result.append(
|
||||
{
|
||||
'end_user':end_user,
|
||||
'memory_num':memory_num
|
||||
}
|
||||
)
|
||||
|
||||
api_logger.info(f"成功获取 {len(end_users)} 个宿主记录")
|
||||
return success(data=result, msg="宿主列表获取成功")
|
||||
|
||||
@@ -512,6 +465,7 @@ async def dashboard_data(
|
||||
if storage_type is None:
|
||||
storage_type = 'neo4j'
|
||||
|
||||
user_rag_memory_id = None
|
||||
|
||||
# 根据 storage_type 决定返回哪个数据对象
|
||||
# 如果是 'rag'，neo4j_data 为 null；否则 rag_data 为 null
|
||||
|
||||
@@ -1,125 +0,0 @@
|
||||
"""
|
||||
情景记忆相关的控制器
|
||||
包含情景记忆总览和详情查询接口
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, Depends
|
||||
|
||||
from app.core.error_codes import BizCode
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import fail, success
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.user_model import User
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.schemas.memory_episodic_schema import (
|
||||
EpisodicMemoryOverviewRequest,
|
||||
EpisodicMemoryDetailsRequest,
|
||||
)
|
||||
from app.services.memory_episodic_service import memory_episodic_service
|
||||
|
||||
# Get API logger
|
||||
api_logger = get_api_logger()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/memory/episodic-memory",
|
||||
tags=["Episodic Memory"],
|
||||
)
|
||||
|
||||
|
||||
@router.post("/overview", response_model=ApiResponse)
|
||||
async def get_episodic_memory_overview_api(
|
||||
request: EpisodicMemoryOverviewRequest,
|
||||
current_user: User = Depends(get_current_user),
|
||||
) -> dict:
|
||||
"""
|
||||
获取情景记忆总览
|
||||
|
||||
返回指定用户的所有情景记忆列表，包括标题和创建时间。
|
||||
支持通过时间范围、情景类型和标题关键词进行筛选。
|
||||
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试查询情景记忆总览但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
# 验证参数
|
||||
valid_time_ranges = ["all", "today", "this_week", "this_month"]
|
||||
valid_episodic_types = ["all", "conversation", "project_work", "learning", "decision", "important_event"]
|
||||
|
||||
if request.time_range not in valid_time_ranges:
|
||||
return fail(BizCode.INVALID_PARAMETER, f"无效的时间范围参数，可选值：{', '.join(valid_time_ranges)}")
|
||||
|
||||
if request.episodic_type not in valid_episodic_types:
|
||||
return fail(BizCode.INVALID_PARAMETER, f"无效的情景类型参数，可选值：{', '.join(valid_episodic_types)}")
|
||||
|
||||
# 处理 title_keyword（去除首尾空格）
|
||||
title_keyword = request.title_keyword.strip() if request.title_keyword else None
|
||||
|
||||
api_logger.info(
|
||||
f"情景记忆总览查询请求: end_user_id={request.end_user_id}, user={current_user.username}, "
|
||||
f"workspace={workspace_id}, time_range={request.time_range}, episodic_type={request.episodic_type}, "
|
||||
f"title_keyword={title_keyword}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 调用Service层方法
|
||||
result = await memory_episodic_service.get_episodic_memory_overview(
|
||||
request.end_user_id, request.time_range, request.episodic_type, title_keyword
|
||||
)
|
||||
|
||||
api_logger.info(
|
||||
f"成功获取情景记忆总览: end_user_id={request.end_user_id}, "
|
||||
f"total={result['total']}"
|
||||
)
|
||||
return success(data=result, msg="查询成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"情景记忆总览查询失败: end_user_id={request.end_user_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "情景记忆总览查询失败", str(e))
|
||||
|
||||
|
||||
@router.post("/details", response_model=ApiResponse)
|
||||
async def get_episodic_memory_details_api(
|
||||
request: EpisodicMemoryDetailsRequest,
|
||||
current_user: User = Depends(get_current_user),
|
||||
) -> dict:
|
||||
"""
|
||||
获取情景记忆详情
|
||||
|
||||
返回指定情景记忆的详细信息，包括涉及对象、情景类型、内容记录和情绪。
|
||||
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试查询情景记忆详情但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
api_logger.info(
|
||||
f"情景记忆详情查询请求: end_user_id={request.end_user_id}, summary_id={request.summary_id}, "
|
||||
f"user={current_user.username}, workspace={workspace_id}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 调用Service层方法
|
||||
result = await memory_episodic_service.get_episodic_memory_details(
|
||||
end_user_id=request.end_user_id,
|
||||
summary_id=request.summary_id
|
||||
)
|
||||
|
||||
api_logger.info(
|
||||
f"成功获取情景记忆详情: end_user_id={request.end_user_id}, summary_id={request.summary_id}"
|
||||
)
|
||||
return success(data=result, msg="查询成功")
|
||||
|
||||
except ValueError as e:
|
||||
# 处理情景记忆不存在的情况
|
||||
api_logger.warning(f"情景记忆不存在: end_user_id={request.end_user_id}, summary_id={request.summary_id}, error={str(e)}")
|
||||
return fail(BizCode.INVALID_PARAMETER, "情景记忆不存在", str(e))
|
||||
except Exception as e:
|
||||
api_logger.error(f"情景记忆详情查询失败: end_user_id={request.end_user_id}, summary_id={request.summary_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "情景记忆详情查询失败", str(e))
|
||||
@@ -1,115 +0,0 @@
|
||||
"""
|
||||
显性记忆控制器
|
||||
|
||||
处理显性记忆相关的API接口，包括情景记忆和语义记忆的查询。
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, Depends
|
||||
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import success, fail
|
||||
from app.core.error_codes import BizCode
|
||||
from app.services.memory_explicit_service import MemoryExplicitService
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.schemas.memory_explicit_schema import (
|
||||
ExplicitMemoryOverviewRequest,
|
||||
ExplicitMemoryDetailsRequest,
|
||||
)
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.user_model import User
|
||||
|
||||
# Get API logger
|
||||
api_logger = get_api_logger()
|
||||
|
||||
# Initialize service
|
||||
memory_explicit_service = MemoryExplicitService()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/memory/explicit-memory",
|
||||
tags=["Explicit Memory"],
|
||||
)
|
||||
|
||||
|
||||
@router.post("/overview", response_model=ApiResponse)
|
||||
async def get_explicit_memory_overview_api(
|
||||
request: ExplicitMemoryOverviewRequest,
|
||||
current_user: User = Depends(get_current_user),
|
||||
) -> dict:
|
||||
"""
|
||||
获取显性记忆总览
|
||||
|
||||
返回指定用户的所有显性记忆列表，包括标题、完整内容、创建时间和情绪信息。
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试查询显性记忆总览但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
api_logger.info(
|
||||
f"显性记忆总览查询请求: end_user_id={request.end_user_id}, user={current_user.username}, "
|
||||
f"workspace={workspace_id}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 调用Service层方法
|
||||
result = await memory_explicit_service.get_explicit_memory_overview(
|
||||
request.end_user_id
|
||||
)
|
||||
|
||||
api_logger.info(
|
||||
f"成功获取显性记忆总览: end_user_id={request.end_user_id}, "
|
||||
f"total={result['total']}"
|
||||
)
|
||||
return success(data=result, msg="查询成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"显性记忆总览查询失败: end_user_id={request.end_user_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "显性记忆总览查询失败", str(e))
|
||||
|
||||
|
||||
@router.post("/details", response_model=ApiResponse)
|
||||
async def get_explicit_memory_details_api(
|
||||
request: ExplicitMemoryDetailsRequest,
|
||||
current_user: User = Depends(get_current_user),
|
||||
) -> dict:
|
||||
"""
|
||||
获取显性记忆详情
|
||||
|
||||
根据 memory_id 返回情景记忆或语义记忆的详细信息。
|
||||
- 情景记忆：包括标题、内容、情绪、创建时间
|
||||
- 语义记忆：包括名称、核心定义、详细笔记、创建时间
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试查询显性记忆详情但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
api_logger.info(
|
||||
f"显性记忆详情查询请求: end_user_id={request.end_user_id}, memory_id={request.memory_id}, "
|
||||
f"user={current_user.username}, workspace={workspace_id}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 调用Service层方法
|
||||
result = await memory_explicit_service.get_explicit_memory_details(
|
||||
end_user_id=request.end_user_id,
|
||||
memory_id=request.memory_id
|
||||
)
|
||||
|
||||
api_logger.info(
|
||||
f"成功获取显性记忆详情: end_user_id={request.end_user_id}, memory_id={request.memory_id}, "
|
||||
f"memory_type={result.get('memory_type')}"
|
||||
)
|
||||
return success(data=result, msg="查询成功")
|
||||
|
||||
except ValueError as e:
|
||||
# 处理记忆不存在的情况
|
||||
api_logger.warning(f"显性记忆不存在: end_user_id={request.end_user_id}, memory_id={request.memory_id}, error={str(e)}")
|
||||
return fail(BizCode.INVALID_PARAMETER, "显性记忆不存在", str(e))
|
||||
except Exception as e:
|
||||
api_logger.error(f"显性记忆详情查询失败: end_user_id={request.end_user_id}, memory_id={request.memory_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "显性记忆详情查询失败", str(e))
|
||||
@@ -1,367 +0,0 @@
|
||||
"""
|
||||
遗忘引擎控制器模块
|
||||
|
||||
本模块提供遗忘引擎的 REST API 接口，包括：
|
||||
1. 手动触发遗忘周期
|
||||
2. 获取和更新配置
|
||||
3. 获取统计信息
|
||||
4. 获取遗忘曲线数据
|
||||
|
||||
所有接口都需要用户认证，并自动关联到当前工作空间。
|
||||
"""
|
||||
|
||||
from typing import Optional
|
||||
from uuid import UUID
|
||||
|
||||
from fastapi import APIRouter, Depends
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.error_codes import BizCode
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import fail, success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.user_model import User
|
||||
from app.schemas.memory_storage_schema import (
|
||||
ForgettingTriggerRequest,
|
||||
ForgettingConfigResponse,
|
||||
ForgettingConfigUpdateRequest,
|
||||
ForgettingStatsResponse,
|
||||
ForgettingReportResponse,
|
||||
ForgettingCurveRequest,
|
||||
ForgettingCurveResponse,
|
||||
ForgettingCurvePoint,
|
||||
)
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services.memory_forget_service import MemoryForgetService
|
||||
from app.utils.config_utils import resolve_config_id
|
||||
|
||||
# 获取API专用日志器
|
||||
api_logger = get_api_logger()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/memory/forget-memory",
|
||||
tags=["Memory Forgetting Engine"],
|
||||
dependencies=[Depends(get_current_user)] # 所有路由都需要认证
|
||||
)
|
||||
|
||||
# 初始化服务
|
||||
forget_service = MemoryForgetService()
|
||||
|
||||
|
||||
# ==================== API 端点 ====================
|
||||
|
||||
@router.post("/trigger", response_model=ApiResponse)
|
||||
async def trigger_forgetting_cycle(
|
||||
payload: ForgettingTriggerRequest,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
手动触发遗忘周期
|
||||
|
||||
执行一次完整的遗忘周期，识别并融合低激活值节点。
|
||||
|
||||
Args:
|
||||
payload: 触发请求参数
|
||||
current_user: 当前用户
|
||||
db: 数据库会话
|
||||
|
||||
Returns:
|
||||
ApiResponse: 包含遗忘报告的响应
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
end_user_id = payload.end_user_id # 从 payload 中获取 end_user_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试触发遗忘周期但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
# 通过 end_user_id 获取关联的 config_id
|
||||
try:
|
||||
from app.services.memory_agent_service import get_end_user_connected_config
|
||||
|
||||
connected_config = get_end_user_connected_config(end_user_id, db)
|
||||
config_id = connected_config.get("memory_config_id")
|
||||
config_id = resolve_config_id((config_id), db)
|
||||
|
||||
if config_id is None:
|
||||
api_logger.warning(f"终端用户 {end_user_id} 未关联记忆配置")
|
||||
return fail(BizCode.INVALID_PARAMETER, f"终端用户 {end_user_id} 未关联记忆配置", "memory_config_id is None")
|
||||
|
||||
api_logger.debug(f"通过 end_user_id={end_user_id} 获取到 config_id={config_id}")
|
||||
except ValueError as e:
|
||||
api_logger.warning(f"获取终端用户配置失败: {str(e)}")
|
||||
return fail(BizCode.INVALID_PARAMETER, str(e), "ValueError")
|
||||
except Exception as e:
|
||||
api_logger.error(f"获取终端用户配置时发生错误: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "获取终端用户配置失败", str(e))
|
||||
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 在工作空间 {workspace_id} 请求触发遗忘周期: "
|
||||
f"end_user_id={end_user_id}, config_id={config_id}, max_batch={payload.max_merge_batch_size}, "
|
||||
f"min_days={payload.min_days_since_access}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 调用服务层执行遗忘周期
|
||||
report = await forget_service.trigger_forgetting_cycle(
|
||||
db=db,
|
||||
end_user_id=end_user_id, # 服务层方法的参数名是 end_user_id
|
||||
max_merge_batch_size=payload.max_merge_batch_size,
|
||||
min_days_since_access=payload.min_days_since_access,
|
||||
config_id=config_id
|
||||
)
|
||||
|
||||
# 构建响应
|
||||
response_data = ForgettingReportResponse(**report)
|
||||
|
||||
return success(data=response_data.model_dump(), msg="遗忘周期执行成功")
|
||||
|
||||
except RuntimeError as e:
|
||||
api_logger.warning(f"遗忘周期执行被拒绝: {str(e)}")
|
||||
return fail(BizCode.INVALID_PARAMETER, str(e), "RuntimeError")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"触发遗忘周期失败: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "触发遗忘周期失败", str(e))
|
||||
|
||||
|
||||
@router.get("/read_config", response_model=ApiResponse)
|
||||
async def read_forgetting_config(
|
||||
config_id: UUID|int,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
获取遗忘引擎配置
|
||||
|
||||
读取指定配置ID的遗忘引擎参数。
|
||||
|
||||
Args:
|
||||
config_id: 配置ID
|
||||
current_user: 当前用户
|
||||
db: 数据库会话
|
||||
|
||||
Returns:
|
||||
ApiResponse: 包含配置信息的响应
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试读取遗忘引擎配置但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 在工作空间 {workspace_id} 请求读取遗忘引擎配置: {config_id}"
|
||||
)
|
||||
|
||||
try:
|
||||
config_id=resolve_config_id(config_id, db)
|
||||
# 调用服务层读取配置
|
||||
config = forget_service.read_forgetting_config(db=db, config_id=config_id)
|
||||
|
||||
# 构建响应
|
||||
response_data = ForgettingConfigResponse(**config)
|
||||
|
||||
return success(data=response_data.model_dump(), msg="查询成功")
|
||||
|
||||
except ValueError as e:
|
||||
api_logger.warning(f"配置不存在: config_id={config_id}, 错误: {str(e)}")
|
||||
return fail(BizCode.INVALID_PARAMETER, f"配置不存在: {config_id}", str(e))
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"读取遗忘引擎配置失败: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "查询遗忘引擎配置失败", str(e))
|
||||
|
||||
|
||||
@router.post("/update_config", response_model=ApiResponse)
|
||||
async def update_forgetting_config(
|
||||
payload: ForgettingConfigUpdateRequest,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
更新遗忘引擎配置
|
||||
|
||||
更新指定配置ID的遗忘引擎参数。
|
||||
|
||||
Args:
|
||||
payload: 配置更新请求
|
||||
current_user: 当前用户
|
||||
db: 数据库会话
|
||||
|
||||
Returns:
|
||||
ApiResponse: 包含更新结果的响应
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
payload.config_id=resolve_config_id((payload.config_id), db)
|
||||
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试更新遗忘引擎配置但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 在工作空间 {workspace_id} 请求更新遗忘引擎配置: {payload.config_id}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 构建更新字段字典（排除 None 值和 config_id）
|
||||
update_data = {
|
||||
key: value
|
||||
for key, value in payload.model_dump(exclude_none=True).items()
|
||||
if key != 'config_id'
|
||||
}
|
||||
|
||||
# 调用服务层更新配置
|
||||
config = forget_service.update_forgetting_config(
|
||||
db=db,
|
||||
config_id=payload.config_id,
|
||||
update_fields=update_data
|
||||
)
|
||||
|
||||
# 构建响应
|
||||
response_data = ForgettingConfigResponse(**config)
|
||||
|
||||
return success(data=response_data.model_dump(), msg="更新成功")
|
||||
|
||||
except ValueError as e:
|
||||
api_logger.warning(f"配置不存在: config_id={payload.config_id}, 错误: {str(e)}")
|
||||
return fail(BizCode.INVALID_PARAMETER, str(e), "ValueError")
|
||||
|
||||
except Exception as e:
|
||||
db.rollback()
|
||||
api_logger.error(f"更新遗忘引擎配置失败: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "更新遗忘引擎配置失败", str(e))
|
||||
|
||||
|
||||
@router.get("/stats", response_model=ApiResponse)
|
||||
async def get_forgetting_stats(
|
||||
end_user_id: Optional[str] = None,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
获取遗忘引擎统计信息
|
||||
|
||||
返回知识层节点统计、激活值分布等信息。
|
||||
|
||||
Args:
|
||||
end_user_id: 组ID（即 end_user_id，可选）
|
||||
current_user: 当前用户
|
||||
db: 数据库会话
|
||||
|
||||
Returns:
|
||||
ApiResponse: 包含统计信息的响应
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试获取遗忘引擎统计但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
# 如果提供了 end_user_id，通过它获取 config_id
|
||||
config_id = None
|
||||
if end_user_id:
|
||||
try:
|
||||
from app.services.memory_agent_service import get_end_user_connected_config
|
||||
|
||||
connected_config = get_end_user_connected_config(end_user_id, db)
|
||||
config_id = connected_config.get("memory_config_id")
|
||||
config_id = resolve_config_id(config_id, db)
|
||||
|
||||
if config_id is None:
|
||||
api_logger.warning(f"终端用户 {end_user_id} 未关联记忆配置")
|
||||
return fail(BizCode.INVALID_PARAMETER, f"终端用户 {end_user_id} 未关联记忆配置", "memory_config_id is None")
|
||||
|
||||
api_logger.debug(f"通过 end_user_id={end_user_id} 获取到 config_id={config_id}")
|
||||
except ValueError as e:
|
||||
api_logger.warning(f"获取终端用户配置失败: {str(e)}")
|
||||
return fail(BizCode.INVALID_PARAMETER, str(e), "ValueError")
|
||||
except Exception as e:
|
||||
api_logger.error(f"获取终端用户配置时发生错误: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "获取终端用户配置失败", str(e))
|
||||
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 在工作空间 {workspace_id} 请求获取遗忘引擎统计: "
|
||||
f"end_user_id={end_user_id}, config_id={config_id}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 调用服务层获取统计信息
|
||||
stats = await forget_service.get_forgetting_stats(
|
||||
db=db,
|
||||
end_user_id=end_user_id,
|
||||
config_id=config_id
|
||||
)
|
||||
|
||||
# 构建响应
|
||||
response_data = ForgettingStatsResponse(**stats)
|
||||
|
||||
return success(data=response_data.model_dump(), msg="查询成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"获取遗忘引擎统计失败: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "获取遗忘引擎统计失败", str(e))
|
||||
|
||||
|
||||
@router.post("/forgetting_curve", response_model=ApiResponse)
|
||||
async def get_forgetting_curve(
|
||||
request: ForgettingCurveRequest,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
获取遗忘曲线数据
|
||||
|
||||
生成遗忘曲线数据用于可视化，模拟记忆激活值随时间的衰减。
|
||||
|
||||
Args:
|
||||
request: 遗忘曲线请求参数
|
||||
current_user: 当前用户
|
||||
db: 数据库会话
|
||||
|
||||
Returns:
|
||||
ApiResponse: 包含遗忘曲线数据的响应
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
request.config_id = resolve_config_id((request.config_id), db)
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试获取遗忘曲线但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
api_logger.info(
|
||||
f"用户 {current_user.username} 在工作空间 {workspace_id} 请求获取遗忘曲线: "
|
||||
f"importance_score={request.importance_score}, days={request.days}, config_id={request.config_id}"
|
||||
)
|
||||
|
||||
try:
|
||||
# 调用服务层生成遗忘曲线
|
||||
result = await forget_service.get_forgetting_curve(
|
||||
db=db,
|
||||
importance_score=request.importance_score,
|
||||
days=request.days,
|
||||
config_id=request.config_id
|
||||
)
|
||||
|
||||
# 转换为响应格式
|
||||
curve_points = [
|
||||
ForgettingCurvePoint(**point)
|
||||
for point in result['curve_data']
|
||||
]
|
||||
|
||||
# 构建响应
|
||||
response_data = ForgettingCurveResponse(
|
||||
curve_data=curve_points,
|
||||
config=result['config']
|
||||
)
|
||||
|
||||
return success(data=response_data.model_dump(), msg="查询成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"获取遗忘曲线失败: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "获取遗忘曲线失败", str(e))
|
||||
@@ -1,255 +0,0 @@
|
||||
import uuid
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import APIRouter, Depends, Query
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.error_codes import BizCode
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import success, fail
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models import User
|
||||
from app.models.memory_perceptual_model import PerceptualType
|
||||
from app.schemas.memory_perceptual_schema import (
|
||||
PerceptualQuerySchema,
|
||||
PerceptualFilter
|
||||
)
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services.memory_perceptual_service import MemoryPerceptualService
|
||||
|
||||
api_logger = get_api_logger()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/memory/perceptual",
|
||||
tags=["Perceptual Memory System"],
|
||||
dependencies=[Depends(get_current_user)]
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/count", response_model=ApiResponse)
|
||||
def get_memory_count(
|
||||
end_user_id: uuid.UUID,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Retrieve perceptual memory statistics for a user group.
|
||||
|
||||
Args:
|
||||
end_user_id: ID of the user group (usually end_user_id in this context)
|
||||
current_user: Current authenticated user
|
||||
db: Database session
|
||||
|
||||
Returns:
|
||||
ApiResponse: Response containing memory count statistics
|
||||
"""
|
||||
api_logger.info(f"Fetching perceptual memory statistics: user={current_user.username}, end_user_id={end_user_id}")
|
||||
|
||||
try:
|
||||
service = MemoryPerceptualService(db)
|
||||
count_stats = service.get_memory_count(end_user_id)
|
||||
|
||||
api_logger.info(f"Memory statistics fetched successfully: total={count_stats.get('total', 0)}")
|
||||
|
||||
return success(
|
||||
data=count_stats,
|
||||
msg="Memory statistics retrieved successfully"
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to fetch memory statistics: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(
|
||||
code=BizCode.INTERNAL_ERROR,
|
||||
msg="Failed to fetch memory statistics",
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/last_visual", response_model=ApiResponse)
|
||||
def get_last_visual_memory(
|
||||
end_user_id: uuid.UUID,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Retrieve the most recent VISION-type memory for a user.
|
||||
|
||||
Args:
|
||||
end_user_id: ID of the user group
|
||||
current_user: Current authenticated user
|
||||
db: Database session
|
||||
|
||||
Returns:
|
||||
ApiResponse: Metadata of the latest visual memory
|
||||
"""
|
||||
api_logger.info(f"Fetching latest visual memory: user={current_user.username}, end_user_id={end_user_id}")
|
||||
|
||||
try:
|
||||
service = MemoryPerceptualService(db)
|
||||
visual_memory = service.get_latest_visual_memory(end_user_id)
|
||||
|
||||
if visual_memory is None:
|
||||
api_logger.info(f"No visual memory found: end_user_id={end_user_id}")
|
||||
return success(
|
||||
data=None,
|
||||
msg="No visual memory available"
|
||||
)
|
||||
|
||||
api_logger.info(f"Latest visual memory retrieved successfully: file={visual_memory.get('file_name')}")
|
||||
|
||||
return success(
|
||||
data=visual_memory,
|
||||
msg="Latest visual memory retrieved successfully"
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to fetch latest visual memory: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(
|
||||
code=BizCode.INTERNAL_ERROR,
|
||||
msg="Failed to fetch latest visual memory",
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/last_listen", response_model=ApiResponse)
|
||||
def get_last_memory_listen(
|
||||
end_user_id: uuid.UUID,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Retrieve the most recent AUDIO-type memory for a user.
|
||||
|
||||
Args:
|
||||
end_user_id: ID of the user group
|
||||
current_user: Current authenticated user
|
||||
db: Database session
|
||||
|
||||
Returns:
|
||||
ApiResponse: Metadata of the latest audio memory
|
||||
"""
|
||||
api_logger.info(f"Fetching latest audio memory: user={current_user.username}, end_user_id={end_user_id}")
|
||||
|
||||
try:
|
||||
service = MemoryPerceptualService(db)
|
||||
audio_memory = service.get_latest_audio_memory(end_user_id)
|
||||
|
||||
if audio_memory is None:
|
||||
api_logger.info(f"No audio memory found: end_user_id={end_user_id}")
|
||||
return success(
|
||||
data=None,
|
||||
msg="No audio memory available"
|
||||
)
|
||||
|
||||
api_logger.info(f"Latest audio memory retrieved successfully: file={audio_memory.get('file_name')}")
|
||||
|
||||
return success(
|
||||
data=audio_memory,
|
||||
msg="Latest audio memory retrieved successfully"
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to fetch latest audio memory: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(
|
||||
code=BizCode.INTERNAL_ERROR,
|
||||
msg="Failed to fetch latest audio memory",
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/last_text", response_model=ApiResponse)
|
||||
def get_last_text_memory(
|
||||
end_user_id: uuid.UUID,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Retrieve the most recent TEXT-type memory for a user.
|
||||
|
||||
Args:
|
||||
end_user_id: ID of the user group
|
||||
current_user: Current authenticated user
|
||||
db: Database session
|
||||
|
||||
Returns:
|
||||
ApiResponse: Metadata of the latest text memory
|
||||
"""
|
||||
api_logger.info(f"Fetching latest text memory: user={current_user.username}, end_user_id={end_user_id}")
|
||||
|
||||
try:
|
||||
# 调用服务层获取最近的文本记忆
|
||||
service = MemoryPerceptualService(db)
|
||||
text_memory = service.get_latest_text_memory(end_user_id)
|
||||
|
||||
if text_memory is None:
|
||||
api_logger.info(f"No text memory found: end_user_id={end_user_id}")
|
||||
return success(
|
||||
data=None,
|
||||
msg="No text memory available"
|
||||
)
|
||||
|
||||
api_logger.info(f"Latest text memory retrieved successfully: file={text_memory.get('file_name')}")
|
||||
|
||||
return success(
|
||||
data=text_memory,
|
||||
msg="Latest text memory retrieved successfully"
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"Failed to fetch latest text memory: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(
|
||||
code=BizCode.INTERNAL_ERROR,
|
||||
msg="Failed to fetch latest text memory",
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/timeline", response_model=ApiResponse)
|
||||
def get_memory_time_line(
|
||||
end_user_id: uuid.UUID,
|
||||
perceptual_type: Optional[PerceptualType] = Query(None, description="感知类型过滤"),
|
||||
page: int = Query(1, ge=1, description="页码"),
|
||||
page_size: int = Query(10, ge=1, le=100, description="每页大小"),
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""Retrieve a timeline of perceptual memories for a user group.
|
||||
|
||||
Args:
|
||||
end_user_id: ID of the user group
|
||||
perceptual_type: Optional filter for perceptual type
|
||||
page: Page number for pagination
|
||||
page_size: Number of items per page
|
||||
current_user: Current authenticated user
|
||||
db: Database session
|
||||
|
||||
Returns:
|
||||
ApiResponse: Timeline data of perceptual memories
|
||||
"""
|
||||
api_logger.info(
|
||||
f"Fetching perceptual memory timeline: user={current_user.username}, "
|
||||
f"end_user_id={end_user_id}, type={perceptual_type}, page={page}"
|
||||
)
|
||||
|
||||
try:
|
||||
query = PerceptualQuerySchema(
|
||||
filter=PerceptualFilter(type=perceptual_type),
|
||||
page=page,
|
||||
page_size=page_size
|
||||
)
|
||||
|
||||
service = MemoryPerceptualService(db)
|
||||
timeline_data = service.get_time_line(end_user_id, query)
|
||||
|
||||
api_logger.info(
|
||||
f"Perceptual memory timeline retrieved successfully: total={timeline_data.total}, "
|
||||
f"returned={len(timeline_data.memories)}"
|
||||
)
|
||||
|
||||
return success(
|
||||
data=timeline_data.model_dump(),
|
||||
msg="Perceptual memory timeline retrieved successfully"
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(
|
||||
f"Failed to fetch perceptual memory timeline: end_user_id={end_user_id}, "
|
||||
f"error={str(e)}"
|
||||
)
|
||||
return fail(
|
||||
code=BizCode.INTERNAL_ERROR,
|
||||
msg="Failed to fetch perceptual memory timeline",
|
||||
)
|
||||
@@ -1,18 +1,16 @@
|
||||
import asyncio
|
||||
import time
|
||||
import uuid
|
||||
from uuid import UUID
|
||||
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.memory.storage_services.reflection_engine.self_reflexion import (
|
||||
ReflectionConfig,
|
||||
ReflectionEngine, ReflectionRange, ReflectionBaseline,
|
||||
ReflectionEngine,
|
||||
)
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.user_model import User
|
||||
from app.repositories.memory_config_repository import MemoryConfigRepository
|
||||
from app.repositories.data_config_repository import DataConfigRepository
|
||||
from app.repositories.neo4j.neo4j_connector import Neo4jConnector
|
||||
from app.schemas.memory_reflection_schemas import Memory_Reflection
|
||||
from app.services.memory_reflection_service import (
|
||||
@@ -21,12 +19,10 @@ from app.services.memory_reflection_service import (
|
||||
)
|
||||
from app.services.model_service import ModelConfigService
|
||||
from dotenv import load_dotenv
|
||||
from fastapi import APIRouter, Depends, HTTPException, status,Header
|
||||
from fastapi import APIRouter, Depends, HTTPException, status
|
||||
from sqlalchemy import text
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.utils.config_utils import resolve_config_id
|
||||
|
||||
load_dotenv()
|
||||
api_logger = get_api_logger()
|
||||
|
||||
@@ -43,9 +39,11 @@ async def save_reflection_config(
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
"""Save reflection configuration to data_comfig table"""
|
||||
|
||||
|
||||
|
||||
try:
|
||||
config_id = request.config_id
|
||||
config_id = resolve_config_id(config_id, db)
|
||||
if not config_id:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
@@ -54,30 +52,51 @@ async def save_reflection_config(
|
||||
|
||||
api_logger.info(f"用户 {current_user.username} 保存反思配置，config_id: {config_id}")
|
||||
|
||||
memory_config = MemoryConfigRepository.update_reflection_config(
|
||||
db,
|
||||
config_id=config_id,
|
||||
enable_self_reflexion=request.reflection_enabled,
|
||||
iteration_period=request.reflection_period_in_hours,
|
||||
reflexion_range=request.reflexion_range,
|
||||
baseline=request.baseline,
|
||||
reflection_model_id=request.reflection_model_id,
|
||||
memory_verify=request.memory_verify,
|
||||
quality_assessment=request.quality_assessment
|
||||
)
|
||||
update_params = {
|
||||
"enable_self_reflexion": request.reflection_enabled,
|
||||
"iteration_period": request.reflection_period_in_hours,
|
||||
"reflexion_range": request.reflexion_range,
|
||||
"baseline": request.baseline,
|
||||
"reflection_model_id": request.reflection_model_id,
|
||||
"memory_verify": request.memory_verify,
|
||||
"quality_assessment": request.quality_assessment,
|
||||
}
|
||||
|
||||
|
||||
|
||||
query, params = DataConfigRepository.build_update_reflection(config_id, **update_params)
|
||||
|
||||
result = db.execute(text(query), params)
|
||||
if result.rowcount == 0:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail=f"未找到config_id为 {config_id} 的配置"
|
||||
)
|
||||
|
||||
db.commit()
|
||||
db.refresh(memory_config)
|
||||
|
||||
# 查询更新后的配置
|
||||
select_query, select_params = DataConfigRepository.build_select_reflection(config_id)
|
||||
result = db.execute(text(select_query), select_params).fetchone()
|
||||
|
||||
if not result:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail=f"更新后未找到config_id为 {config_id} 的配置"
|
||||
)
|
||||
|
||||
api_logger.info(f"成功保存反思配置到数据库，config_id: {config_id}")
|
||||
|
||||
reflection_result={
|
||||
"config_id": memory_config.config_id,
|
||||
"enable_self_reflexion": memory_config.enable_self_reflexion,
|
||||
"iteration_period": memory_config.iteration_period,
|
||||
"reflexion_range": memory_config.reflexion_range,
|
||||
"baseline": memory_config.baseline,
|
||||
"reflection_model_id": memory_config.reflection_model_id,
|
||||
"memory_verify": memory_config.memory_verify,
|
||||
"quality_assessment": memory_config.quality_assessment}
|
||||
"config_id": result.config_id,
|
||||
"enable_self_reflexion": result.enable_self_reflexion,
|
||||
"iteration_period": result.iteration_period,
|
||||
"reflexion_range": result.reflexion_range,
|
||||
"baseline": result.baseline,
|
||||
"reflection_model_id": result.reflection_model_id,
|
||||
"memory_verify": result.memory_verify,
|
||||
"quality_assessment": result.quality_assessment,
|
||||
"user_id": result.user_id}
|
||||
|
||||
return success(data=reflection_result, msg="反思配置成功")
|
||||
|
||||
@@ -97,8 +116,9 @@ async def save_reflection_config(
|
||||
)
|
||||
|
||||
|
||||
@router.get("/reflection")
|
||||
@router.post("/reflection")
|
||||
async def start_workspace_reflection(
|
||||
config_id: int,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
@@ -115,28 +135,19 @@ async def start_workspace_reflection(
|
||||
reflection_results = []
|
||||
|
||||
for data in result['apps_detailed_info']:
|
||||
if data['memory_configs'] == []:
|
||||
if data['data_configs'] == []:
|
||||
continue
|
||||
|
||||
releases = data['releases']
|
||||
memory_configs = data['memory_configs']
|
||||
data_configs = data['data_configs']
|
||||
end_users = data['end_users']
|
||||
|
||||
for base, config, user in zip(releases, memory_configs, end_users):
|
||||
# 安全地转换为整数，处理空字符串和None的情况
|
||||
print(base['config'])
|
||||
try:
|
||||
base_config = int(base['config']) if base['config'] else 0
|
||||
config_id = int(config['config_id']) if config['config_id'] else 0
|
||||
except (ValueError, TypeError):
|
||||
api_logger.warning(f"无效的配置ID: base['config']={base.get('config')}, config['config_id']={config.get('config_id')}")
|
||||
continue
|
||||
|
||||
if base_config == config_id and base['app_id'] == user['app_id']:
|
||||
for base, config, user in zip(releases, data_configs, end_users):
|
||||
if int(base['config']) == int(config['config_id']) and base['app_id'] == user['app_id']:
|
||||
# 调用反思服务
|
||||
api_logger.info(f"为用户 {user['id']} 启动反思，config_id: {config['config_id']}")
|
||||
|
||||
reflection_result = await reflection_service.start_text_reflection(
|
||||
reflection_result = await reflection_service.start_reflection_from_data(
|
||||
config_data=config,
|
||||
end_user_id=user['id']
|
||||
)
|
||||
@@ -160,27 +171,35 @@ async def start_workspace_reflection(
|
||||
|
||||
@router.get("/reflection/configs")
|
||||
async def start_reflection_configs(
|
||||
config_id: uuid.UUID|int,
|
||||
config_id: int,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
"""通过config_id查询memory_config表中的反思配置信息"""
|
||||
config_id = resolve_config_id(config_id, db)
|
||||
"""通过config_id查询data_config表中的反思配置信息"""
|
||||
try:
|
||||
config_id=resolve_config_id(config_id,db)
|
||||
api_logger.info(f"用户 {current_user.username} 查询反思配置，config_id: {config_id}")
|
||||
result = MemoryConfigRepository.query_reflection_config_by_id(db, config_id)
|
||||
memory_config_id = resolve_config_id(result.config_id, db)
|
||||
|
||||
# 使用DataConfigRepository查询反思配置
|
||||
select_query, select_params = DataConfigRepository.build_select_reflection(config_id)
|
||||
result = db.execute(text(select_query), select_params).fetchone()
|
||||
|
||||
if not result:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
detail=f"未找到config_id为 {config_id} 的配置"
|
||||
)
|
||||
|
||||
# 构建返回数据
|
||||
reflection_config = {
|
||||
"config_id": memory_config_id,
|
||||
"config_id": result.config_id,
|
||||
"reflection_enabled": result.enable_self_reflexion,
|
||||
"reflection_period_in_hours": result.iteration_period,
|
||||
"reflexion_range": result.reflexion_range,
|
||||
"baseline": result.baseline,
|
||||
"reflection_model_id": result.reflection_model_id,
|
||||
"memory_verify": result.memory_verify,
|
||||
"quality_assessment": result.quality_assessment
|
||||
"quality_assessment": result.quality_assessment,
|
||||
"user_id": result.user_id
|
||||
}
|
||||
api_logger.info(f"成功查询反思配置，config_id: {config_id}")
|
||||
return success(data=reflection_config, msg="反思配置查询成功")
|
||||
@@ -198,17 +217,19 @@ async def start_reflection_configs(
|
||||
|
||||
@router.get("/reflection/run")
|
||||
async def reflection_run(
|
||||
config_id: UUID|int,
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
config_id: int,
|
||||
language_type: str = "zh",
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
"""Activate the reflection function for all matching applications in the workspace"""
|
||||
|
||||
api_logger.info(f"用户 {current_user.username} 查询反思配置，config_id: {config_id}")
|
||||
config_id = resolve_config_id(config_id, db)
|
||||
# 使用MemoryConfigRepository查询反思配置
|
||||
result = MemoryConfigRepository.query_reflection_config_by_id(db, config_id)
|
||||
|
||||
# 使用DataConfigRepository查询反思配置
|
||||
select_query, select_params = DataConfigRepository.build_select_reflection(config_id)
|
||||
result = db.execute(text(select_query), select_params).fetchone()
|
||||
|
||||
if not result:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_404_NOT_FOUND,
|
||||
@@ -221,7 +242,7 @@ async def reflection_run(
|
||||
model_id = result.reflection_model_id
|
||||
if model_id:
|
||||
try:
|
||||
ModelConfigService.get_model_by_id(db=db, model_id=uuid.UUID(model_id))
|
||||
ModelConfigService.get_model_by_id(db=db, model_id=model_id)
|
||||
api_logger.info(f"模型ID验证成功: {model_id}")
|
||||
except Exception as e:
|
||||
api_logger.warning(f"模型ID '{model_id}' 不存在，将使用默认模型: {str(e)}")
|
||||
@@ -231,8 +252,8 @@ async def reflection_run(
|
||||
config = ReflectionConfig(
|
||||
enabled=result.enable_self_reflexion,
|
||||
iteration_period=result.iteration_period,
|
||||
reflexion_range=ReflectionRange(result.reflexion_range),
|
||||
baseline=ReflectionBaseline(result.baseline),
|
||||
reflexion_range=result.reflexion_range,
|
||||
baseline=result.baseline,
|
||||
output_example='',
|
||||
memory_verify=result.memory_verify,
|
||||
quality_assessment=result.quality_assessment,
|
||||
|
||||
@@ -1,44 +0,0 @@
|
||||
from fastapi import APIRouter, Depends, HTTPException, status,Header
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.user_model import User
|
||||
|
||||
from app.services.memory_storage_service import search_entity
|
||||
from app.services.memory_short_service import ShortService,LongService
|
||||
from dotenv import load_dotenv
|
||||
from sqlalchemy.orm import Session
|
||||
from typing import Optional
|
||||
load_dotenv()
|
||||
api_logger = get_api_logger()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/memory/short",
|
||||
tags=["Memory"],
|
||||
)
|
||||
@router.get("/short_term")
|
||||
async def short_term_configs(
|
||||
end_user_id: str,
|
||||
language_type:str = Header(default="zh", alias="X-Language-Type"),
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
# 获取短期记忆数据
|
||||
short_term=ShortService(end_user_id)
|
||||
short_result=short_term.get_short_databasets()
|
||||
short_count=short_term.get_short_count()
|
||||
|
||||
long_term=LongService(end_user_id)
|
||||
long_result=long_term.get_long_databasets()
|
||||
|
||||
entity_result = await search_entity(end_user_id)
|
||||
result = {
|
||||
'short_term': short_result,
|
||||
'long_term': long_result,
|
||||
'entity': entity_result.get('num', 0),
|
||||
"retrieval_number":short_count,
|
||||
"long_term_number":len(long_result)
|
||||
}
|
||||
|
||||
return success(data=result, msg="短期记忆系统数据获取成功")
|
||||
@@ -1,13 +1,20 @@
|
||||
import datetime
|
||||
import os
|
||||
import uuid
|
||||
from typing import Optional
|
||||
from uuid import UUID
|
||||
|
||||
from app.core.error_codes import BizCode
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.memory.utils.self_reflexion_utils import self_reflexion
|
||||
from app.core.response_utils import fail, success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.end_user_model import EndUser
|
||||
from app.models.user_model import User
|
||||
from app.schemas.end_user_schema import (
|
||||
EndUserProfileResponse,
|
||||
EndUserProfileUpdate,
|
||||
)
|
||||
from app.schemas.memory_storage_schema import (
|
||||
ConfigKey,
|
||||
ConfigParamsCreate,
|
||||
@@ -15,6 +22,8 @@ from app.schemas.memory_storage_schema import (
|
||||
ConfigPilotRun,
|
||||
ConfigUpdate,
|
||||
ConfigUpdateExtracted,
|
||||
ConfigUpdateForget,
|
||||
GenerateCacheRequest,
|
||||
)
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services.memory_storage_service import (
|
||||
@@ -29,14 +38,13 @@ from app.services.memory_storage_service import (
|
||||
search_dialogue,
|
||||
search_edges,
|
||||
search_entity,
|
||||
search_entity_graph,
|
||||
search_statement,
|
||||
)
|
||||
from fastapi import APIRouter, Depends
|
||||
from fastapi.responses import StreamingResponse
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.utils.config_utils import resolve_config_id
|
||||
|
||||
# Get API logger
|
||||
api_logger = get_api_logger()
|
||||
|
||||
@@ -143,6 +151,7 @@ def create_config(
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试创建配置但未选择工作空间")
|
||||
@@ -162,12 +171,12 @@ def create_config(
|
||||
|
||||
@router.delete("/delete_config", response_model=ApiResponse) # 删除数据库中的内容（按配置名称）
|
||||
def delete_config(
|
||||
config_id: UUID|int,
|
||||
config_id: str,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
config_id=resolve_config_id(config_id, db)
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试删除配置但未选择工作空间")
|
||||
@@ -189,7 +198,7 @@ def update_config(
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
payload.config_id = resolve_config_id(payload.config_id, db)
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试更新配置但未选择工作空间")
|
||||
@@ -212,7 +221,7 @@ def update_config_extracted(
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
payload.config_id = resolve_config_id(payload.config_id, db)
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试更新提取配置但未选择工作空间")
|
||||
@@ -229,17 +238,37 @@ def update_config_extracted(
|
||||
|
||||
|
||||
# --- Forget config params ---
|
||||
# 遗忘引擎配置接口已迁移到 memory_forget_controller.py
|
||||
# 使用新接口: /api/memory/forget/read_config 和 /api/memory/forget/update_config
|
||||
|
||||
@router.get("/read_config_extracted", response_model=ApiResponse) # 通过查询参数读取某条配置（固定路径） 没有意义的话就删除
|
||||
def read_config_extracted(
|
||||
config_id: UUID | int,
|
||||
@router.post("/update_config_forget", response_model=ApiResponse) # 更新遗忘引擎配置参数（固定路径）
|
||||
def update_config_forget(
|
||||
payload: ConfigUpdateForget,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
config_id = resolve_config_id(config_id, db)
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试更新遗忘引擎配置但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
api_logger.info(f"用户 {current_user.username} 在工作空间 {workspace_id} 请求更新遗忘引擎配置: {payload.config_id}")
|
||||
try:
|
||||
svc = DataConfigService(db)
|
||||
result = svc.update_forget(payload)
|
||||
return success(data=result, msg="更新成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"Update config forget failed: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "更新遗忘引擎配置失败", str(e))
|
||||
|
||||
|
||||
@router.get("/read_config_extracted", response_model=ApiResponse) # 通过查询参数读取某条配置（固定路径） 没有意义的话就删除
|
||||
def read_config_extracted(
|
||||
config_id: str,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试读取提取配置但未选择工作空间")
|
||||
@@ -254,6 +283,28 @@ def read_config_extracted(
|
||||
api_logger.error(f"Read config extracted failed: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "查询配置失败", str(e))
|
||||
|
||||
@router.get("/read_config_forget", response_model=ApiResponse) # 通过查询参数读取某条配置（固定路径） 没有意义的话就删除
|
||||
def read_config_forget(
|
||||
config_id: str,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试读取遗忘引擎配置但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
api_logger.info(f"用户 {current_user.username} 在工作空间 {workspace_id} 请求读取遗忘引擎配置: {config_id}")
|
||||
try:
|
||||
svc = DataConfigService(db)
|
||||
result = svc.get_forget(ConfigKey(config_id=config_id))
|
||||
return success(data=result, msg="查询成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"Read config forget failed: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "查询遗忘引擎配置失败", str(e))
|
||||
|
||||
@router.get("/read_all_config", response_model=ApiResponse) # 读取所有配置文件列表
|
||||
def read_all_config(
|
||||
current_user: User = Depends(get_current_user),
|
||||
@@ -287,7 +338,6 @@ async def pilot_run(
|
||||
f"Pilot run requested: config_id={payload.config_id}, "
|
||||
f"dialogue_text_length={len(payload.dialogue_text)}"
|
||||
)
|
||||
payload.config_id = resolve_config_id(payload.config_id, db)
|
||||
svc = DataConfigService(db)
|
||||
return StreamingResponse(
|
||||
svc.pilot_run_stream(payload),
|
||||
@@ -414,7 +464,21 @@ async def search_entity_edges(
|
||||
api_logger.error(f"Search edges failed: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "边查询失败", str(e))
|
||||
|
||||
|
||||
@router.get("/search/entity_graph", response_model=ApiResponse)
|
||||
async def search_for_entity_graph(
|
||||
end_user_id: Optional[str] = None,
|
||||
current_user: User = Depends(get_current_user),
|
||||
) -> dict:
|
||||
"""
|
||||
搜索所有实体之间的关系网络
|
||||
"""
|
||||
api_logger.info(f"Search entity graph requested for end_user_id: {end_user_id}")
|
||||
try:
|
||||
result = await search_entity_graph(end_user_id)
|
||||
return success(data=result, msg="查询成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"Search entity graph failed: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "实体图查询失败", str(e))
|
||||
|
||||
|
||||
@router.get("/analytics/hot_memory_tags", response_model=ApiResponse)
|
||||
@@ -423,95 +487,15 @@ async def get_hot_memory_tags_api(
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user),
|
||||
) -> dict:
|
||||
"""
|
||||
获取热门记忆标签（带Redis缓存）
|
||||
|
||||
缓存策略：
|
||||
- 缓存键：workspace_id + limit
|
||||
- 过期时间：5分钟（300秒）
|
||||
- 缓存命中：~50ms
|
||||
- 缓存未命中：~600-800ms（取决于LLM速度）
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 构建缓存键
|
||||
cache_key = f"hot_memory_tags:{workspace_id}:{limit}"
|
||||
|
||||
api_logger.info(f"Hot memory tags requested for workspace: {workspace_id}, limit: {limit}")
|
||||
|
||||
api_logger.info(f"Hot memory tags requested for current_user: {current_user.id}")
|
||||
try:
|
||||
# 尝试从Redis缓存获取
|
||||
from app.aioRedis import aio_redis_get, aio_redis_set
|
||||
import json
|
||||
|
||||
cached_result = await aio_redis_get(cache_key)
|
||||
if cached_result:
|
||||
api_logger.info(f"Cache hit for key: {cache_key}")
|
||||
try:
|
||||
data = json.loads(cached_result)
|
||||
return success(data=data, msg="查询成功（缓存）")
|
||||
except json.JSONDecodeError:
|
||||
api_logger.warning(f"Failed to parse cached data, will refresh")
|
||||
|
||||
# 缓存未命中，执行查询
|
||||
api_logger.info(f"Cache miss for key: {cache_key}, executing query")
|
||||
result = await analytics_hot_memory_tags(db, current_user, limit)
|
||||
|
||||
# 写入缓存（过期时间：5分钟）
|
||||
# 注意：result是列表，需要转换为JSON字符串
|
||||
try:
|
||||
cache_data = json.dumps(result, ensure_ascii=False)
|
||||
await aio_redis_set(cache_key, cache_data, expire=300)
|
||||
api_logger.info(f"Cached result for key: {cache_key}")
|
||||
except Exception as cache_error:
|
||||
# 缓存写入失败不影响主流程
|
||||
api_logger.warning(f"Failed to cache result: {str(cache_error)}")
|
||||
|
||||
return success(data=result, msg="查询成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"Hot memory tags failed: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "热门标签查询失败", str(e))
|
||||
|
||||
|
||||
@router.delete("/analytics/hot_memory_tags/cache", response_model=ApiResponse)
|
||||
async def clear_hot_memory_tags_cache(
|
||||
current_user: User = Depends(get_current_user),
|
||||
) -> dict:
|
||||
"""
|
||||
清除热门标签缓存
|
||||
|
||||
用于：
|
||||
- 手动刷新数据
|
||||
- 调试和测试
|
||||
- 数据更新后立即生效
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
api_logger.info(f"Clear hot memory tags cache requested for workspace: {workspace_id}")
|
||||
|
||||
try:
|
||||
from app.aioRedis import aio_redis_delete
|
||||
|
||||
# 清除所有limit的缓存（常见的limit值）
|
||||
cleared_count = 0
|
||||
for limit in [5, 10, 15, 20, 30, 50]:
|
||||
cache_key = f"hot_memory_tags:{workspace_id}:{limit}"
|
||||
result = await aio_redis_delete(cache_key)
|
||||
if result:
|
||||
cleared_count += 1
|
||||
api_logger.info(f"Cleared cache for key: {cache_key}")
|
||||
|
||||
return success(
|
||||
data={"cleared_count": cleared_count},
|
||||
msg=f"成功清除 {cleared_count} 个缓存"
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"Clear cache failed: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "清除缓存失败", str(e))
|
||||
|
||||
|
||||
@router.get("/analytics/recent_activity_stats", response_model=ApiResponse)
|
||||
async def get_recent_activity_stats_api(
|
||||
current_user: User = Depends(get_current_user),
|
||||
@@ -524,3 +508,18 @@ async def get_recent_activity_stats_api(
|
||||
api_logger.error(f"Recent activity stats failed: {str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "最近活动统计失败", str(e))
|
||||
|
||||
|
||||
|
||||
|
||||
@router.get("/self_reflexion")
|
||||
async def self_reflexion_endpoint(host_id: uuid.UUID) -> str:
|
||||
"""
|
||||
自我反思接口，自动对检索出的信息进行自我反思并返回自我反思结果。
|
||||
|
||||
Args:
|
||||
None
|
||||
Returns:
|
||||
自我反思结果。
|
||||
"""
|
||||
return await self_reflexion(host_id)
|
||||
|
||||
|
||||
@@ -1,134 +0,0 @@
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Depends
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models import User
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services.conversation_service import ConversationService
|
||||
|
||||
api_logger = get_api_logger()
|
||||
|
||||
router = APIRouter(
|
||||
prefix="/memory/work",
|
||||
tags=["Working Memory System"],
|
||||
dependencies=[Depends(get_current_user)]
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/count", response_model=ApiResponse)
|
||||
def get_memory_count(
|
||||
end_user_id: uuid.UUID,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
pass
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/conversations", response_model=ApiResponse)
|
||||
def get_conversations(
|
||||
end_user_id: uuid.UUID,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
Retrieve all conversations for the current user in a specific group.
|
||||
|
||||
Args:
|
||||
end_user_id (UUID): The group identifier.
|
||||
current_user (User, optional): The authenticated user.
|
||||
db (Session, optional): SQLAlchemy session.
|
||||
|
||||
Returns:
|
||||
ApiResponse: Contains a list of conversation IDs.
|
||||
|
||||
Notes:
|
||||
- Initializes the ConversationService with the current DB session.
|
||||
- Returns only conversation IDs for lightweight response.
|
||||
- Logs can be added to trace requests in production.
|
||||
"""
|
||||
conversation_service = ConversationService(db)
|
||||
conversations = conversation_service.get_user_conversations(
|
||||
end_user_id
|
||||
)
|
||||
return success(data=[
|
||||
{
|
||||
"id": conversation.id,
|
||||
"title": conversation.title
|
||||
} for conversation in conversations
|
||||
], msg="get conversations success")
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/messages", response_model=ApiResponse)
|
||||
def get_messages(
|
||||
conversation_id: uuid.UUID,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
Retrieve the message history for a specific conversation.
|
||||
|
||||
Args:
|
||||
conversation_id (UUID): The ID of the conversation to fetch messages from.
|
||||
current_user (User, optional): The authenticated user.
|
||||
db (Session, optional): SQLAlchemy session.
|
||||
|
||||
Returns:
|
||||
ApiResponse: Contains the list of messages in the conversation.
|
||||
|
||||
Notes:
|
||||
- Uses ConversationService to fetch messages.
|
||||
- Consider paginating results if message history is large.
|
||||
- Logging can be added for audit and debugging.
|
||||
"""
|
||||
conversation_service = ConversationService(db)
|
||||
messages_obj = conversation_service.get_messages(
|
||||
conversation_id,
|
||||
)
|
||||
messages = [
|
||||
{
|
||||
"role": message.role,
|
||||
"content": message.content,
|
||||
"created_at": int(message.created_at.timestamp() * 1000),
|
||||
}
|
||||
for message in messages_obj
|
||||
]
|
||||
return success(data=messages, msg="get conversation history success")
|
||||
|
||||
|
||||
@router.get("/{end_user_id}/detail", response_model=ApiResponse)
|
||||
async def get_conversation_detail(
|
||||
conversation_id: uuid.UUID,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""
|
||||
Retrieve detailed information about a specific conversation.
|
||||
|
||||
This endpoint will fetch the conversation detail for the user. If the detail
|
||||
does not exist or is outdated, it will trigger the LLM to generate a new summary.
|
||||
|
||||
Args:
|
||||
conversation_id (UUID): The ID of the conversation.
|
||||
current_user (User, optional): The authenticated user making the request.
|
||||
db (Session, optional): SQLAlchemy session.
|
||||
|
||||
Returns:
|
||||
ApiResponse: Contains the conversation detail serialized as a dictionary.
|
||||
|
||||
Notes:
|
||||
- Uses async ConversationService to fetch or generate the conversation detail.
|
||||
- Handles workspace and user-specific context automatically.
|
||||
- Logging and exception handling should be implemented for production monitoring.
|
||||
"""
|
||||
conversation_service = ConversationService(db)
|
||||
detail = await conversation_service.get_conversation_detail(
|
||||
user=current_user,
|
||||
conversation_id=conversation_id,
|
||||
workspace_id=current_user.current_workspace_id
|
||||
)
|
||||
return success(data=detail.model_dump(), msg="get conversation detail success")
|
||||
@@ -3,17 +3,15 @@ from sqlalchemy.orm import Session
|
||||
from typing import Optional
|
||||
import uuid
|
||||
|
||||
from app.core.error_codes import BizCode
|
||||
from app.core.exceptions import BusinessException
|
||||
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.models_model import ModelProvider, ModelType, LoadBalanceStrategy
|
||||
from app.models.models_model import ModelProvider, ModelType
|
||||
from app.models.user_model import User
|
||||
from app.repositories.model_repository import ModelConfigRepository
|
||||
from app.schemas import model_schema
|
||||
from app.core.response_utils import success
|
||||
from app.schemas.response_schema import ApiResponse, PageData
|
||||
from app.services.model_service import ModelConfigService, ModelApiKeyService, ModelBaseService
|
||||
from app.services.model_service import ModelConfigService, ModelApiKeyService
|
||||
from app.core.logging_config import get_api_logger
|
||||
|
||||
# 获取API专用日志器
|
||||
@@ -26,54 +24,44 @@ router = APIRouter(
|
||||
|
||||
@router.get("/type", response_model=ApiResponse)
|
||||
def get_model_types():
|
||||
|
||||
return success(msg="获取模型类型成功", data=list(ModelType))
|
||||
|
||||
|
||||
@router.get("/provider", response_model=ApiResponse)
|
||||
def get_model_providers():
|
||||
providers = [p for p in ModelProvider if p != ModelProvider.COMPOSITE]
|
||||
return success(msg="获取模型提供商成功", data=providers)
|
||||
|
||||
@router.get("/strategy", response_model=ApiResponse)
|
||||
def get_model_strategies():
|
||||
return success(msg="获取模型策略成功", data=list(LoadBalanceStrategy))
|
||||
return success(msg="获取模型提供商成功", data=list(ModelProvider))
|
||||
|
||||
|
||||
@router.get("", response_model=ApiResponse)
|
||||
def get_model_list(
|
||||
type: Optional[list[str]] = Query(None, description="模型类型筛选（支持多个，如 ?type=LLM 或 ?type=LLM,EMBEDDING）"),
|
||||
provider: Optional[model_schema.ModelProvider] = Query(None, description="提供商筛选(基于API Key)"),
|
||||
is_active: Optional[bool] = Query(None, description="激活状态筛选"),
|
||||
is_public: Optional[bool] = Query(None, description="公开状态筛选"),
|
||||
search: Optional[str] = Query(None, description="搜索关键词"),
|
||||
page: int = Query(1, ge=1, description="页码"),
|
||||
pagesize: int = Query(10, ge=1, le=100, description="每页数量"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
type: Optional[str] = Query(None, description="模型类型筛选（支持多个，如 ?type=LLM 或 ?type=LLM,EMBEDDING）"),
|
||||
provider: Optional[model_schema.ModelProvider] = Query(None, description="提供商筛选(基于API Key)"),
|
||||
is_active: Optional[bool] = Query(None, description="激活状态筛选"),
|
||||
is_public: Optional[bool] = Query(None, description="公开状态筛选"),
|
||||
search: Optional[str] = Query(None, description="搜索关键词"),
|
||||
page: int = Query(1, ge=1, description="页码"),
|
||||
pagesize: int = Query(10, ge=1, le=100, description="每页数量"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
获取模型配置列表
|
||||
|
||||
|
||||
支持多个 type 参数：
|
||||
- 单个：?type=LLM
|
||||
- 多个（逗号分隔）：?type=LLM,EMBEDDING
|
||||
- 多个（重复参数）：?type=LLM&type=EMBEDDING
|
||||
"""
|
||||
api_logger.info(
|
||||
f"获取模型配置列表请求: type={type}, provider={provider}, page={page}, pagesize={pagesize}, tenant_id={current_user.tenant_id}")
|
||||
|
||||
api_logger.info(f"获取模型配置列表请求: type={type}, provider={provider}, page={page}, pagesize={pagesize}, tenant_id={current_user.tenant_id}")
|
||||
|
||||
try:
|
||||
# 解析 type 参数（支持逗号分隔）
|
||||
type_list = []
|
||||
if type is not None:
|
||||
flat_type = []
|
||||
for item in type:
|
||||
split_items = [t.strip() for t in item.split(',') if t.strip()]
|
||||
flat_type.extend(split_items)
|
||||
|
||||
unique_flat_type = list(dict.fromkeys(flat_type))
|
||||
type_list = [ModelType(t.lower()) for t in unique_flat_type]
|
||||
|
||||
type_list = None
|
||||
if type:
|
||||
type_values = [t.strip() for t in type.split(',')]
|
||||
type_list = [model_schema.ModelType(t.lower()) for t in type_values if t]
|
||||
|
||||
api_logger.error(f"获取模型type_list: {type_list}")
|
||||
query = model_schema.ModelConfigQuery(
|
||||
type=type_list,
|
||||
@@ -84,7 +72,7 @@ def get_model_list(
|
||||
page=page,
|
||||
pagesize=pagesize
|
||||
)
|
||||
|
||||
|
||||
api_logger.debug(f"开始获取模型配置列表: {query.dict()}")
|
||||
result_orm = ModelConfigService.get_model_list(db=db, query=query, tenant_id=current_user.tenant_id)
|
||||
result = PageData.model_validate(result_orm)
|
||||
@@ -95,146 +83,6 @@ def get_model_list(
|
||||
raise
|
||||
|
||||
|
||||
@router.get("/new", response_model=ApiResponse)
|
||||
def get_model_list_new(
|
||||
type: Optional[list[str]] = Query(None, description="模型类型筛选（支持多个，如 ?type=LLM 或 ?type=LLM,EMBEDDING）"),
|
||||
provider: Optional[model_schema.ModelProvider] = Query(None, description="提供商筛选(基于ModelConfig)"),
|
||||
is_active: Optional[bool] = Query(None, description="激活状态筛选"),
|
||||
is_public: Optional[bool] = Query(None, description="公开状态筛选"),
|
||||
search: Optional[str] = Query(None, description="搜索关键词"),
|
||||
is_composite: Optional[bool] = Query(None, description="组合模型筛选"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
获取模型配置列表
|
||||
|
||||
支持多个 type 参数：
|
||||
- 单个：?type=LLM
|
||||
- 多个（逗号分隔）：?type=LLM,EMBEDDING
|
||||
- 多个（重复参数）：?type=LLM&type=EMBEDDING
|
||||
"""
|
||||
api_logger.info(f"获取模型配置列表请求: type={type}, provider={provider}, tenant_id={current_user.tenant_id}")
|
||||
|
||||
try:
|
||||
# 解析 type 参数（支持逗号分隔）
|
||||
type_list = []
|
||||
if type is not None:
|
||||
flat_type = []
|
||||
for item in type:
|
||||
split_items = [t.strip() for t in item.split(',') if t.strip()]
|
||||
flat_type.extend(split_items)
|
||||
|
||||
unique_flat_type = list(dict.fromkeys(flat_type))
|
||||
type_list = [ModelType(t.lower()) for t in unique_flat_type]
|
||||
|
||||
api_logger.info(f"获取模型type_list: {type_list}")
|
||||
query = model_schema.ModelConfigQueryNew(
|
||||
type=type_list,
|
||||
provider=provider,
|
||||
is_active=is_active,
|
||||
is_public=is_public,
|
||||
is_composite=is_composite,
|
||||
search=search
|
||||
)
|
||||
|
||||
api_logger.debug(f"开始获取模型配置列表: {query.model_dump()}")
|
||||
result = ModelConfigService.get_model_list_new(db=db, query=query, tenant_id=current_user.tenant_id)
|
||||
api_logger.info(f"模型配置列表获取成功: 分组数={len(result)}, 总模型数={sum(len(item['models']) for item in result)}")
|
||||
return success(data=result, msg="模型配置列表获取成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"获取模型配置列表失败: {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
@router.get("/model_plaza", response_model=ApiResponse)
|
||||
def get_model_plaza_list(
|
||||
type: Optional[ModelType] = Query(None, description="模型类型"),
|
||||
provider: Optional[ModelProvider] = Query(None, description="供应商"),
|
||||
is_official: Optional[bool] = Query(None, description="是否官方模型"),
|
||||
is_deprecated: Optional[bool] = Query(None, description="是否弃用"),
|
||||
search: Optional[str] = Query(None, description="搜索关键词"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""模型广场查询接口（按供应商分组）"""
|
||||
|
||||
query = model_schema.ModelBaseQuery(
|
||||
type=type,
|
||||
provider=provider,
|
||||
is_official=is_official,
|
||||
is_deprecated=is_deprecated,
|
||||
search=search
|
||||
)
|
||||
result = ModelBaseService.get_model_base_list(db=db, query=query, tenant_id=current_user.tenant_id)
|
||||
return success(data=result, msg="模型广场列表获取成功")
|
||||
|
||||
|
||||
@router.get("/model_plaza/{model_base_id}", response_model=ApiResponse)
|
||||
def get_model_base_by_id(
|
||||
model_base_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""获取基础模型详情"""
|
||||
|
||||
result = ModelBaseService.get_model_base_by_id(db=db, model_base_id=model_base_id)
|
||||
return success(data=model_schema.ModelBase.model_validate(result), msg="基础模型获取成功")
|
||||
|
||||
|
||||
@router.post("/model_plaza", response_model=ApiResponse)
|
||||
def create_model_base(
|
||||
data: model_schema.ModelBaseCreate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""创建基础模型"""
|
||||
|
||||
result = ModelBaseService.create_model_base(db=db, data=data)
|
||||
return success(data=model_schema.ModelBase.model_validate(result), msg="基础模型创建成功")
|
||||
|
||||
|
||||
@router.put("/model_plaza/{model_base_id}", response_model=ApiResponse)
|
||||
def update_model_base(
|
||||
model_base_id: uuid.UUID,
|
||||
data: model_schema.ModelBaseUpdate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""更新基础模型"""
|
||||
|
||||
# 不允许更改type类型
|
||||
if data.type is not None or data.provider is not None:
|
||||
raise BusinessException("不允许更改模型类型和供应商", BizCode.INVALID_PARAMETER)
|
||||
|
||||
result = ModelBaseService.update_model_base(db=db, model_base_id=model_base_id, data=data)
|
||||
return success(data=model_schema.ModelBase.model_validate(result), msg="基础模型更新成功")
|
||||
|
||||
|
||||
@router.delete("/model_plaza/{model_base_id}", response_model=ApiResponse)
|
||||
def delete_model_base(
|
||||
model_base_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""删除基础模型"""
|
||||
|
||||
ModelBaseService.delete_model_base(db=db, model_base_id=model_base_id)
|
||||
return success(msg="基础模型删除成功")
|
||||
|
||||
|
||||
@router.post("/model_plaza/{model_base_id}/add", response_model=ApiResponse)
|
||||
def add_model_from_plaza(
|
||||
model_base_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""从模型广场添加模型到模型列表"""
|
||||
|
||||
result = ModelBaseService.add_model_from_plaza(db=db, model_base_id=model_base_id, tenant_id=current_user.tenant_id)
|
||||
return success(data=model_schema.ModelConfig.model_validate(result), msg="模型添加成功")
|
||||
|
||||
|
||||
@router.get("/{model_id}", response_model=ApiResponse)
|
||||
def get_model_by_id(
|
||||
model_id: uuid.UUID,
|
||||
@@ -290,73 +138,6 @@ async def create_model(
|
||||
raise
|
||||
|
||||
|
||||
@router.post("/composite", response_model=ApiResponse)
|
||||
async def create_composite_model(
|
||||
model_data: model_schema.CompositeModelCreate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
创建组合模型
|
||||
|
||||
- 绑定一个或多个现有的 API Key
|
||||
- 所有 API Key 必须来自非组合模型
|
||||
- 所有 API Key 关联的模型类型必须与组合模型类型一致
|
||||
"""
|
||||
api_logger.info(f"创建组合模型请求: {model_data.name}, 用户: {current_user.username}, tenant_id={current_user.tenant_id}")
|
||||
|
||||
try:
|
||||
result_orm = await ModelConfigService.create_composite_model(db=db, model_data=model_data, tenant_id=current_user.tenant_id)
|
||||
api_logger.info(f"组合模型创建成功: {result_orm.name} (ID: {result_orm.id})")
|
||||
|
||||
result = model_schema.ModelConfig.model_validate(result_orm)
|
||||
return success(data=result, msg="组合模型创建成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"创建组合模型失败: {model_data.name} - {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
@router.put("/composite/{model_id}", response_model=ApiResponse)
|
||||
async def update_composite_model(
|
||||
model_id: uuid.UUID,
|
||||
model_data: model_schema.CompositeModelCreate,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""更新组合模型"""
|
||||
api_logger.info(f"更新组合模型请求: model_id={model_id}, 用户: {current_user.username}")
|
||||
|
||||
try:
|
||||
if model_data.type is not None:
|
||||
raise BusinessException("不允许更改模型类型和供应商", BizCode.INVALID_PARAMETER)
|
||||
result_orm = await ModelConfigService.update_composite_model(db=db, model_id=model_id, model_data=model_data, tenant_id=current_user.tenant_id)
|
||||
api_logger.info(f"组合模型更新成功: {result_orm.name} (ID: {model_id})")
|
||||
|
||||
result = model_schema.ModelConfig.model_validate(result_orm)
|
||||
return success(data=result, msg="组合模型更新成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"更新组合模型失败: model_id={model_id} - {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
@router.delete("/composite/{model_id}", response_model=ApiResponse)
|
||||
def delete_composite_model(
|
||||
model_id: uuid.UUID,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""删除组合模型"""
|
||||
api_logger.info(f"删除组合模型请求: model_id={model_id}, 用户: {current_user.username}")
|
||||
|
||||
try:
|
||||
ModelConfigService.delete_model(db=db, model_id=model_id, tenant_id=current_user.tenant_id)
|
||||
api_logger.info(f"组合模型删除成功: model_id={model_id}")
|
||||
return success(msg="组合模型删除成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"删除组合模型失败: model_id={model_id} - {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
@router.put("/{model_id}", response_model=ApiResponse)
|
||||
def update_model(
|
||||
model_id: uuid.UUID,
|
||||
@@ -433,53 +214,6 @@ def get_model_api_keys(
|
||||
raise
|
||||
|
||||
|
||||
@router.post("/provider/apikeys", response_model=ApiResponse)
|
||||
async def create_model_api_key_by_provider(
|
||||
api_key_data: model_schema.ModelApiKeyCreateByProvider,
|
||||
db: Session = Depends(get_db),
|
||||
current_user: User = Depends(get_current_user)
|
||||
):
|
||||
"""
|
||||
根据供应商为所有匹配的模型创建API Key
|
||||
"""
|
||||
api_logger.info(f"创建API Key请求: provider={api_key_data.provider}, 用户: {current_user.username}")
|
||||
|
||||
try:
|
||||
# 根据tenant_id和provider筛选model_config_id列表
|
||||
model_config_ids = api_key_data.model_config_ids
|
||||
if not model_config_ids:
|
||||
model_config_ids = ModelConfigRepository.get_model_config_ids_by_provider(
|
||||
db=db,
|
||||
tenant_id=current_user.tenant_id,
|
||||
provider=api_key_data.provider
|
||||
)
|
||||
|
||||
if not model_config_ids:
|
||||
raise BusinessException(f"未找到供应商 {api_key_data.provider} 的模型配置", BizCode.MODEL_NOT_FOUND)
|
||||
|
||||
# 构造schema并调用service
|
||||
create_data = model_schema.ModelApiKeyCreateByProvider(
|
||||
provider=api_key_data.provider,
|
||||
api_key=api_key_data.api_key,
|
||||
api_base=api_key_data.api_base,
|
||||
description=api_key_data.description,
|
||||
config=api_key_data.config,
|
||||
is_active=api_key_data.is_active,
|
||||
priority=api_key_data.priority,
|
||||
model_config_ids=model_config_ids
|
||||
)
|
||||
created_keys, failed_models = await ModelApiKeyService.create_api_key_by_provider(db=db, data=create_data)
|
||||
|
||||
api_logger.info(f"API Key创建成功: 关联{len(created_keys)}个模型")
|
||||
# result_list = [model_schema.ModelApiKey.model_validate(key) for key in created_keys]
|
||||
result = "API Key已存在" if len(created_keys) == 0 and len(failed_models) == 0 else \
|
||||
f"成功为 {len(created_keys)} 个模型创建API Key, 失败模型列表{failed_models}"
|
||||
return success(data=result, msg=f"成功为 {len(created_keys)} 个模型创建API Key")
|
||||
except Exception as e:
|
||||
api_logger.error(f"创建API Key失败: {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
@router.post("/{model_id}/apikeys", response_model=ApiResponse, status_code=status.HTTP_201_CREATED)
|
||||
async def create_model_api_key(
|
||||
model_id: uuid.UUID,
|
||||
@@ -494,12 +228,11 @@ async def create_model_api_key(
|
||||
|
||||
try:
|
||||
# 设置模型配置ID
|
||||
api_key_data.model_config_ids = [model_id]
|
||||
api_key_data.model_config_id = model_id
|
||||
|
||||
api_logger.debug(f"开始创建模型API Key: {api_key_data.model_name}")
|
||||
result_orm = await ModelApiKeyService.create_api_key(db=db, api_key_data=api_key_data)
|
||||
api_logger.info(f"模型API Key创建成功: {result_orm.model_name} (ID: {result_orm.id})")
|
||||
result = model_schema.ModelApiKey.model_validate(result_orm)
|
||||
result = await ModelApiKeyService.create_api_key(db=db, api_key_data=api_key_data)
|
||||
api_logger.info(f"模型API Key创建成功: {result.model_name} (ID: {result.id})")
|
||||
return success(data=result, msg="模型API Key创建成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"创建模型API Key失败: {api_key_data.model_name} - {str(e)}")
|
||||
@@ -601,3 +334,5 @@ async def validate_model_config(
|
||||
return success(data=model_schema.ModelValidateResponse(**result), msg="验证完成")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -74,7 +74,7 @@ def get_multi_agent_configs(
|
||||
"app_id": str(app_id),
|
||||
"default_model_config_id": None,
|
||||
"model_parameters": None,
|
||||
"orchestration_mode": "supervisor",
|
||||
"orchestration_mode": "conditional",
|
||||
"sub_agents": [],
|
||||
"routing_rules": [],
|
||||
"execution_config": {
|
||||
|
||||
@@ -1,9 +1,7 @@
|
||||
import uuid
|
||||
import json
|
||||
|
||||
from fastapi import APIRouter, Depends, Path
|
||||
from sqlalchemy.orm import Session
|
||||
from starlette.responses import StreamingResponse
|
||||
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import success
|
||||
@@ -72,12 +70,12 @@ def get_prompt_session(
|
||||
SessionMessage(role=role, content=content)
|
||||
for role, content in history
|
||||
]
|
||||
|
||||
|
||||
result = SessionHistoryResponse(
|
||||
session_id=session_id,
|
||||
messages=messages
|
||||
)
|
||||
|
||||
|
||||
return success(data=result)
|
||||
|
||||
|
||||
@@ -106,32 +104,35 @@ async def get_prompt_opt(
|
||||
ApiResponse: Contains the optimized prompt, description, and a list of variables.
|
||||
"""
|
||||
service = PromptOptimizerService(db)
|
||||
|
||||
async def event_generator():
|
||||
yield "event:start\ndata: {}\n\n"
|
||||
try:
|
||||
async for chunk in service.optimize_prompt(
|
||||
tenant_id=current_user.tenant_id,
|
||||
model_id=data.model_id,
|
||||
session_id=session_id,
|
||||
user_id=current_user.id,
|
||||
current_prompt=data.current_prompt,
|
||||
user_require=data.message
|
||||
):
|
||||
# chunk 是 prompt 的增量内容
|
||||
yield f"event:message\ndata: {json.dumps(chunk)}\n\n"
|
||||
except Exception as e:
|
||||
yield f"event:error\ndata: {json.dumps(
|
||||
{"error": str(e)}
|
||||
)}\n\n"
|
||||
yield "event:end\ndata: {}\n\n"
|
||||
|
||||
return StreamingResponse(
|
||||
event_generator(),
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive",
|
||||
"X-Accel-Buffering": "no"
|
||||
}
|
||||
service.create_message(
|
||||
tenant_id=current_user.tenant_id,
|
||||
session_id=session_id,
|
||||
user_id=current_user.id,
|
||||
role=RoleType.USER,
|
||||
content=data.message
|
||||
)
|
||||
opt_result = await service.optimize_prompt(
|
||||
tenant_id=current_user.tenant_id,
|
||||
model_id=data.model_id,
|
||||
session_id=session_id,
|
||||
user_id=current_user.id,
|
||||
current_prompt=data.current_prompt,
|
||||
user_require=data.message
|
||||
)
|
||||
service.create_message(
|
||||
tenant_id=current_user.tenant_id,
|
||||
session_id=session_id,
|
||||
user_id=current_user.id,
|
||||
role=RoleType.ASSISTANT,
|
||||
content=opt_result.desc
|
||||
)
|
||||
variables = service.parser_prompt_variables(opt_result.prompt)
|
||||
result = {
|
||||
"prompt": opt_result.prompt,
|
||||
"desc": opt_result.desc,
|
||||
"variables": variables
|
||||
}
|
||||
result_schema = OptimizePromptResponse.model_validate(result)
|
||||
return success(data=result_schema)
|
||||
|
||||
|
||||
|
||||
@@ -1,17 +1,15 @@
|
||||
import hashlib
|
||||
import json
|
||||
import uuid
|
||||
from typing import Annotated
|
||||
|
||||
from fastapi import APIRouter, Depends, Query, Request
|
||||
from fastapi.responses import StreamingResponse
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.logging_config import get_business_logger
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db, get_db_read
|
||||
from app.db import get_db
|
||||
from app.dependencies import get_share_user_id, ShareTokenData
|
||||
from app.repositories import knowledge_repository
|
||||
from app.repositories.workflow_repository import WorkflowConfigRepository
|
||||
from app.schemas import release_share_schema, conversation_schema
|
||||
from app.schemas.response_schema import PageData, PageMeta
|
||||
from app.services import workspace_service
|
||||
@@ -19,9 +17,6 @@ from app.services.auth_service import create_access_token
|
||||
from app.services.conversation_service import ConversationService
|
||||
from app.services.release_share_service import ReleaseShareService
|
||||
from app.services.shared_chat_service import SharedChatService
|
||||
from app.services.app_chat_service import AppChatService, get_app_chat_service
|
||||
from app.utils.app_config_utils import dict_to_multi_agent_config, workflow_config_4_app_release, \
|
||||
agent_config_4_app_release, multi_agent_config_4_app_release
|
||||
|
||||
router = APIRouter(prefix="/public/share", tags=["Public Share"])
|
||||
logger = get_business_logger()
|
||||
@@ -67,10 +62,10 @@ def get_or_generate_user_id(payload_user_id: str, request: Request) -> str:
|
||||
summary="获取访问 token"
|
||||
)
|
||||
def get_access_token(
|
||||
share_token: str,
|
||||
payload: release_share_schema.TokenRequest,
|
||||
request: Request,
|
||||
db: Session = Depends(get_db),
|
||||
share_token: str,
|
||||
payload: release_share_schema.TokenRequest,
|
||||
request: Request,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""获取访问 token
|
||||
|
||||
@@ -115,9 +110,9 @@ def get_access_token(
|
||||
response_model=None
|
||||
)
|
||||
def get_shared_release(
|
||||
password: str = Query(None, description="访问密码（如果需要）"),
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
password: str = Query(None, description="访问密码（如果需要）"),
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""获取公开分享的发布版本信息
|
||||
|
||||
@@ -139,9 +134,9 @@ def get_shared_release(
|
||||
summary="验证访问密码"
|
||||
)
|
||||
def verify_password(
|
||||
payload: release_share_schema.PasswordVerifyRequest,
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
payload: release_share_schema.PasswordVerifyRequest,
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""验证分享的访问密码
|
||||
|
||||
@@ -161,11 +156,11 @@ def verify_password(
|
||||
summary="获取嵌入代码"
|
||||
)
|
||||
def get_embed_code(
|
||||
width: str = Query("100%", description="iframe 宽度"),
|
||||
height: str = Query("600px", description="iframe 高度"),
|
||||
request: Request = None,
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
width: str = Query("100%", description="iframe 宽度"),
|
||||
height: str = Query("600px", description="iframe 高度"),
|
||||
request: Request = None,
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""获取嵌入代码
|
||||
|
||||
@@ -185,6 +180,7 @@ def get_embed_code(
|
||||
return success(data=embed_code)
|
||||
|
||||
|
||||
|
||||
# ---------- 会话管理接口 ----------
|
||||
|
||||
@router.get(
|
||||
@@ -192,11 +188,11 @@ def get_embed_code(
|
||||
summary="获取会话列表"
|
||||
)
|
||||
def list_conversations(
|
||||
password: str = Query(None, description="访问密码"),
|
||||
page: int = Query(1, ge=1),
|
||||
pagesize: int = Query(20, ge=1, le=100),
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
password: str = Query(None, description="访问密码"),
|
||||
page: int = Query(1, ge=1),
|
||||
pagesize: int = Query(20, ge=1, le=100),
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""获取分享应用的会话列表
|
||||
|
||||
@@ -210,9 +206,9 @@ def list_conversations(
|
||||
from app.repositories.end_user_repository import EndUserRepository
|
||||
end_user_repo = EndUserRepository(db)
|
||||
new_end_user = end_user_repo.get_or_create_end_user(
|
||||
app_id=share.app_id,
|
||||
other_id=other_id
|
||||
)
|
||||
app_id=share.app_id,
|
||||
other_id=other_id
|
||||
)
|
||||
logger.debug(new_end_user.id)
|
||||
service = SharedChatService(db)
|
||||
conversations, total = service.list_conversations(
|
||||
@@ -234,10 +230,10 @@ def list_conversations(
|
||||
summary="获取会话详情（含消息）"
|
||||
)
|
||||
def get_conversation(
|
||||
conversation_id: uuid.UUID,
|
||||
password: str = Query(None, description="访问密码"),
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
conversation_id: uuid.UUID,
|
||||
password: str = Query(None, description="访问密码"),
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""获取会话详情和消息历史"""
|
||||
chat_service = SharedChatService(db)
|
||||
@@ -267,10 +263,9 @@ def get_conversation(
|
||||
summary="发送消息（支持流式和非流式）"
|
||||
)
|
||||
async def chat(
|
||||
payload: conversation_schema.ChatRequest,
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db),
|
||||
app_chat_service: Annotated[AppChatService, Depends(get_app_chat_service)] = None,
|
||||
payload: conversation_schema.ChatRequest,
|
||||
share_data: ShareTokenData = Depends(get_share_user_id),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""发送消息并获取回复
|
||||
|
||||
@@ -312,17 +307,14 @@ async def chat(
|
||||
other_id=other_id,
|
||||
original_user_id=user_id # Save original user_id to other_id
|
||||
)
|
||||
end_user_id = str(new_end_user.id)
|
||||
|
||||
appid = share.app_id
|
||||
|
||||
appid=share.app_id
|
||||
"""获取存储类型和工作空间的ID"""
|
||||
|
||||
# 直接通过 SQLAlchemy 查询 app（仅查询未删除的应用）
|
||||
# 直接通过 SQLAlchemy 查询 app
|
||||
from app.models.app_model import App
|
||||
app = db.query(App).filter(
|
||||
App.id == appid,
|
||||
App.is_active.is_(True)
|
||||
).first()
|
||||
app = db.query(App).filter(App.id == appid).first()
|
||||
if not app:
|
||||
raise BusinessException("应用不存在", BizCode.APP_NOT_FOUND)
|
||||
|
||||
@@ -369,9 +361,6 @@ async def chat(
|
||||
config = release.config or {}
|
||||
if not config.get("sub_agents"):
|
||||
raise BusinessException("多 Agent 应用未配置子 Agent", BizCode.AGENT_CONFIG_MISSING)
|
||||
elif app_type == AppType.WORKFLOW:
|
||||
# Multi-Agent 类型：验证多 Agent 配置
|
||||
pass
|
||||
else:
|
||||
raise BusinessException(f"不支持的应用类型: {app_type}", BizCode.APP_TYPE_NOT_SUPPORTED)
|
||||
|
||||
@@ -400,45 +389,19 @@ async def chat(
|
||||
|
||||
if app_type == AppType.AGENT:
|
||||
# 流式返回
|
||||
agent_config = agent_config_4_app_release(release)
|
||||
|
||||
if payload.stream:
|
||||
# async def event_generator():
|
||||
# async for event in service.chat_stream(
|
||||
# share_token=share_token,
|
||||
# message=payload.message,
|
||||
# conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
# user_id=str(new_end_user.id), # 转换为字符串
|
||||
# variables=payload.variables,
|
||||
# password=password,
|
||||
# web_search=payload.web_search,
|
||||
# memory=payload.memory,
|
||||
# storage_type=storage_type,
|
||||
# user_rag_memory_id=user_rag_memory_id
|
||||
# ):
|
||||
# yield event
|
||||
|
||||
# return StreamingResponse(
|
||||
# event_generator(),
|
||||
# media_type="text/event-stream",
|
||||
# headers={
|
||||
# "Cache-Control": "no-cache",
|
||||
# "Connection": "keep-alive",
|
||||
# "X-Accel-Buffering": "no"
|
||||
# }
|
||||
# )
|
||||
async def event_generator():
|
||||
async for event in app_chat_service.agnet_chat_stream(
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=str(new_end_user.id), # 转换为字符串
|
||||
variables=payload.variables,
|
||||
web_search=payload.web_search,
|
||||
config=agent_config,
|
||||
memory=payload.memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
workspace_id=workspace_id
|
||||
async for event in service.chat_stream(
|
||||
share_token=share_token,
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=str(new_end_user.id), # 转换为字符串
|
||||
variables=payload.variables,
|
||||
password=password,
|
||||
web_search=payload.web_search,
|
||||
memory=payload.memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
):
|
||||
yield event
|
||||
|
||||
@@ -451,47 +414,34 @@ async def chat(
|
||||
"X-Accel-Buffering": "no"
|
||||
}
|
||||
)
|
||||
|
||||
# 非流式返回
|
||||
# result = await service.chat(
|
||||
# share_token=share_token,
|
||||
# message=payload.message,
|
||||
# conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
# user_id=str(new_end_user.id), # 转换为字符串
|
||||
# variables=payload.variables,
|
||||
# password=password,
|
||||
# web_search=payload.web_search,
|
||||
# memory=payload.memory,
|
||||
# storage_type=storage_type,
|
||||
# user_rag_memory_id=user_rag_memory_id
|
||||
# )
|
||||
# return success(data=conversation_schema.ChatResponse(**result))
|
||||
result = await app_chat_service.agnet_chat(
|
||||
result = await service.chat(
|
||||
share_token=share_token,
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=str(new_end_user.id), # 转换为字符串
|
||||
variables=payload.variables,
|
||||
config=agent_config,
|
||||
password=password,
|
||||
web_search=payload.web_search,
|
||||
memory=payload.memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
workspace_id=workspace_id
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
)
|
||||
return success(data=conversation_schema.ChatResponse(**result).model_dump(mode="json"))
|
||||
return success(data=conversation_schema.ChatResponse(**result))
|
||||
elif app_type == AppType.MULTI_AGENT:
|
||||
# config = workflow_config_4_app_release(release)
|
||||
config = multi_agent_config_4_app_release(release)
|
||||
# 多 Agent 流式返回
|
||||
if payload.stream:
|
||||
async def event_generator():
|
||||
async for event in app_chat_service.multi_agent_chat_stream(
|
||||
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=str(new_end_user.id), # 转换为字符串
|
||||
variables=payload.variables,
|
||||
config=config,
|
||||
web_search=payload.web_search,
|
||||
memory=payload.memory,
|
||||
async for event in service.multi_agent_chat_stream(
|
||||
share_token=share_token,
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=str(new_end_user.id), # 转换为字符串
|
||||
variables=payload.variables,
|
||||
password=password,
|
||||
web_search=payload.web_search,
|
||||
memory=payload.memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
):
|
||||
@@ -508,132 +458,22 @@ async def chat(
|
||||
)
|
||||
|
||||
# 多 Agent 非流式返回
|
||||
result = await app_chat_service.multi_agent_chat(
|
||||
|
||||
result = await service.multi_agent_chat(
|
||||
share_token=share_token,
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=end_user_id, # 转换为字符串
|
||||
user_id=str(new_end_user.id), # 转换为字符串
|
||||
variables=payload.variables,
|
||||
config=config,
|
||||
password=password,
|
||||
web_search=payload.web_search,
|
||||
memory=payload.memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
)
|
||||
|
||||
return success(data=conversation_schema.ChatResponse(**result).model_dump(mode="json"))
|
||||
# 多 Agent 流式返回
|
||||
# if payload.stream:
|
||||
# async def event_generator():
|
||||
# async for event in service.multi_agent_chat_stream(
|
||||
# share_token=share_token,
|
||||
# message=payload.message,
|
||||
# conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
# user_id=str(new_end_user.id), # 转换为字符串
|
||||
# variables=payload.variables,
|
||||
# password=password,
|
||||
# web_search=payload.web_search,
|
||||
# memory=payload.memory,
|
||||
# storage_type=storage_type,
|
||||
# user_rag_memory_id=user_rag_memory_id
|
||||
# ):
|
||||
# yield event
|
||||
|
||||
# return StreamingResponse(
|
||||
# event_generator(),
|
||||
# media_type="text/event-stream",
|
||||
# headers={
|
||||
# "Cache-Control": "no-cache",
|
||||
# "Connection": "keep-alive",
|
||||
# "X-Accel-Buffering": "no"
|
||||
# }
|
||||
# )
|
||||
|
||||
# # 多 Agent 非流式返回
|
||||
# result = await service.multi_agent_chat(
|
||||
# share_token=share_token,
|
||||
# message=payload.message,
|
||||
# conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
# user_id=str(new_end_user.id), # 转换为字符串
|
||||
# variables=payload.variables,
|
||||
# password=password,
|
||||
# web_search=payload.web_search,
|
||||
# memory=payload.memory,
|
||||
# storage_type=storage_type,
|
||||
# user_rag_memory_id=user_rag_memory_id
|
||||
# )
|
||||
|
||||
# return success(data=conversation_schema.ChatResponse(**result))
|
||||
elif app_type == AppType.WORKFLOW:
|
||||
config = workflow_config_4_app_release(release)
|
||||
if not config.id:
|
||||
with get_db_read() as db:
|
||||
source_config = WorkflowConfigRepository(db).get_by_app_id(release.app_id)
|
||||
config.id = source_config.id
|
||||
config.id = uuid.UUID(config.id)
|
||||
if payload.stream:
|
||||
async def event_generator():
|
||||
async for event in app_chat_service.workflow_chat_stream(
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=end_user_id, # 转换为字符串
|
||||
variables=payload.variables,
|
||||
config=config,
|
||||
web_search=payload.web_search,
|
||||
memory=payload.memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
app_id=release.app_id,
|
||||
workspace_id=workspace_id,
|
||||
release_id=release.id
|
||||
):
|
||||
event_type = event.get("event", "message")
|
||||
event_data = event.get("data", {})
|
||||
|
||||
# 转换为标准 SSE 格式（字符串）
|
||||
sse_message = f"event: {event_type}\ndata: {json.dumps(event_data, default=str, ensure_ascii=False)}\n\n"
|
||||
yield sse_message
|
||||
|
||||
return StreamingResponse(
|
||||
event_generator(),
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive",
|
||||
"X-Accel-Buffering": "no"
|
||||
}
|
||||
)
|
||||
|
||||
# 多 Agent 非流式返回
|
||||
result = await app_chat_service.workflow_chat(
|
||||
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=end_user_id, # 转换为字符串
|
||||
variables=payload.variables,
|
||||
config=config,
|
||||
web_search=payload.web_search,
|
||||
memory=payload.memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
app_id=release.app_id,
|
||||
workspace_id=workspace_id,
|
||||
release_id=release.id
|
||||
)
|
||||
logger.debug(
|
||||
"工作流试运行返回结果",
|
||||
extra={
|
||||
"result_type": str(type(result)),
|
||||
"has_response": "response" in result if isinstance(result, dict) else False
|
||||
}
|
||||
)
|
||||
return success(
|
||||
data=result,
|
||||
msg="工作流任务执行成功"
|
||||
)
|
||||
# return success(data=conversation_schema.ChatResponse(**result).model_dump(mode="json"))
|
||||
|
||||
return success(data=conversation_schema.ChatResponse(**result))
|
||||
else:
|
||||
from app.core.exceptions import BusinessException
|
||||
from app.core.error_codes import BizCode
|
||||
raise BusinessException(f"不支持的应用类型: {app_type}", BizCode.APP_TYPE_NOT_SUPPORTED)
|
||||
pass
|
||||
|
||||
@@ -4,17 +4,14 @@
|
||||
认证方式: API Key
|
||||
"""
|
||||
from fastapi import APIRouter
|
||||
from . import app_api_controller, rag_api_knowledge_controller, rag_api_document_controller, rag_api_file_controller, rag_api_chunk_controller, memory_api_controller
|
||||
from . import app_api_controller, rag_api_controller, memory_api_controller
|
||||
|
||||
# 创建 V1 API 路由器
|
||||
service_router = APIRouter()
|
||||
|
||||
# 注册子路由
|
||||
service_router.include_router(app_api_controller.router)
|
||||
service_router.include_router(rag_api_knowledge_controller.router)
|
||||
service_router.include_router(rag_api_document_controller.router)
|
||||
service_router.include_router(rag_api_file_controller.router)
|
||||
service_router.include_router(rag_api_chunk_controller.router)
|
||||
service_router.include_router(rag_api_controller.router)
|
||||
service_router.include_router(memory_api_controller.router)
|
||||
|
||||
__all__ = ["service_router"]
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
"""App 服务接口 - 基于 API Key 认证"""
|
||||
import json
|
||||
from typing import Annotated
|
||||
|
||||
from fastapi import APIRouter, Depends, Request, Body
|
||||
@@ -22,7 +21,7 @@ from app.schemas.api_key_schema import ApiKeyAuth
|
||||
from app.services import workspace_service
|
||||
from app.services.app_chat_service import AppChatService, get_app_chat_service
|
||||
from app.services.conversation_service import ConversationService, get_conversation_service
|
||||
from app.utils.app_config_utils import dict_to_multi_agent_config, workflow_config_4_app_release, agent_config_4_app_release, multi_agent_config_4_app_release
|
||||
from app.utils.app_config_utils import dict_to_multi_agent_config, dict_to_workflow_config, agent_config_4_app_release
|
||||
from app.services.app_service import get_app_service, AppService
|
||||
|
||||
router = APIRouter(prefix="/app", tags=["V1 - App API"])
|
||||
@@ -138,10 +137,10 @@ async def chat(
|
||||
|
||||
if app_type == AppType.AGENT:
|
||||
|
||||
# print("="*50)
|
||||
# print(app.current_release.default_model_config_id)
|
||||
print("="*50)
|
||||
print(app.current_release.default_model_config_id)
|
||||
agent_config = agent_config_4_app_release(app.current_release)
|
||||
# print(agent_config.default_model_config_id)
|
||||
print(agent_config.default_model_config_id)
|
||||
# 流式返回
|
||||
if payload.stream:
|
||||
async def event_generator():
|
||||
@@ -154,8 +153,7 @@ async def chat(
|
||||
config=agent_config,
|
||||
memory=memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
workspace_id=workspace_id
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
):
|
||||
yield event
|
||||
|
||||
@@ -179,13 +177,12 @@ async def chat(
|
||||
web_search=web_search,
|
||||
memory=memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
workspace_id=workspace_id
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
)
|
||||
return success(data=conversation_schema.ChatResponse(**result).model_dump(mode="json"))
|
||||
elif app_type == AppType.MULTI_AGENT:
|
||||
# 多 Agent 流式返回
|
||||
config = multi_agent_config_4_app_release(app.current_release)
|
||||
config = dict_to_multi_agent_config(app.current_release.config,app.id)
|
||||
if payload.stream:
|
||||
async def event_generator():
|
||||
async for event in app_chat_service.multi_agent_chat_stream(
|
||||
@@ -197,8 +194,8 @@ async def chat(
|
||||
config=config,
|
||||
web_search=web_search,
|
||||
memory=memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
):
|
||||
yield event
|
||||
|
||||
@@ -214,6 +211,7 @@ async def chat(
|
||||
|
||||
# 多 Agent 非流式返回
|
||||
result = await app_chat_service.multi_agent_chat(
|
||||
|
||||
message=payload.message,
|
||||
conversation_id=conversation.id, # 使用已创建的会话 ID
|
||||
user_id=end_user_id, # 转换为字符串
|
||||
@@ -228,7 +226,7 @@ async def chat(
|
||||
return success(data=conversation_schema.ChatResponse(**result).model_dump(mode="json"))
|
||||
elif app_type == AppType.WORKFLOW:
|
||||
# 多 Agent 流式返回
|
||||
config = workflow_config_4_app_release(app.current_release)
|
||||
config = dict_to_workflow_config(app.current_release.config,app.id)
|
||||
if payload.stream:
|
||||
async def event_generator():
|
||||
async for event in app_chat_service.workflow_chat_stream(
|
||||
@@ -240,18 +238,10 @@ async def chat(
|
||||
config=config,
|
||||
web_search=web_search,
|
||||
memory=memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
app_id=app.id,
|
||||
workspace_id=workspace_id,
|
||||
release_id=app.current_release.id,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
):
|
||||
event_type = event.get("event", "message")
|
||||
event_data = event.get("data", {})
|
||||
|
||||
# 转换为标准 SSE 格式（字符串）
|
||||
sse_message = f"event: {event_type}\ndata: {json.dumps(event_data)}\n\n"
|
||||
yield sse_message
|
||||
yield event
|
||||
|
||||
return StreamingResponse(
|
||||
event_generator(),
|
||||
@@ -263,7 +253,7 @@ async def chat(
|
||||
}
|
||||
)
|
||||
|
||||
# 多 Agent 非流式返回
|
||||
# 非流式返回
|
||||
result = await app_chat_service.workflow_chat(
|
||||
|
||||
message=payload.message,
|
||||
@@ -274,24 +264,12 @@ async def chat(
|
||||
web_search=web_search,
|
||||
memory=memory,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
app_id=app.id,
|
||||
workspace_id=workspace_id,
|
||||
release_id=app.current_release.id
|
||||
)
|
||||
logger.debug(
|
||||
"工作流试运行返回结果",
|
||||
extra={
|
||||
"result_type": str(type(result)),
|
||||
"has_response": "response" in result if isinstance(result, dict) else False
|
||||
}
|
||||
)
|
||||
return success(
|
||||
data=result,
|
||||
msg="工作流任务执行成功"
|
||||
user_rag_memory_id=user_rag_memory_id
|
||||
)
|
||||
|
||||
return success(data=conversation_schema.ChatResponse(**result).model_dump(mode="json"))
|
||||
else:
|
||||
from app.core.exceptions import BusinessException
|
||||
from app.core.error_codes import BizCode
|
||||
raise BusinessException(f"不支持的应用类型: {app_type}", BizCode.APP_TYPE_NOT_SUPPORTED)
|
||||
|
||||
pass
|
||||
|
||||
@@ -39,7 +39,7 @@ async def write_memory_api_service(
|
||||
|
||||
Stores memory content for the specified end user using the Memory API Service.
|
||||
"""
|
||||
logger.info(f"Memory write request - end_user_id: {payload.end_user_id}, tenant_id: {api_key_auth.tenant_id}")
|
||||
logger.info(f"Memory write request - end_user_id: {payload.end_user_id}")
|
||||
|
||||
memory_api_service = MemoryAPIService(db)
|
||||
|
||||
|
||||
@@ -1,221 +0,0 @@
|
||||
"""RAG 服务接口 - 基于 API Key 认证"""
|
||||
|
||||
from typing import Any, Optional, Union
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Body, Depends, Request, status, Query
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.controllers import chunk_controller
|
||||
from app.core.api_key_auth import require_api_key
|
||||
from app.core.logging_config import get_business_logger
|
||||
from app.core.rag.models.chunk import QAChunk
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.schemas import chunk_schema
|
||||
from app.schemas.api_key_schema import ApiKeyAuth
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services import api_key_service
|
||||
|
||||
|
||||
router = APIRouter(prefix="/chunks", tags=["V1 - RAG API"])
|
||||
api_logger = get_business_logger()
|
||||
|
||||
|
||||
@router.get("/{kb_id}/{document_id}/previewchunks", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_preview_chunks(
|
||||
kb_id: uuid.UUID,
|
||||
document_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
page: int = Query(1, gt=0), # Default: 1, which must be greater than 0
|
||||
pagesize: int = Query(20, gt=0, le=100), # Default: 20 items per page, maximum: 100 items
|
||||
keywords: Optional[str] = Query(None, description="The keywords used to match chunk content")
|
||||
):
|
||||
"""
|
||||
Paged query document block preview list
|
||||
- Support filtering by document_id
|
||||
- Support keyword search for segmented content
|
||||
- Return paging metadata + file list
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await chunk_controller.get_preview_chunks(kb_id=kb_id,
|
||||
document_id=document_id,
|
||||
page=page,
|
||||
pagesize=pagesize,
|
||||
keywords=keywords,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.get("/{kb_id}/{document_id}/chunks", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_chunks(
|
||||
kb_id: uuid.UUID,
|
||||
document_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
page: int = Query(1, gt=0), # Default: 1, which must be greater than 0
|
||||
pagesize: int = Query(20, gt=0, le=100), # Default: 20 items per page, maximum: 100 items
|
||||
keywords: Optional[str] = Query(None, description="The keywords used to match chunk content")
|
||||
):
|
||||
"""
|
||||
Paged query document chunk list
|
||||
- Support filtering by document_id
|
||||
- Support keyword search for segmented content
|
||||
- Return paging metadata + file list
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await chunk_controller.get_chunks(kb_id=kb_id,
|
||||
document_id=document_id,
|
||||
page=page,
|
||||
pagesize=pagesize,
|
||||
keywords=keywords,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.post("/{kb_id}/{document_id}/chunk", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def create_chunk(
|
||||
kb_id: uuid.UUID,
|
||||
document_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
content: Union[str, QAChunk] = Body(..., description="Content can be either a string or a QAChunk object"),
|
||||
):
|
||||
"""
|
||||
create chunk
|
||||
"""
|
||||
body = await request.json()
|
||||
create_data = chunk_schema.ChunkCreate(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await chunk_controller.create_chunk(kb_id=kb_id,
|
||||
document_id=document_id,
|
||||
create_data=create_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.get("/{kb_id}/{document_id}/{doc_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_chunk(
|
||||
kb_id: uuid.UUID,
|
||||
document_id: uuid.UUID,
|
||||
doc_id: str,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Retrieve document chunk information based on doc_id
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await chunk_controller.get_chunk(kb_id=kb_id,
|
||||
document_id=document_id,
|
||||
doc_id=doc_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.put("/{kb_id}/{document_id}/{doc_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def update_chunk(
|
||||
kb_id: uuid.UUID,
|
||||
document_id: uuid.UUID,
|
||||
doc_id: str,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
content: Union[str, QAChunk] = Body(..., description="Content can be either a string or a QAChunk object"),
|
||||
):
|
||||
"""
|
||||
Update document chunk content
|
||||
"""
|
||||
body = await request.json()
|
||||
update_data = chunk_schema.ChunkUpdate(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await chunk_controller.update_chunk(kb_id=kb_id,
|
||||
document_id=document_id,
|
||||
doc_id=doc_id,
|
||||
update_data=update_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.delete("/{kb_id}/{document_id}/{doc_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def delete_chunk(
|
||||
kb_id: uuid.UUID,
|
||||
document_id: uuid.UUID,
|
||||
doc_id: str,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
delete document chunk
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await chunk_controller.delete_chunk(kb_id=kb_id,
|
||||
document_id=document_id,
|
||||
doc_id=doc_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.get("/retrieve_type", response_model=ApiResponse)
|
||||
def get_retrieve_types():
|
||||
return success(msg="Successfully obtained the retrieval type", data=list(chunk_schema.RetrieveType))
|
||||
|
||||
|
||||
@router.post("/retrieval", response_model=Any, status_code=status.HTTP_200_OK)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def retrieve_chunks(
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
query: str = Body(..., description="question"),
|
||||
):
|
||||
"""
|
||||
retrieve chunk
|
||||
"""
|
||||
body = await request.json()
|
||||
retrieve_data = chunk_schema.ChunkRetrieve(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await chunk_controller.retrieve_chunks(retrieve_data=retrieve_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
16
api/app/controllers/service/rag_api_controller.py
Normal file
16
api/app/controllers/service/rag_api_controller.py
Normal file
@@ -0,0 +1,16 @@
|
||||
"""RAG 服务接口 - 基于 API Key 认证"""
|
||||
from fastapi import APIRouter, Depends
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.db import get_db
|
||||
from app.core.response_utils import success
|
||||
from app.core.logging_config import get_business_logger
|
||||
|
||||
router = APIRouter(prefix="/knowledge", tags=["V1 - RAG API"])
|
||||
logger = get_business_logger()
|
||||
|
||||
|
||||
@router.get("")
|
||||
async def list_knowledge():
|
||||
"""列出可访问的知识库（占位）"""
|
||||
return success(data=[], msg="RAG API - Coming Soon")
|
||||
@@ -1,172 +0,0 @@
|
||||
"""RAG 服务接口 - 基于 API Key 认证"""
|
||||
|
||||
from typing import Optional
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Body, Depends, Request, Query
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.controllers import document_controller
|
||||
from app.core.api_key_auth import require_api_key
|
||||
from app.core.logging_config import get_business_logger
|
||||
from app.db import get_db
|
||||
from app.schemas import document_schema
|
||||
from app.schemas.api_key_schema import ApiKeyAuth
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services import api_key_service
|
||||
|
||||
|
||||
router = APIRouter(prefix="/documents", tags=["V1 - RAG API"])
|
||||
api_logger = get_business_logger()
|
||||
|
||||
|
||||
@router.get("/{kb_id}/documents", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_documents(
|
||||
kb_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
parent_id: Optional[uuid.UUID] = Query(None, description="parent folder id when type is Folder"),
|
||||
page: int = Query(1, gt=0), # Default: 1, which must be greater than 0
|
||||
pagesize: int = Query(20, gt=0, le=100), # Default: 20 items per page, maximum: 100 items
|
||||
orderby: Optional[str] = Query(None, description="Sort fields, such as: created_at,updated_at"),
|
||||
desc: Optional[bool] = Query(False, description="Is it descending order"),
|
||||
keywords: Optional[str] = Query(None, description="Search keywords (file name)"),
|
||||
document_ids: Optional[str] = Query(None, description="document ids, separated by commas")
|
||||
):
|
||||
"""
|
||||
Paged query document list
|
||||
- Support filtering by kb_id and parent_id
|
||||
- Support keyword search for file names
|
||||
- Support dynamic sorting
|
||||
- Return paging metadata + file list
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await document_controller.get_documents(kb_id=kb_id,
|
||||
parent_id=parent_id,
|
||||
page=page,
|
||||
pagesize=pagesize,
|
||||
orderby=orderby,
|
||||
desc=desc,
|
||||
keywords=keywords,
|
||||
document_ids=document_ids,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.post("/document", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def create_document(
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
kb_id: uuid.UUID = Body(..., description="kb id"),
|
||||
file_name: str = Body(..., description="file name"),
|
||||
):
|
||||
"""
|
||||
create document
|
||||
"""
|
||||
body = await request.json()
|
||||
create_data = document_schema.DocumentCreate(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await document_controller.create_document(create_data=create_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.get("/{document_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_document(
|
||||
document_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Retrieve document information based on document_id
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await document_controller.get_document(document_id=document_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.put("/{document_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def update_document(
|
||||
document_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
file_name: str = Body(None, description="file name (optional)"),
|
||||
):
|
||||
"""
|
||||
Update document information
|
||||
"""
|
||||
body = await request.json()
|
||||
update_data = document_schema.DocumentUpdate(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await document_controller.update_document(document_id=document_id,
|
||||
update_data=update_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.delete("/{document_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def delete_document(
|
||||
document_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Delete document
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await document_controller.delete_document(document_id=document_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.post("/{document_id}/chunks", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def parse_documents(
|
||||
document_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
parse document
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await document_controller.parse_documents(document_id=document_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
@@ -1,198 +0,0 @@
|
||||
"""RAG 服务接口 - 基于 API Key 认证"""
|
||||
|
||||
from typing import Any, Optional
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Body, Depends, Request, Query, File, UploadFile
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.controllers import file_controller
|
||||
from app.core.api_key_auth import require_api_key
|
||||
from app.core.logging_config import get_business_logger
|
||||
from app.db import get_db
|
||||
from app.schemas import file_schema
|
||||
from app.schemas.api_key_schema import ApiKeyAuth
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services import api_key_service
|
||||
|
||||
|
||||
router = APIRouter(prefix="/files", tags=["V1 - RAG API"])
|
||||
api_logger = get_business_logger()
|
||||
|
||||
|
||||
@router.get("/{kb_id}/{parent_id}/files", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_files(
|
||||
kb_id: uuid.UUID,
|
||||
parent_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
page: int = Query(1, gt=0), # Default: 1, which must be greater than 0
|
||||
pagesize: int = Query(20, gt=0, le=100), # Default: 20 items per page, maximum: 100 items
|
||||
orderby: Optional[str] = Query(None, description="Sort fields, such as: created_at"),
|
||||
desc: Optional[bool] = Query(False, description="Is it descending order"),
|
||||
keywords: Optional[str] = Query(None, description="Search keywords (file name)"),
|
||||
):
|
||||
"""
|
||||
Paged query file list
|
||||
- Support filtering by kb_id and parent_id
|
||||
- Support keyword search for file names
|
||||
- Support dynamic sorting
|
||||
- Return paging metadata + file list
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id=api_key_auth.workspace_id
|
||||
|
||||
return await file_controller.get_files(kb_id=kb_id,
|
||||
parent_id=parent_id,
|
||||
page=page,
|
||||
pagesize=pagesize,
|
||||
orderby=orderby,
|
||||
desc=desc,
|
||||
keywords=keywords,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.post("/folder", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def create_folder(
|
||||
kb_id: uuid.UUID,
|
||||
parent_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
folder_name: str = '/'
|
||||
):
|
||||
"""
|
||||
Create a new folder
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await file_controller.create_folder(kb_id=kb_id,
|
||||
parent_id=parent_id,
|
||||
folder_name=folder_name,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.post("/file", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def upload_file(
|
||||
kb_id: uuid.UUID,
|
||||
parent_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
file: UploadFile = File(...),
|
||||
):
|
||||
"""
|
||||
upload file
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await file_controller.upload_file(kb_id=kb_id,
|
||||
parent_id=parent_id,
|
||||
file=file,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.post("/customtext", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def custom_text(
|
||||
kb_id: uuid.UUID,
|
||||
parent_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
title: str = Body(..., description="title"),
|
||||
content: str = Body(..., description="content"),
|
||||
):
|
||||
"""
|
||||
custom text
|
||||
"""
|
||||
body = await request.json()
|
||||
create_data = file_schema.CustomTextFileCreate(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await file_controller.custom_text(kb_id=kb_id,
|
||||
parent_id=parent_id,
|
||||
create_data=create_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.get("/{file_id}", response_model=Any)
|
||||
async def get_file(
|
||||
file_id: uuid.UUID,
|
||||
db: Session = Depends(get_db)
|
||||
) -> Any:
|
||||
"""
|
||||
Download the file based on the file_id
|
||||
- Query file information from the database
|
||||
- Construct the file path and check if it exists
|
||||
- Return a FileResponse to download the file
|
||||
"""
|
||||
return await file_controller.get_file(file_id=file_id,
|
||||
db=db)
|
||||
|
||||
|
||||
@router.put("/{file_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def update_file(
|
||||
file_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
file_name: str = Body(None, description="file name (optional)"),
|
||||
):
|
||||
"""
|
||||
Update file information (such as file name)
|
||||
- Only specified fields such as file_name are allowed to be modified
|
||||
"""
|
||||
body = await request.json()
|
||||
update_data = file_schema.FileUpdate(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await file_controller.update_file(file_id=file_id,
|
||||
update_data=update_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.delete("/{file_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def delete_file(
|
||||
file_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Delete a file or folder
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await file_controller.delete_file(file_id=file_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
@@ -1,248 +0,0 @@
|
||||
"""RAG 服务接口 - 基于 API Key 认证"""
|
||||
|
||||
from typing import Optional, Dict
|
||||
import uuid
|
||||
|
||||
from fastapi import APIRouter, Body, Depends, Request, Query
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.controllers import knowledge_controller
|
||||
from app.core.api_key_auth import require_api_key
|
||||
from app.core.logging_config import get_business_logger
|
||||
from app.core.response_utils import success
|
||||
from app.db import get_db
|
||||
from app.models import knowledge_model
|
||||
from app.schemas import knowledge_schema
|
||||
from app.schemas.api_key_schema import ApiKeyAuth
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.services import api_key_service
|
||||
|
||||
|
||||
router = APIRouter(prefix="/knowledges", tags=["V1 - RAG API"])
|
||||
api_logger = get_business_logger()
|
||||
|
||||
|
||||
@router.get("/knowledgetype", response_model=ApiResponse)
|
||||
def get_knowledge_types():
|
||||
return success(msg="Successfully obtained the knowledge type", data=list(knowledge_model.KnowledgeType))
|
||||
|
||||
|
||||
@router.get("/permissiontype", response_model=ApiResponse)
|
||||
def get_permission_types():
|
||||
return success(msg="Successfully obtained the knowledge permission type", data=list(knowledge_model.PermissionType))
|
||||
|
||||
|
||||
@router.get("/parsertype", response_model=ApiResponse)
|
||||
def get_parser_types():
|
||||
return success(msg="Successfully obtained the knowledge parser type", data=list(knowledge_model.ParserType))
|
||||
|
||||
|
||||
@router.get("/knowledge_graph_entity_types", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_knowledge_graph_entity_types(
|
||||
llm_id: uuid.UUID,
|
||||
scenario: str,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
get knowledge graph entity types based on llm_id
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.get_knowledge_graph_entity_types(llm_id=llm_id,
|
||||
scenario=scenario,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.get("/knowledges", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_knowledges(
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
parent_id: Optional[uuid.UUID] = Query(None, description="parent folder id"),
|
||||
page: int = Query(1, gt=0), # Default: 1, which must be greater than 0
|
||||
pagesize: int = Query(20, gt=0, le=100), # Default: 20 items per page, maximum: 100 items
|
||||
orderby: Optional[str] = Query(None, description="Sort fields, such as: created_at,updated_at"),
|
||||
desc: Optional[bool] = Query(False, description="Is it descending order"),
|
||||
keywords: Optional[str] = Query(None, description="Search keywords (knowledge base name)"),
|
||||
kb_ids: Optional[str] = Query(None, description="Knowledge base ids, separated by commas")
|
||||
):
|
||||
"""
|
||||
Query the knowledge base list in pages
|
||||
- Support filtering by parent_id
|
||||
- Support keyword search for knowledge base names
|
||||
- Support dynamic sorting
|
||||
- Return paging metadata + file list
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.get_knowledges(parent_id=parent_id,
|
||||
page=page,
|
||||
pagesize=pagesize,
|
||||
orderby=orderby,
|
||||
desc=desc,
|
||||
keywords=keywords,
|
||||
kb_ids=kb_ids,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.post("/knowledge", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def create_knowledge(
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
name: str = Body(..., description="KB name"),
|
||||
):
|
||||
"""
|
||||
create knowledge
|
||||
"""
|
||||
body = await request.json()
|
||||
create_data = knowledge_schema.KnowledgeCreate(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.create_knowledge(create_data=create_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.get("/{knowledge_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_knowledge(
|
||||
knowledge_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Retrieve knowledge base information based on knowledge_id
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.get_knowledge(knowledge_id=knowledge_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.put("/{knowledge_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def update_knowledge(
|
||||
knowledge_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
name: str = Body(None, description="KB name (optional)"),
|
||||
):
|
||||
body = await request.json()
|
||||
update_data = knowledge_schema.KnowledgeUpdate(**body)
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.update_knowledge(knowledge_id=knowledge_id,
|
||||
update_data=update_data,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.delete("/{knowledge_id}", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def delete_knowledge(
|
||||
knowledge_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Soft-delete knowledge base
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.delete_knowledge(knowledge_id=knowledge_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.get("/{knowledge_id}/knowledge_graph", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def get_knowledge_graph(
|
||||
knowledge_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
Retrieve knowledge_graph base information based on knowledge_id
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.get_knowledge_graph(knowledge_id=knowledge_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.delete("/{knowledge_id}/knowledge_graph", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def delete_knowledge_graph(
|
||||
knowledge_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
delete knowledge graph
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.delete_knowledge_graph(knowledge_id=knowledge_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
|
||||
@router.post("/{knowledge_id}/knowledge_graph", response_model=ApiResponse)
|
||||
@require_api_key(scopes=["rag"])
|
||||
async def rebuild_knowledge_graph(
|
||||
knowledge_id: uuid.UUID,
|
||||
request: Request,
|
||||
api_key_auth: ApiKeyAuth = None,
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
"""
|
||||
rebuild knowledge graph
|
||||
"""
|
||||
# 0. Obtain the creator of the api key
|
||||
api_key = api_key_service.ApiKeyService.get_api_key(db, api_key_auth.api_key_id, api_key_auth.workspace_id)
|
||||
current_user = api_key.creator
|
||||
current_user.current_workspace_id = api_key_auth.workspace_id
|
||||
|
||||
return await knowledge_controller.rebuild_knowledge_graph(knowledge_id=knowledge_id,
|
||||
db=db,
|
||||
current_user=current_user)
|
||||
|
||||
@@ -1,22 +1,23 @@
|
||||
from fastapi import APIRouter, Depends, status, HTTPException, Body, Path
|
||||
from fastapi.responses import StreamingResponse
|
||||
from fastapi import APIRouter, Depends, status, Query, HTTPException
|
||||
from langchain_core.messages import HumanMessage, SystemMessage
|
||||
from langchain_core.prompts import ChatPromptTemplate
|
||||
from sqlalchemy.orm import Session
|
||||
from typing import List, Optional
|
||||
import uuid
|
||||
|
||||
|
||||
from app.core.models import RedBearLLM, RedBearRerank
|
||||
from app.core.models.base import RedBearModelConfig
|
||||
from app.core.models.embedding import RedBearEmbeddings
|
||||
from app.db import get_db
|
||||
from app.models.models_model import ModelApiKey
|
||||
from app.core.response_utils import success
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.schemas.app_schema import AppChatRequest
|
||||
from app.services.model_service import ModelConfigService
|
||||
from app.services.handoffs_service import get_handoffs_service_for_app, reset_handoffs_service_cache
|
||||
from app.services.conversation_service import ConversationService
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.dependencies import get_current_user
|
||||
from app.models.models_model import ModelApiKey, ModelProvider, ModelType
|
||||
from app.models.user_model import User
|
||||
from app.schemas import model_schema
|
||||
from app.core.response_utils import success
|
||||
from app.schemas.response_schema import ApiResponse, PageData
|
||||
from app.services.model_service import ModelConfigService, ModelApiKeyService
|
||||
from app.core.logging_config import get_api_logger
|
||||
|
||||
# 获取API专用日志器
|
||||
api_logger = get_api_logger()
|
||||
@@ -27,8 +28,6 @@ router = APIRouter(
|
||||
)
|
||||
|
||||
|
||||
# ==================== 原有测试接口 ====================
|
||||
|
||||
@router.get("/llm/{model_id}", response_model=ApiResponse)
|
||||
def test_llm(
|
||||
model_id: uuid.UUID,
|
||||
@@ -51,6 +50,7 @@ def test_llm(
|
||||
template = """Question: {question}
|
||||
|
||||
Answer: Let's think step by step."""
|
||||
# ChatPromptTemplate
|
||||
prompt = ChatPromptTemplate.from_template(template)
|
||||
chain = prompt | llm
|
||||
answer = chain.invoke({"question": "What is LangChain?"})
|
||||
@@ -80,13 +80,13 @@ def test_embedding(
|
||||
base_url=apiConfig.api_base
|
||||
))
|
||||
|
||||
data = [
|
||||
"最近哪家咖啡店评价最好？",
|
||||
"附近有没有推荐的咖啡厅？",
|
||||
"明天天气预报说会下雨。",
|
||||
"北京是中国的首都。",
|
||||
"我想找一个适合学习的地方。"
|
||||
]
|
||||
data = [
|
||||
"最近哪家咖啡店评价最好？",
|
||||
"附近有没有推荐的咖啡厅？",
|
||||
"明天天气预报说会下雨。",
|
||||
"北京是中国的首都。",
|
||||
"我想找一个适合学习的地方。"
|
||||
]
|
||||
embeddings = model.embed_documents(data)
|
||||
print(embeddings)
|
||||
query = "我想找一个适合学习的地方。"
|
||||
@@ -114,123 +114,13 @@ def test_rerank(
|
||||
base_url=apiConfig.api_base
|
||||
))
|
||||
query = "最近哪家咖啡店评价最好？"
|
||||
data = [
|
||||
"最近哪家咖啡店评价最好？",
|
||||
"附近有没有推荐的咖啡厅？",
|
||||
"明天天气预报说会下雨。",
|
||||
"北京是中国的首都。",
|
||||
"我想找一个适合学习的地方。"
|
||||
]
|
||||
data = [
|
||||
"最近哪家咖啡店评价最好？",
|
||||
"附近有没有推荐的咖啡厅？",
|
||||
"明天天气预报说会下雨。",
|
||||
"北京是中国的首都。",
|
||||
"我想找一个适合学习的地方。"
|
||||
]
|
||||
scores = model.rerank(query=query, documents=data, top_n=3)
|
||||
print(scores)
|
||||
return success(msg="测试Rerank成功", data={"query": query, "documents": data, "scores": scores})
|
||||
|
||||
|
||||
# ==================== Handoffs 测试接口 ====================
|
||||
|
||||
@router.post("/handoffs/{app_id}")
|
||||
async def test_handoffs(
|
||||
app_id: uuid.UUID = Path(..., description="应用 ID"),
|
||||
request: AppChatRequest = Body(...),
|
||||
current_user=Depends(get_current_user),
|
||||
db: Session = Depends(get_db)
|
||||
):
|
||||
"""测试 Agent Handoffs 功能
|
||||
|
||||
演示 LangGraph 实现的多 Agent 协作和动态切换
|
||||
|
||||
- 从数据库 multi_agent_config 获取 Agent 配置
|
||||
- 根据用户问题自动切换到合适的 Agent
|
||||
- 使用 conversation_id 保持会话状态
|
||||
- 通过 stream 参数控制是否流式输出
|
||||
|
||||
事件类型（流式）：
|
||||
- start: 开始执行
|
||||
- agent: 当前 Agent 信息
|
||||
- message: 流式消息内容
|
||||
- handoff: Agent 切换事件
|
||||
- end: 执行结束
|
||||
- error: 错误信息
|
||||
"""
|
||||
try:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
# 获取或创建会话
|
||||
conversation_service = ConversationService(db)
|
||||
|
||||
if request.conversation_id:
|
||||
# 验证会话存在
|
||||
conversation = conversation_service.get_conversation(uuid.UUID(request.conversation_id))
|
||||
if not conversation:
|
||||
raise HTTPException(status_code=404, detail="会话不存在")
|
||||
conversation_id = str(conversation.id)
|
||||
else:
|
||||
# 创建新会话
|
||||
conversation = conversation_service.create_or_get_conversation(
|
||||
app_id=app_id,
|
||||
workspace_id=workspace_id,
|
||||
user_id=request.user_id,
|
||||
is_draft=True
|
||||
)
|
||||
conversation_id = str(conversation.id)
|
||||
|
||||
# 根据 stream 参数决定返回方式
|
||||
if request.stream:
|
||||
# 流式返回
|
||||
service = get_handoffs_service_for_app(app_id, db, streaming=True)
|
||||
return StreamingResponse(
|
||||
service.chat_stream(
|
||||
message=request.message,
|
||||
conversation_id=conversation_id
|
||||
),
|
||||
media_type="text/event-stream",
|
||||
headers={
|
||||
"Cache-Control": "no-cache",
|
||||
"Connection": "keep-alive",
|
||||
"X-Accel-Buffering": "no"
|
||||
}
|
||||
)
|
||||
else:
|
||||
# 非流式返回
|
||||
service = get_handoffs_service_for_app(app_id, db, streaming=False)
|
||||
result = await service.chat(
|
||||
message=request.message,
|
||||
conversation_id=conversation_id
|
||||
)
|
||||
return success(data=result, msg="Handoffs 测试成功")
|
||||
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
api_logger.error(f"Handoffs 测试失败: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.get("/handoffs/{app_id}/agents", response_model=ApiResponse)
|
||||
def get_handoff_agents(
|
||||
app_id: uuid.UUID = Path(..., description="应用 ID"),
|
||||
db: Session = Depends(get_db),
|
||||
current_user=Depends(get_current_user)
|
||||
):
|
||||
"""获取应用的 Handoff Agent 列表"""
|
||||
try:
|
||||
service = get_handoffs_service_for_app(app_id, db, streaming=False)
|
||||
agents = service.get_agents()
|
||||
return success(data={"agents": agents}, msg="获取 Agent 列表成功")
|
||||
except ValueError as e:
|
||||
raise HTTPException(status_code=400, detail=str(e))
|
||||
except Exception as e:
|
||||
api_logger.error(f"获取 Agent 列表失败: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.delete("/handoffs/{app_id}/reset")
|
||||
def reset_handoff_service(
|
||||
app_id: uuid.UUID = Path(..., description="应用 ID"),
|
||||
current_user=Depends(get_current_user)
|
||||
):
|
||||
"""重置指定应用的 Handoff 服务缓存"""
|
||||
reset_handoffs_service_cache(app_id)
|
||||
return success(msg="Handoff 服务已重置")
|
||||
|
||||
@@ -60,22 +60,6 @@ async def list_tools(
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.get("/{tool_id}/methods", response_model=ApiResponse)
|
||||
async def get_tool_methods(
|
||||
tool_id: str,
|
||||
current_user: User = Depends(get_current_user),
|
||||
service: ToolService = Depends(get_tool_service)
|
||||
):
|
||||
"""获取工具的所有方法"""
|
||||
try:
|
||||
methods = await service.get_tool_methods(tool_id, current_user.tenant_id)
|
||||
if methods is None:
|
||||
raise HTTPException(status_code=404, detail="工具不存在")
|
||||
return success(data=methods, msg="获取工具方法成功")
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.get("/{tool_id}", response_model=ApiResponse)
|
||||
async def get_tool(
|
||||
tool_id: str,
|
||||
@@ -175,8 +159,7 @@ async def execute_tool(
|
||||
workspace_id=current_user.current_workspace_id,
|
||||
timeout=request.timeout
|
||||
)
|
||||
if not result.success:
|
||||
raise HTTPException(status_code=400, detail=result["error"])
|
||||
|
||||
return success(
|
||||
data={
|
||||
"success": result.success,
|
||||
@@ -215,8 +198,8 @@ async def sync_mcp_tools(
|
||||
"""同步MCP工具列表"""
|
||||
try:
|
||||
result = await service.sync_mcp_tools(tool_id, current_user.tenant_id)
|
||||
if not result.get("success", False):
|
||||
raise HTTPException(status_code=400, detail=result.get("message", "同步失败"))
|
||||
if result["success"] is False:
|
||||
raise HTTPException(status_code=404, detail=result["message"])
|
||||
return success(data=result, msg="MCP工具列表同步完成")
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
@@ -5,23 +5,20 @@
|
||||
from typing import Optional
|
||||
import datetime
|
||||
from sqlalchemy.orm import Session
|
||||
from fastapi import APIRouter, Depends,Header
|
||||
from fastapi import APIRouter, Depends
|
||||
|
||||
from app.db import get_db
|
||||
from app.core.logging_config import get_api_logger
|
||||
from app.core.response_utils import success, fail
|
||||
from app.core.error_codes import BizCode
|
||||
from app.core.api_key_utils import timestamp_to_datetime
|
||||
from app.services.memory_base_service import Translation_English
|
||||
from app.services.user_memory_service import (
|
||||
UserMemoryService,
|
||||
analytics_node_statistics,
|
||||
analytics_memory_types,
|
||||
analytics_graph_data,
|
||||
)
|
||||
from app.services.memory_entity_relationship_service import MemoryEntityService,MemoryEmotion,MemoryInteraction
|
||||
from app.schemas.response_schema import ApiResponse
|
||||
from app.schemas.memory_storage_schema import GenerateCacheRequest
|
||||
from app.repositories.workspace_repository import WorkspaceRepository
|
||||
from app.schemas.end_user_schema import (
|
||||
EndUserProfileResponse,
|
||||
EndUserProfileUpdate,
|
||||
@@ -44,36 +41,24 @@ router = APIRouter(
|
||||
|
||||
@router.get("/analytics/memory_insight/report", response_model=ApiResponse)
|
||||
async def get_memory_insight_report_api(
|
||||
end_user_id: str,
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
end_user_id: str, # 使用 end_user_id
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
"""
|
||||
获取缓存的记忆洞察报告
|
||||
|
||||
此接口仅查询数据库中已缓存的记忆洞察数据，不执行生成操作。
|
||||
如需生成新的洞察报告，请使用专门的生成接口。
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
workspace_repo = WorkspaceRepository(db)
|
||||
workspace_models = workspace_repo.get_workspace_models_configs(workspace_id)
|
||||
|
||||
if workspace_models:
|
||||
model_id = workspace_models.get("llm", None)
|
||||
else:
|
||||
model_id = None
|
||||
api_logger.info(f"记忆洞察报告查询请求: end_user_id={end_user_id}, user={current_user.username}")
|
||||
) -> dict:
|
||||
"""获取缓存的记忆洞察报告"""
|
||||
api_logger.info(f"记忆洞察报告请求: end_user_id={end_user_id}, user={current_user.username}")
|
||||
try:
|
||||
# 调用服务层获取缓存数据
|
||||
result = await user_memory_service.get_cached_memory_insight(db, end_user_id,model_id,language_type)
|
||||
|
||||
result = await user_memory_service.get_cached_memory_insight(db, end_user_id)
|
||||
|
||||
if result["is_cached"]:
|
||||
# 缓存存在，返回缓存数据
|
||||
api_logger.info(f"成功返回缓存的记忆洞察报告: end_user_id={end_user_id}")
|
||||
return success(data=result, msg="查询成功")
|
||||
else:
|
||||
# 缓存不存在，返回提示消息
|
||||
api_logger.info(f"记忆洞察报告缓存不存在: end_user_id={end_user_id}")
|
||||
return success(data=result, msg="数据尚未生成")
|
||||
return success(data=result, msg="查询成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"记忆洞察报告查询失败: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "记忆洞察报告查询失败", str(e))
|
||||
@@ -81,36 +66,24 @@ async def get_memory_insight_report_api(
|
||||
|
||||
@router.get("/analytics/user_summary", response_model=ApiResponse)
|
||||
async def get_user_summary_api(
|
||||
end_user_id: str,
|
||||
language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
end_user_id: str, # 使用 end_user_id
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
"""
|
||||
获取缓存的用户摘要
|
||||
|
||||
此接口仅查询数据库中已缓存的用户摘要数据，不执行生成操作。
|
||||
如需生成新的用户摘要，请使用专门的生成接口。
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
workspace_repo = WorkspaceRepository(db)
|
||||
workspace_models = workspace_repo.get_workspace_models_configs(workspace_id)
|
||||
|
||||
if workspace_models:
|
||||
model_id = workspace_models.get("llm", None)
|
||||
else:
|
||||
model_id = None
|
||||
api_logger.info(f"用户摘要查询请求: end_user_id={end_user_id}, user={current_user.username}")
|
||||
) -> dict:
|
||||
"""获取缓存的用户摘要"""
|
||||
api_logger.info(f"用户摘要请求: end_user_id={end_user_id}, user={current_user.username}")
|
||||
try:
|
||||
# 调用服务层获取缓存数据
|
||||
result = await user_memory_service.get_cached_user_summary(db, end_user_id,model_id,language_type)
|
||||
|
||||
result = await user_memory_service.get_cached_user_summary(db, end_user_id)
|
||||
|
||||
if result["is_cached"]:
|
||||
# 缓存存在，返回缓存数据
|
||||
api_logger.info(f"成功返回缓存的用户摘要: end_user_id={end_user_id}")
|
||||
return success(data=result, msg="查询成功")
|
||||
else:
|
||||
# 缓存不存在，返回提示消息
|
||||
api_logger.info(f"用户摘要缓存不存在: end_user_id={end_user_id}")
|
||||
return success(data=result, msg="数据尚未生成")
|
||||
return success(data=result, msg="查询成功")
|
||||
except Exception as e:
|
||||
api_logger.error(f"用户摘要查询失败: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "用户摘要查询失败", str(e))
|
||||
@@ -124,43 +97,43 @@ async def generate_cache_api(
|
||||
) -> dict:
|
||||
"""
|
||||
手动触发缓存生成
|
||||
|
||||
|
||||
- 如果提供 end_user_id，只为该用户生成
|
||||
- 如果不提供，为当前工作空间的所有用户生成
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试生成缓存但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
end_user_id = request.end_user_id
|
||||
|
||||
|
||||
group_id = request.end_user_id
|
||||
|
||||
api_logger.info(
|
||||
f"缓存生成请求: user={current_user.username}, workspace={workspace_id}, "
|
||||
f"end_user_id={end_user_id if end_user_id else '全部用户'}"
|
||||
f"end_user_id={group_id if group_id else '全部用户'}"
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
if end_user_id:
|
||||
if group_id:
|
||||
# 为单个用户生成
|
||||
api_logger.info(f"开始为单个用户生成缓存: end_user_id={end_user_id}")
|
||||
|
||||
api_logger.info(f"开始为单个用户生成缓存: end_user_id={group_id}")
|
||||
|
||||
# 生成记忆洞察
|
||||
insight_result = await user_memory_service.generate_and_cache_insight(db, end_user_id, workspace_id)
|
||||
|
||||
insight_result = await user_memory_service.generate_and_cache_insight(db, group_id, workspace_id)
|
||||
|
||||
# 生成用户摘要
|
||||
summary_result = await user_memory_service.generate_and_cache_summary(db, end_user_id, workspace_id)
|
||||
|
||||
summary_result = await user_memory_service.generate_and_cache_summary(db, group_id, workspace_id)
|
||||
|
||||
# 构建响应
|
||||
result = {
|
||||
"end_user_id": end_user_id,
|
||||
"end_user_id": group_id,
|
||||
"insight_success": insight_result["success"],
|
||||
"summary_success": summary_result["success"],
|
||||
"errors": []
|
||||
}
|
||||
|
||||
|
||||
# 收集错误信息
|
||||
if not insight_result["success"]:
|
||||
result["errors"].append({
|
||||
@@ -172,29 +145,29 @@ async def generate_cache_api(
|
||||
"type": "summary",
|
||||
"error": summary_result.get("error")
|
||||
})
|
||||
|
||||
|
||||
# 记录结果
|
||||
if result["insight_success"] and result["summary_success"]:
|
||||
api_logger.info(f"成功为用户 {end_user_id} 生成缓存")
|
||||
api_logger.info(f"成功为用户 {group_id} 生成缓存")
|
||||
else:
|
||||
api_logger.warning(f"用户 {end_user_id} 的缓存生成部分失败: {result['errors']}")
|
||||
|
||||
api_logger.warning(f"用户 {group_id} 的缓存生成部分失败: {result['errors']}")
|
||||
|
||||
return success(data=result, msg="生成完成")
|
||||
|
||||
|
||||
else:
|
||||
# 为整个工作空间生成
|
||||
api_logger.info(f"开始为工作空间 {workspace_id} 批量生成缓存")
|
||||
|
||||
|
||||
result = await user_memory_service.generate_cache_for_workspace(db, workspace_id)
|
||||
|
||||
|
||||
# 记录统计信息
|
||||
api_logger.info(
|
||||
f"工作空间 {workspace_id} 批量生成完成: "
|
||||
f"总数={result['total_users']}, 成功={result['successful']}, 失败={result['failed']}"
|
||||
)
|
||||
|
||||
|
||||
return success(data=result, msg="批量生成完成")
|
||||
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"缓存生成失败: user={current_user.username}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "缓存生成失败", str(e))
|
||||
@@ -207,18 +180,18 @@ async def get_node_statistics_api(
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试查询节点统计但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
|
||||
api_logger.info(f"记忆类型统计请求: end_user_id={end_user_id}, user={current_user.username}, workspace={workspace_id}")
|
||||
|
||||
|
||||
try:
|
||||
# 调用新的记忆类型统计函数
|
||||
result = await analytics_memory_types(db, end_user_id)
|
||||
|
||||
|
||||
# 计算总数用于日志
|
||||
total_count = sum(item["count"] for item in result)
|
||||
api_logger.info(f"成功获取记忆类型统计: end_user_id={end_user_id}, 总记忆数={total_count}, 类型数={len(result)}")
|
||||
@@ -238,31 +211,31 @@ async def get_graph_data_api(
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试查询图数据但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
|
||||
# 参数验证
|
||||
if limit > 1000:
|
||||
limit = 1000
|
||||
api_logger.warning("limit 参数超过最大值，已调整为 1000")
|
||||
|
||||
|
||||
if depth > 3:
|
||||
depth = 3
|
||||
api_logger.warning("depth 参数超过最大值，已调整为 3")
|
||||
|
||||
|
||||
# 解析 node_types 参数
|
||||
node_types_list = None
|
||||
if node_types:
|
||||
node_types_list = [t.strip() for t in node_types.split(",") if t.strip()]
|
||||
|
||||
|
||||
api_logger.info(
|
||||
f"图数据查询请求: end_user_id={end_user_id}, user={current_user.username}, "
|
||||
f"workspace={workspace_id}, node_types={node_types_list}, limit={limit}, depth={depth}"
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
result = await analytics_graph_data(
|
||||
db=db,
|
||||
@@ -272,18 +245,19 @@ async def get_graph_data_api(
|
||||
depth=depth,
|
||||
center_node_id=center_node_id
|
||||
)
|
||||
|
||||
# 检查是否有错误消息
|
||||
if "message" in result and result["statistics"]["total_nodes"] == 0:
|
||||
api_logger.warning(f"图数据查询返回空结果: {result.get('message')}")
|
||||
return success(data=result, msg=result.get("message", "查询成功"))
|
||||
|
||||
|
||||
api_logger.info(
|
||||
f"成功获取图数据: end_user_id={end_user_id}, "
|
||||
f"nodes={result['statistics']['total_nodes']}, "
|
||||
f"edges={result['statistics']['total_edges']}"
|
||||
)
|
||||
return success(data=result, msg="查询成功")
|
||||
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"图数据查询失败: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "图数据查询失败", str(e))
|
||||
@@ -296,30 +270,25 @@ async def get_end_user_profile(
|
||||
db: Session = Depends(get_db),
|
||||
) -> dict:
|
||||
workspace_id = current_user.current_workspace_id
|
||||
workspace_repo = WorkspaceRepository(db)
|
||||
workspace_models = workspace_repo.get_workspace_models_configs(workspace_id)
|
||||
|
||||
if workspace_models:
|
||||
model_id = workspace_models.get("llm", None)
|
||||
else:
|
||||
model_id = None
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试查询用户信息但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
|
||||
api_logger.info(
|
||||
f"用户信息查询请求: end_user_id={end_user_id}, user={current_user.username}, "
|
||||
f"workspace={workspace_id}"
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
# 查询终端用户
|
||||
end_user = db.query(EndUser).filter(EndUser.id == end_user_id).first()
|
||||
|
||||
|
||||
if not end_user:
|
||||
api_logger.warning(f"终端用户不存在: end_user_id={end_user_id}")
|
||||
return fail(BizCode.INVALID_PARAMETER, "终端用户不存在", f"end_user_id={end_user_id}")
|
||||
|
||||
# 构建响应数据
|
||||
profile_data = EndUserProfileResponse(
|
||||
id=end_user.id,
|
||||
@@ -331,10 +300,10 @@ async def get_end_user_profile(
|
||||
hire_date=end_user.hire_date,
|
||||
updatetime_profile=end_user.updatetime_profile
|
||||
)
|
||||
|
||||
|
||||
api_logger.info(f"成功获取用户信息: end_user_id={end_user_id}")
|
||||
return success(data=UserMemoryService.convert_profile_to_dict_with_timestamp(profile_data), msg="查询成功")
|
||||
|
||||
return success(data=profile_data.model_dump(), msg="查询成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"用户信息查询失败: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "用户信息查询失败", str(e))
|
||||
@@ -348,87 +317,65 @@ async def update_end_user_profile(
|
||||
) -> dict:
|
||||
"""
|
||||
更新终端用户的基本信息
|
||||
|
||||
|
||||
该接口可以更新用户的姓名、职位、部门、联系方式、电话和入职日期等信息。
|
||||
所有字段都是可选的，只更新提供的字段。
|
||||
|
||||
"""
|
||||
workspace_id = current_user.current_workspace_id
|
||||
end_user_id = profile_update.end_user_id
|
||||
|
||||
# 验证工作空间
|
||||
|
||||
# 检查用户是否已选择工作空间
|
||||
if workspace_id is None:
|
||||
api_logger.warning(f"用户 {current_user.username} 尝试更新用户信息但未选择工作空间")
|
||||
return fail(BizCode.INVALID_PARAMETER, "请先切换到一个工作空间", "current_workspace_id is None")
|
||||
|
||||
|
||||
api_logger.info(
|
||||
f"用户信息更新请求: end_user_id={end_user_id}, user={current_user.username}, "
|
||||
f"workspace={workspace_id}"
|
||||
)
|
||||
|
||||
# 调用 Service 层处理业务逻辑
|
||||
result = user_memory_service.update_end_user_profile(db, end_user_id, profile_update)
|
||||
|
||||
if result["success"]:
|
||||
api_logger.info(f"成功更新用户信息: end_user_id={end_user_id}")
|
||||
return success(data=result["data"], msg="更新成功")
|
||||
else:
|
||||
error_msg = result["error"]
|
||||
api_logger.error(f"用户信息更新失败: end_user_id={end_user_id}, error={error_msg}")
|
||||
|
||||
# 根据错误类型映射到合适的业务错误码
|
||||
if error_msg == "终端用户不存在":
|
||||
return fail(BizCode.USER_NOT_FOUND, "终端用户不存在", error_msg)
|
||||
elif error_msg == "无效的用户ID格式":
|
||||
return fail(BizCode.INVALID_USER_ID, "无效的用户ID格式", error_msg)
|
||||
else:
|
||||
# 只有未预期的错误才使用 INTERNAL_ERROR
|
||||
return fail(BizCode.INTERNAL_ERROR, "用户信息更新失败", error_msg)
|
||||
|
||||
@router.get("/memory_space/timeline_memories", response_model=ApiResponse)
|
||||
async def memory_space_timeline_of_shared_memories(id: str, label: str,language_type: str = Header(default="zh", alias="X-Language-Type"),
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
workspace_id=current_user.current_workspace_id
|
||||
workspace_repo = WorkspaceRepository(db)
|
||||
workspace_models = workspace_repo.get_workspace_models_configs(workspace_id)
|
||||
|
||||
if workspace_models:
|
||||
model_id = workspace_models.get("llm", None)
|
||||
else:
|
||||
model_id = None
|
||||
MemoryEntity = MemoryEntityService(id, label)
|
||||
timeline_memories_result = await MemoryEntity.get_timeline_memories_server(model_id, language_type)
|
||||
|
||||
return success(data=timeline_memories_result, msg="共同记忆时间线")
|
||||
@router.get("/memory_space/relationship_evolution", response_model=ApiResponse)
|
||||
async def memory_space_relationship_evolution(id: str, label: str,
|
||||
current_user: User = Depends(get_current_user),
|
||||
db: Session = Depends(get_db),
|
||||
):
|
||||
|
||||
try:
|
||||
api_logger.info(f"关系演变查询请求: id={id}, table={label}, user={current_user.username}")
|
||||
|
||||
# 获取情绪数据
|
||||
emotion = MemoryEmotion(id, label)
|
||||
emotion_result = await emotion.get_emotion()
|
||||
|
||||
# 获取交互数据
|
||||
interaction = MemoryInteraction(id, label)
|
||||
interaction_result = await interaction.get_interaction_frequency()
|
||||
|
||||
# 关闭连接
|
||||
await emotion.close()
|
||||
await interaction.close()
|
||||
|
||||
result = {
|
||||
"emotion": emotion_result,
|
||||
"interaction": interaction_result
|
||||
}
|
||||
|
||||
api_logger.info(f"关系演变查询成功: id={id}, table={label}")
|
||||
return success(data=result, msg="关系演变")
|
||||
|
||||
# 查询终端用户
|
||||
end_user = db.query(EndUser).filter(EndUser.id == end_user_id).first()
|
||||
|
||||
if not end_user:
|
||||
api_logger.warning(f"终端用户不存在: end_user_id={end_user_id}")
|
||||
return fail(BizCode.INVALID_PARAMETER, "终端用户不存在", f"end_user_id={end_user_id}")
|
||||
|
||||
# 更新字段（只更新提供的字段，排除 end_user_id）
|
||||
# 允许 None 值来重置字段（如 hire_date）
|
||||
update_data = profile_update.model_dump(exclude_unset=True, exclude={'end_user_id'})
|
||||
for field, value in update_data.items():
|
||||
setattr(end_user, field, value)
|
||||
|
||||
# 更新 updated_at 时间戳
|
||||
end_user.updated_at = datetime.datetime.now()
|
||||
|
||||
# 更新 updatetime_profile 为当前时间戳（毫秒）
|
||||
current_timestamp = int(datetime.datetime.now().timestamp() * 1000)
|
||||
end_user.updatetime_profile = current_timestamp
|
||||
|
||||
# 提交更改
|
||||
db.commit()
|
||||
db.refresh(end_user)
|
||||
|
||||
# 构建响应数据
|
||||
profile_data = EndUserProfileResponse(
|
||||
id=end_user.id,
|
||||
other_name=end_user.other_name,
|
||||
position=end_user.position,
|
||||
department=end_user.department,
|
||||
contact=end_user.contact,
|
||||
phone=end_user.phone,
|
||||
hire_date=end_user.hire_date,
|
||||
updatetime_profile=end_user.updatetime_profile
|
||||
)
|
||||
|
||||
api_logger.info(f"成功更新用户信息: end_user_id={end_user_id}, updated_fields={list(update_data.keys())}, updatetime_profile={current_timestamp}")
|
||||
return success(data=profile_data.model_dump(), msg="更新成功")
|
||||
|
||||
except Exception as e:
|
||||
api_logger.error(f"关系演变查询失败: id={id}, table={label}, error={str(e)}", exc_info=True)
|
||||
return fail(BizCode.INTERNAL_ERROR, "关系演变查询失败", str(e))
|
||||
db.rollback()
|
||||
api_logger.error(f"用户信息更新失败: end_user_id={end_user_id}, error={str(e)}")
|
||||
return fail(BizCode.INTERNAL_ERROR, "用户信息更新失败", str(e))
|
||||
|
||||
@@ -39,11 +39,11 @@ router = APIRouter(prefix="/apps", tags=["workflow"])
|
||||
@router.post("/{app_id}/workflow")
|
||||
@cur_workspace_access_guard()
|
||||
async def create_workflow_config(
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
config: WorkflowConfigCreate,
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
config: WorkflowConfigCreate,
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
):
|
||||
"""创建工作流配置
|
||||
|
||||
@@ -54,7 +54,7 @@ async def create_workflow_config(
|
||||
app = db.query(App).filter(
|
||||
App.id == app_id,
|
||||
App.workspace_id == current_user.current_workspace_id,
|
||||
App.is_active.is_(True)
|
||||
App.is_active == True
|
||||
).first()
|
||||
|
||||
if not app:
|
||||
@@ -96,7 +96,6 @@ async def create_workflow_config(
|
||||
msg=f"创建工作流配置失败: {str(e)}"
|
||||
)
|
||||
|
||||
|
||||
#
|
||||
# @router.get("/{app_id}/workflow")
|
||||
# async def get_workflow_config(
|
||||
@@ -200,10 +199,10 @@ async def create_workflow_config(
|
||||
|
||||
@router.delete("/{app_id}/workflow")
|
||||
async def delete_workflow_config(
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
):
|
||||
"""删除工作流配置
|
||||
|
||||
@@ -214,7 +213,7 @@ async def delete_workflow_config(
|
||||
app = db.query(App).filter(
|
||||
App.id == app_id,
|
||||
App.workspace_id == current_user.current_workspace_id,
|
||||
App.is_active.is_(True)
|
||||
App.is_active == True
|
||||
).first()
|
||||
|
||||
if not app:
|
||||
@@ -244,11 +243,11 @@ async def delete_workflow_config(
|
||||
|
||||
@router.post("/{app_id}/workflow/validate")
|
||||
async def validate_workflow_config(
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)],
|
||||
for_publish: Annotated[bool, Query(description="是否为发布验证")] = False
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)],
|
||||
for_publish: Annotated[bool, Query(description="是否为发布验证")] = False
|
||||
):
|
||||
"""验证工作流配置
|
||||
|
||||
@@ -259,7 +258,7 @@ async def validate_workflow_config(
|
||||
app = db.query(App).filter(
|
||||
App.id == app_id,
|
||||
App.workspace_id == current_user.current_workspace_id,
|
||||
App.is_active.is_(True)
|
||||
App.is_active == True
|
||||
).first()
|
||||
|
||||
if not app:
|
||||
@@ -313,12 +312,12 @@ async def validate_workflow_config(
|
||||
|
||||
@router.get("/{app_id}/workflow/executions")
|
||||
async def get_workflow_executions(
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)],
|
||||
limit: Annotated[int, Query(ge=1, le=100)] = 50,
|
||||
offset: Annotated[int, Query(ge=0)] = 0
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)],
|
||||
limit: Annotated[int, Query(ge=1, le=100)] = 50,
|
||||
offset: Annotated[int, Query(ge=0)] = 0
|
||||
):
|
||||
"""获取工作流执行记录列表
|
||||
|
||||
@@ -329,7 +328,7 @@ async def get_workflow_executions(
|
||||
app = db.query(App).filter(
|
||||
App.id == app_id,
|
||||
App.workspace_id == current_user.current_workspace_id,
|
||||
App.is_active.is_(True)
|
||||
App.is_active == True
|
||||
).first()
|
||||
|
||||
if not app:
|
||||
@@ -366,10 +365,10 @@ async def get_workflow_executions(
|
||||
|
||||
@router.get("/workflow/executions/{execution_id}")
|
||||
async def get_workflow_execution(
|
||||
execution_id: Annotated[str, Path(description="执行 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
execution_id: Annotated[str, Path(description="执行 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
):
|
||||
"""获取工作流执行详情
|
||||
|
||||
@@ -389,7 +388,7 @@ async def get_workflow_execution(
|
||||
app = db.query(App).filter(
|
||||
App.id == execution.app_id,
|
||||
App.workspace_id == current_user.current_workspace_id,
|
||||
App.is_active.is_(True)
|
||||
App.is_active == True
|
||||
).first()
|
||||
|
||||
if not app:
|
||||
@@ -418,14 +417,16 @@ async def get_workflow_execution(
|
||||
)
|
||||
|
||||
|
||||
|
||||
# ==================== 工作流执行 ====================
|
||||
|
||||
@router.post("/{app_id}/workflow/run")
|
||||
async def run_workflow(
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
request: WorkflowExecutionRequest,
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
app_id: Annotated[uuid.UUID, Path(description="应用 ID")],
|
||||
request: WorkflowExecutionRequest,
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
):
|
||||
"""执行工作流
|
||||
|
||||
@@ -440,7 +441,7 @@ async def run_workflow(
|
||||
app = db.query(App).filter(
|
||||
App.id == app_id,
|
||||
App.workspace_id == current_user.current_workspace_id,
|
||||
App.is_active.is_(True)
|
||||
App.is_active == True
|
||||
).first()
|
||||
|
||||
if not app:
|
||||
@@ -486,22 +487,22 @@ async def run_workflow(
|
||||
"""
|
||||
try:
|
||||
async for event in await service.run_workflow(
|
||||
app_id=app_id,
|
||||
input_data=input_data,
|
||||
triggered_by=current_user.id,
|
||||
conversation_id=uuid.UUID(request.conversation_id) if request.conversation_id else None,
|
||||
stream=True
|
||||
app_id=app_id,
|
||||
input_data=input_data,
|
||||
triggered_by=current_user.id,
|
||||
conversation_id=uuid.UUID(request.conversation_id) if request.conversation_id else None,
|
||||
stream=True
|
||||
):
|
||||
# 提取事件类型和数据
|
||||
event_type = event.get("event", "message")
|
||||
event_data = event.get("data", {})
|
||||
|
||||
|
||||
# 转换为标准 SSE 格式（字符串）
|
||||
# event: <type>
|
||||
# data: <json>
|
||||
sse_message = f"event: {event_type}\ndata: {json.dumps(event_data)}\n\n"
|
||||
yield sse_message
|
||||
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"流式执行异常: {e}", exc_info=True)
|
||||
# 发送错误事件
|
||||
@@ -553,10 +554,10 @@ async def run_workflow(
|
||||
|
||||
@router.post("/workflow/executions/{execution_id}/cancel")
|
||||
async def cancel_workflow_execution(
|
||||
execution_id: Annotated[str, Path(description="执行 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
execution_id: Annotated[str, Path(description="执行 ID")],
|
||||
db: Annotated[Session, Depends(get_db)],
|
||||
current_user: Annotated[User, Depends(get_current_user)],
|
||||
service: Annotated[WorkflowService, Depends(get_workflow_service)]
|
||||
):
|
||||
"""取消工作流执行
|
||||
|
||||
@@ -578,7 +579,7 @@ async def cancel_workflow_execution(
|
||||
app = db.query(App).filter(
|
||||
App.id == execution.app_id,
|
||||
App.workspace_id == current_user.current_workspace_id,
|
||||
App.is_active.is_(True)
|
||||
App.is_active == True
|
||||
).first()
|
||||
|
||||
if not app:
|
||||
@@ -601,7 +602,7 @@ async def cancel_workflow_execution(
|
||||
|
||||
except BusinessException as e:
|
||||
logger.warning(f"取消工作流执行失败: {e.message}")
|
||||
return fail(code=e.code, msg=e.message)
|
||||
return fail(code=e.error_code, msg=e.message)
|
||||
except Exception as e:
|
||||
logger.error(f"取消工作流执行异常: {e}", exc_info=True)
|
||||
return fail(
|
||||
|
||||
@@ -11,16 +11,10 @@ import os
|
||||
import time
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional, Sequence
|
||||
|
||||
|
||||
from app.db import get_db
|
||||
from app.core.logging_config import get_business_logger
|
||||
from app.core.memory.agent.utils.redis_tool import store
|
||||
from app.core.models import RedBearLLM, RedBearModelConfig
|
||||
from app.models.models_model import ModelType
|
||||
from app.repositories.memory_short_repository import LongTermMemoryRepository
|
||||
from app.services.memory_agent_service import (
|
||||
get_end_user_connected_config,
|
||||
)
|
||||
from app.services.memory_konwledges_server import write_rag
|
||||
from app.services.task_service import get_task_memory_write_result
|
||||
from app.tasks import write_message_task
|
||||
@@ -28,8 +22,6 @@ from langchain.agents import create_agent
|
||||
from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, SystemMessage
|
||||
from langchain_core.tools import BaseTool
|
||||
|
||||
from app.utils.config_utils import resolve_config_id
|
||||
|
||||
logger = get_business_logger()
|
||||
|
||||
|
||||
@@ -147,104 +139,43 @@ class LangChainAgent:
|
||||
messages.append(HumanMessage(content=user_content))
|
||||
|
||||
return messages
|
||||
# TODO 乐力齐 - 累积多组对话批量写入功能已禁用
|
||||
# async def term_memory_save(self,messages,end_user_end,aimessages):
|
||||
# '''短长期存储redis，为不影响正常使用6句一段话，存储用户名加一个前缀，当数据存够6条返回给neo4j'''
|
||||
# end_user_end=f"Term_{end_user_end}"
|
||||
# print(messages)
|
||||
# print(aimessages)
|
||||
# session_id = store.save_session(
|
||||
# userid=end_user_end,
|
||||
# messages=messages,
|
||||
# apply_id=end_user_end,
|
||||
# end_user_id=end_user_end,
|
||||
# aimessages=aimessages
|
||||
# )
|
||||
# store.delete_duplicate_sessions()
|
||||
# # logger.info(f'Redis_Agent:{end_user_end};{session_id}')
|
||||
# return session_id
|
||||
async def term_memory_save(self,messages,end_user_end,aimessages):
|
||||
'''短长期存储redis，为不影响正常使用6句一段话，存储用户名加一个前缀，当数据存够6条返回给neo4j'''
|
||||
end_user_end=f"Term_{end_user_end}"
|
||||
print(messages)
|
||||
print(aimessages)
|
||||
session_id = store.save_session(
|
||||
userid=end_user_end,
|
||||
messages=messages,
|
||||
apply_id=end_user_end,
|
||||
group_id=end_user_end,
|
||||
aimessages=aimessages
|
||||
)
|
||||
store.delete_duplicate_sessions()
|
||||
# logger.info(f'Redis_Agent:{end_user_end};{session_id}')
|
||||
return session_id
|
||||
async def term_memory_redis_read(self,end_user_end):
|
||||
end_user_end = f"Term_{end_user_end}"
|
||||
history = store.find_user_apply_group(end_user_end, end_user_end, end_user_end)
|
||||
# logger.info(f'Redis_Agent:{end_user_end};{history}')
|
||||
messagss_list=[]
|
||||
for messages in history:
|
||||
query = messages.get("Query")
|
||||
aimessages = messages.get("Answer")
|
||||
messagss_list.append(f'用户:{query}。AI回复:{aimessages}')
|
||||
return messagss_list
|
||||
|
||||
# TODO 乐力齐 - 累积多组对话批量写入功能已禁用
|
||||
# async def term_memory_redis_read(self,end_user_end):
|
||||
# end_user_end = f"Term_{end_user_end}"
|
||||
# history = store.find_user_apply_group(end_user_end, end_user_end, end_user_end)
|
||||
# # logger.info(f'Redis_Agent:{end_user_end};{history}')
|
||||
# messagss_list=[]
|
||||
# retrieved_content=[]
|
||||
# for messages in history:
|
||||
# query = messages.get("Query")
|
||||
# aimessages = messages.get("Answer")
|
||||
# messagss_list.append(f'用户:{query}。AI回复:{aimessages}')
|
||||
# retrieved_content.append({query: aimessages})
|
||||
# return messagss_list,retrieved_content
|
||||
async def write(self, storage_type, end_user_id, user_message, ai_message, user_rag_memory_id, actual_end_user_id, actual_config_id):
|
||||
"""
|
||||
写入记忆（支持结构化消息）
|
||||
|
||||
Args:
|
||||
storage_type: 存储类型 (neo4j/rag)
|
||||
end_user_id: 终端用户ID
|
||||
user_message: 用户消息内容
|
||||
ai_message: AI 回复内容
|
||||
user_rag_memory_id: RAG 记忆ID
|
||||
actual_end_user_id: 实际用户ID
|
||||
actual_config_id: 配置ID
|
||||
async def write(self,storage_type,end_user_id,message,user_rag_memory_id,actual_end_user_id,content,actual_config_id):
|
||||
if storage_type == "rag":
|
||||
await write_rag(end_user_id, message, user_rag_memory_id)
|
||||
logger.info(f'RAG_Agent:{end_user_id};{user_rag_memory_id}')
|
||||
else:
|
||||
write_id = write_message_task.delay(actual_end_user_id, content, actual_config_id, storage_type,
|
||||
user_rag_memory_id)
|
||||
write_status = get_task_memory_write_result(str(write_id))
|
||||
logger.info(f'Agent:{actual_end_user_id};{write_status}')
|
||||
|
||||
逻辑说明：
|
||||
- RAG 模式：组合 user_message 和 ai_message 为字符串格式，保持原有逻辑不变
|
||||
- Neo4j 模式：使用结构化消息列表
|
||||
1. 如果 user_message 和 ai_message 都不为空：创建配对消息 [user, assistant]
|
||||
2. 如果只有 user_message：创建单条用户消息 [user]（用于历史记忆场景）
|
||||
3. 每条消息会被转换为独立的 Chunk，保留 speaker 字段
|
||||
"""
|
||||
|
||||
db = next(get_db())
|
||||
try:
|
||||
actual_config_id=resolve_config_id(actual_config_id, db)
|
||||
|
||||
if storage_type == "rag":
|
||||
# RAG 模式：组合消息为字符串格式（保持原有逻辑）
|
||||
combined_message = f"user: {user_message}\nassistant: {ai_message}"
|
||||
await write_rag(end_user_id, combined_message, user_rag_memory_id)
|
||||
logger.info(f'RAG_Agent:{end_user_id};{user_rag_memory_id}')
|
||||
else:
|
||||
# Neo4j 模式：使用结构化消息列表
|
||||
structured_messages = []
|
||||
|
||||
# 始终添加用户消息（如果不为空）
|
||||
if user_message:
|
||||
structured_messages.append({"role": "user", "content": user_message})
|
||||
|
||||
# 只有当 AI 回复不为空时才添加 assistant 消息
|
||||
if ai_message:
|
||||
structured_messages.append({"role": "assistant", "content": ai_message})
|
||||
|
||||
# 如果没有消息，直接返回
|
||||
if not structured_messages:
|
||||
logger.warning(f"No messages to write for user {actual_end_user_id}")
|
||||
return
|
||||
|
||||
# 调用 Celery 任务，传递结构化消息列表
|
||||
# 数据流：
|
||||
# 1. structured_messages 传递给 write_message_task
|
||||
# 2. write_message_task 调用 memory_agent_service.write_memory
|
||||
# 3. write_memory 调用 write_tools.write，传递 messages 参数
|
||||
# 4. write_tools.write 调用 get_chunked_dialogs，传递 messages 参数
|
||||
# 5. get_chunked_dialogs 为每条消息创建独立的 Chunk，设置 speaker 字段
|
||||
# 6. 每个 Chunk 保存到 Neo4j，包含 speaker 字段
|
||||
logger.info(f"[WRITE] Submitting Celery task - user={actual_end_user_id}, messages={len(structured_messages)}, config={actual_config_id}")
|
||||
write_id = write_message_task.delay(
|
||||
actual_end_user_id, # end_user_id: 用户ID
|
||||
structured_messages, # message: 结构化消息列表 [{"role": "user", "content": "..."}, {"role": "assistant", "content": "..."}]
|
||||
actual_config_id, # config_id: 配置ID
|
||||
storage_type, # storage_type: "neo4j"
|
||||
user_rag_memory_id # user_rag_memory_id: RAG记忆ID（Neo4j模式下不使用）
|
||||
)
|
||||
logger.info(f"[WRITE] Celery task submitted - task_id={write_id}")
|
||||
write_status = get_task_memory_write_result(str(write_id))
|
||||
logger.info(f'[WRITE] Task result - user={actual_end_user_id}, status={write_status}')
|
||||
finally:
|
||||
db.close()
|
||||
async def chat(
|
||||
self,
|
||||
message: str,
|
||||
@@ -272,6 +203,7 @@ class LangChainAgent:
|
||||
# If config_id is None, try to get from end_user's connected config
|
||||
if actual_config_id is None and end_user_id:
|
||||
try:
|
||||
from app.db import get_db
|
||||
from app.services.memory_agent_service import (
|
||||
get_end_user_connected_config,
|
||||
)
|
||||
@@ -288,30 +220,14 @@ class LangChainAgent:
|
||||
actual_end_user_id = end_user_id if end_user_id is not None else "unknown"
|
||||
logger.info(f'写入类型{storage_type,str(end_user_id), message, str(user_rag_memory_id)}')
|
||||
print(f'写入类型{storage_type,str(end_user_id), message, str(user_rag_memory_id)}')
|
||||
# # TODO 乐力齐，在长短期记忆存储的时候再使用此代码
|
||||
# history_term_memory_result = await self.term_memory_redis_read(end_user_id)
|
||||
# history_term_memory = history_term_memory_result[0]
|
||||
# db_for_memory = next(get_db())
|
||||
# if memory_flag:
|
||||
# if len(history_term_memory)>=4 and storage_type != "rag":
|
||||
# history_term_memory = ';'.join(history_term_memory)
|
||||
# retrieved_content = history_term_memory_result[1]
|
||||
# print(retrieved_content)
|
||||
# # 为长期记忆操作获取新的数据库连接
|
||||
# try:
|
||||
# repo = LongTermMemoryRepository(db_for_memory)
|
||||
# repo.upsert(end_user_id, retrieved_content)
|
||||
# logger.info(
|
||||
# f'写入短长期：{storage_type, str(end_user_id), history_term_memory, str(user_rag_memory_id)}')
|
||||
# except Exception as e:
|
||||
# logger.error(f"Failed to write to LongTermMemory: {e}")
|
||||
# raise
|
||||
# finally:
|
||||
# db_for_memory.close()
|
||||
|
||||
# # 长期记忆写入（
|
||||
# await self.write(storage_type, actual_end_user_id, history_term_memory, "", user_rag_memory_id, actual_end_user_id, actual_config_id)
|
||||
# # 注意：不在这里写入用户消息，等 AI 回复后一起写入
|
||||
history_term_memory=await self.term_memory_redis_read(end_user_id)
|
||||
if memory_flag:
|
||||
if len(history_term_memory)>=4 and storage_type != "rag":
|
||||
history_term_memory=';'.join(history_term_memory)
|
||||
logger.info(f'写入短长期：{storage_type, str(end_user_id), history_term_memory, str(user_rag_memory_id)}')
|
||||
await self.write(storage_type,end_user_id,history_term_memory,user_rag_memory_id,actual_end_user_id,history_term_memory,actual_config_id)
|
||||
await self.write(storage_type,end_user_id,message,user_rag_memory_id,actual_end_user_id,message,actual_config_id)
|
||||
try:
|
||||
# 准备消息列表
|
||||
messages = self._prepare_messages(message, history, context)
|
||||
@@ -339,10 +255,8 @@ class LangChainAgent:
|
||||
|
||||
elapsed_time = time.time() - start_time
|
||||
if memory_flag:
|
||||
# AI 回复写入（用户消息和 AI 回复配对，一次性写入完整对话）
|
||||
await self.write(storage_type, actual_end_user_id, message_chat, content, user_rag_memory_id, actual_end_user_id, actual_config_id)
|
||||
# TODO 乐力齐 - 累积多组对话批量写入功能已禁用
|
||||
# await self.term_memory_save(message_chat, end_user_id, content)
|
||||
await self.write(storage_type,end_user_id,content,user_rag_memory_id,actual_end_user_id,content,actual_config_id)
|
||||
await self.term_memory_save(message_chat,end_user_id,content)
|
||||
response = {
|
||||
"content": content,
|
||||
"model": self.model_name,
|
||||
@@ -400,6 +314,10 @@ class LangChainAgent:
|
||||
# If config_id is None, try to get from end_user's connected config
|
||||
if actual_config_id is None and end_user_id:
|
||||
try:
|
||||
from app.db import get_db
|
||||
from app.services.memory_agent_service import (
|
||||
get_end_user_connected_config,
|
||||
)
|
||||
db = next(get_db())
|
||||
try:
|
||||
connected_config = get_end_user_connected_config(end_user_id, db)
|
||||
@@ -410,27 +328,17 @@ class LangChainAgent:
|
||||
db.close()
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to get db session: {e}")
|
||||
# # TODO 乐力齐
|
||||
# history_term_memory_result = await self.term_memory_redis_read(end_user_id)
|
||||
# history_term_memory = history_term_memory_result[0]
|
||||
# if memory_flag:
|
||||
# if len(history_term_memory) >= 4 and storage_type != "rag":
|
||||
# history_term_memory = ';'.join(history_term_memory)
|
||||
# retrieved_content = history_term_memory_result[1]
|
||||
# db_for_memory = next(get_db())
|
||||
# try:
|
||||
# repo = LongTermMemoryRepository(db_for_memory)
|
||||
# repo.upsert(end_user_id, retrieved_content)
|
||||
# logger.info(
|
||||
# f'写入短长期：{storage_type, str(end_user_id), history_term_memory, str(user_rag_memory_id)}')
|
||||
# # 长期记忆写入
|
||||
# await self.write(storage_type, end_user_id, history_term_memory, "", user_rag_memory_id, end_user_id, actual_config_id)
|
||||
# except Exception as e:
|
||||
# logger.error(f"Failed to write to long term memory: {e}")
|
||||
# finally:
|
||||
# db_for_memory.close()
|
||||
|
||||
# 注意：不在这里写入用户消息，等 AI 回复后一起写入
|
||||
history_term_memory = await self.term_memory_redis_read(end_user_id)
|
||||
if memory_flag:
|
||||
if len(history_term_memory) >= 4 and storage_type != "rag":
|
||||
history_term_memory = ';'.join(history_term_memory)
|
||||
logger.info(
|
||||
f'写入短长期：{storage_type, str(end_user_id), history_term_memory, str(user_rag_memory_id)}')
|
||||
await self.write(storage_type, end_user_id, history_term_memory, user_rag_memory_id, end_user_id,
|
||||
history_term_memory, actual_config_id)
|
||||
|
||||
await self.write(storage_type, end_user_id, message, user_rag_memory_id, end_user_id, message, actual_config_id)
|
||||
try:
|
||||
# 准备消息列表
|
||||
messages = self._prepare_messages(message, history, context)
|
||||
@@ -482,10 +390,8 @@ class LangChainAgent:
|
||||
|
||||
logger.debug(f"Agent 流式完成，共 {chunk_count} 个事件")
|
||||
if memory_flag:
|
||||
# AI 回复写入（用户消息和 AI 回复配对，一次性写入完整对话）
|
||||
await self.write(storage_type, end_user_id, message_chat, full_content, user_rag_memory_id, end_user_id, actual_config_id)
|
||||
# TODO 乐力齐 - 累积多组对话批量写入功能已禁用
|
||||
# await self.term_memory_save(message_chat, end_user_id, full_content)
|
||||
await self.write(storage_type, end_user_id,full_content, user_rag_memory_id, end_user_id,full_content, actual_config_id)
|
||||
await self.term_memory_save(message_chat, end_user_id, full_content)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Agent astream_events 失败: {str(e)}", exc_info=True)
|
||||
|
||||
@@ -3,7 +3,7 @@ import secrets
|
||||
from typing import Optional, Union
|
||||
from datetime import datetime
|
||||
|
||||
from app.models.api_key_model import ApiKeyType
|
||||
from app.schemas.api_key_schema import ApiKeyType
|
||||
from fastapi import Response
|
||||
from fastapi.responses import JSONResponse
|
||||
|
||||
|
||||
@@ -7,37 +7,17 @@ from dotenv import load_dotenv
|
||||
|
||||
load_dotenv()
|
||||
|
||||
|
||||
class Settings:
|
||||
# ========================================================================
|
||||
# Deployment Mode Configuration
|
||||
# ========================================================================
|
||||
# community: 社区版（开源，功能受限）
|
||||
# cloud: SaaS 云服务版（全功能，按量计费）
|
||||
# enterprise: 企业私有化版（License 控制）
|
||||
DEPLOYMENT_MODE: str = os.getenv("DEPLOYMENT_MODE", "community")
|
||||
|
||||
# License 配置（企业版）
|
||||
LICENSE_FILE: str = os.getenv("LICENSE_FILE", "/etc/app/license.json")
|
||||
LICENSE_SERVER_URL: str = os.getenv("LICENSE_SERVER_URL", "https://license.yourcompany.com")
|
||||
|
||||
# 计费服务配置（SaaS 版）
|
||||
BILLING_SERVICE_URL: str = os.getenv("BILLING_SERVICE_URL", "")
|
||||
|
||||
# 基础 URL（用于 SSO 回调等）
|
||||
BASE_URL: str = os.getenv("BASE_URL", "http://localhost:8000")
|
||||
FRONTEND_URL: str = os.getenv("FRONTEND_URL", "http://localhost:3000")
|
||||
|
||||
ENABLE_SINGLE_WORKSPACE: bool = os.getenv("ENABLE_SINGLE_WORKSPACE", "true").lower() == "true"
|
||||
# API Keys Configuration
|
||||
OPENAI_API_KEY: str = os.getenv("OPENAI_API_KEY", "")
|
||||
DASHSCOPE_API_KEY: str = os.getenv("DASHSCOPE_API_KEY", "")
|
||||
|
||||
|
||||
# Neo4j Configuration (记忆系统数据库)
|
||||
NEO4J_URI: str = os.getenv("NEO4J_URI", "bolt://1.94.111.67:7687")
|
||||
NEO4J_USERNAME: str = os.getenv("NEO4J_USERNAME", "neo4j")
|
||||
NEO4J_PASSWORD: str = os.getenv("NEO4J_PASSWORD", "")
|
||||
|
||||
|
||||
# Database configuration (Postgres)
|
||||
DB_HOST: str = os.getenv("DB_HOST", "127.0.0.1")
|
||||
DB_PORT: int = int(os.getenv("DB_PORT", "5432"))
|
||||
@@ -58,7 +38,6 @@ class Settings:
|
||||
REDIS_DB: int = int(os.getenv("REDIS_DB", "1"))
|
||||
REDIS_PASSWORD: str = os.getenv("REDIS_PASSWORD", "")
|
||||
|
||||
|
||||
# ElasticSearch configuration
|
||||
ELASTICSEARCH_HOST: str = os.getenv("ELASTICSEARCH_HOST", "https://127.0.0.1")
|
||||
ELASTICSEARCH_PORT: int = int(os.getenv("ELASTICSEARCH_PORT", "9200"))
|
||||
@@ -69,7 +48,7 @@ class Settings:
|
||||
ELASTICSEARCH_REQUEST_TIMEOUT: int = int(os.getenv("ELASTICSEARCH_REQUEST_TIMEOUT", "100000"))
|
||||
ELASTICSEARCH_RETRY_ON_TIMEOUT: bool = os.getenv("ELASTICSEARCH_RETRY_ON_TIMEOUT", "True").lower() == "true"
|
||||
ELASTICSEARCH_MAX_RETRIES: int = int(os.getenv("ELASTICSEARCH_MAX_RETRIES", "10"))
|
||||
|
||||
|
||||
# Xinference configuration
|
||||
XINFERENCE_URL: str = os.getenv("XINFERENCE_URL", "http://127.0.0.1")
|
||||
|
||||
@@ -78,43 +57,23 @@ class Settings:
|
||||
LANGCHAIN_TRACING: bool = os.getenv("LANGCHAIN_TRACING", "false").lower() == "true"
|
||||
LANGCHAIN_API_KEY: str = os.getenv("LANGCHAIN_API_KEY", "")
|
||||
LANGCHAIN_ENDPOINT: str = os.getenv("LANGCHAIN_ENDPOINT", "")
|
||||
|
||||
|
||||
# LLM Request Configuration
|
||||
LLM_TIMEOUT: float = float(os.getenv("LLM_TIMEOUT", "120.0"))
|
||||
LLM_MAX_RETRIES: int = int(os.getenv("LLM_MAX_RETRIES", "2"))
|
||||
|
||||
|
||||
# JWT Token Configuration
|
||||
SECRET_KEY: str = os.getenv("SECRET_KEY", "a_default_secret_key_that_is_long_and_random")
|
||||
ALGORITHM: str = "HS256"
|
||||
ACCESS_TOKEN_EXPIRE_MINUTES: int = int(os.getenv("ACCESS_TOKEN_EXPIRE_MINUTES", "30"))
|
||||
REFRESH_TOKEN_EXPIRE_DAYS: int = int(os.getenv("REFRESH_TOKEN_EXPIRE_DAYS", "7"))
|
||||
|
||||
|
||||
# Single Sign-On configuration
|
||||
ENABLE_SINGLE_SESSION: bool = os.getenv("ENABLE_SINGLE_SESSION", "false").lower() == "true"
|
||||
|
||||
# SSO 免登配置
|
||||
SSO_TOKEN_EXPIRE_SECONDS: int = int(os.getenv("SSO_TOKEN_EXPIRE_SECONDS", "300"))
|
||||
SSO_TRUSTED_SOURCES_CONFIG: str = os.getenv("SSO_TRUSTED_SOURCES_CONFIG", "{}")
|
||||
|
||||
# File Upload
|
||||
MAX_FILE_SIZE: int = int(os.getenv("MAX_FILE_SIZE", "52428800"))
|
||||
FILE_PATH: str = os.getenv("FILE_PATH", "/files")
|
||||
FILE_URL_EXPIRES: int = int(os.getenv("FILE_URL_EXPIRES", "3600"))
|
||||
|
||||
# Storage Configuration
|
||||
STORAGE_TYPE: str = os.getenv("STORAGE_TYPE", "local")
|
||||
|
||||
# Aliyun OSS Configuration
|
||||
OSS_ENDPOINT: str = os.getenv("OSS_ENDPOINT", "")
|
||||
OSS_ACCESS_KEY_ID: str = os.getenv("OSS_ACCESS_KEY_ID", "")
|
||||
OSS_ACCESS_KEY_SECRET: str = os.getenv("OSS_ACCESS_KEY_SECRET", "")
|
||||
OSS_BUCKET_NAME: str = os.getenv("OSS_BUCKET_NAME", "")
|
||||
|
||||
# AWS S3 Configuration
|
||||
S3_REGION: str = os.getenv("S3_REGION", "")
|
||||
S3_ACCESS_KEY_ID: str = os.getenv("S3_ACCESS_KEY_ID", "")
|
||||
S3_SECRET_ACCESS_KEY: str = os.getenv("S3_SECRET_ACCESS_KEY", "")
|
||||
S3_BUCKET_NAME: str = os.getenv("S3_BUCKET_NAME", "")
|
||||
|
||||
# VOLC ASR settings
|
||||
VOLC_APP_KEY: str = os.getenv("VOLC_APP_KEY", "")
|
||||
@@ -127,20 +86,19 @@ class Settings:
|
||||
LANGFUSE_PUBLIC_KEY: str = os.getenv("LANGFUSE_PUBLIC_KEY", "")
|
||||
LANGFUSE_SECRET_KEY: str = os.getenv("LANGFUSE_SECRET_KEY", "")
|
||||
LANGFUSE_HOST: str = os.getenv("LANGFUSE_HOST", "")
|
||||
|
||||
|
||||
# Server Configuration
|
||||
SERVER_IP: str = os.getenv("SERVER_IP", "127.0.0.1")
|
||||
FILE_LOCAL_SERVER_URL : str = os.getenv("FILE_LOCAL_SERVER_URL", "http://localhost:8000/api")
|
||||
|
||||
# ========================================================================
|
||||
# Internal Configuration (not in .env, used by application code)
|
||||
# ========================================================================
|
||||
|
||||
|
||||
# Superuser settings (internal defaults)
|
||||
FIRST_SUPERUSER_EMAIL: str = os.getenv("FIRST_SUPERUSER_EMAIL", "admin@example.com")
|
||||
FIRST_SUPERUSER_USERNAME: str = os.getenv("FIRST_SUPERUSER_USERNAME", "admin")
|
||||
FIRST_SUPERUSER_PASSWORD: str = os.getenv("FIRST_SUPERUSER_PASSWORD", "admin_password")
|
||||
|
||||
|
||||
# Generic File Upload (internal)
|
||||
GENERIC_FILE_PATH: str = os.getenv("GENERIC_FILE_PATH", "/uploads")
|
||||
ENABLE_FILE_COMPRESSION: bool = os.getenv("ENABLE_FILE_COMPRESSION", "false").lower() == "true"
|
||||
@@ -165,7 +123,7 @@ class Settings:
|
||||
LOG_BACKUP_COUNT: int = int(os.getenv("LOG_BACKUP_COUNT", "5"))
|
||||
LOG_TO_CONSOLE: bool = os.getenv("LOG_TO_CONSOLE", "true").lower() == "true"
|
||||
LOG_TO_FILE: bool = os.getenv("LOG_TO_FILE", "true").lower() == "true"
|
||||
|
||||
|
||||
# Sensitive Data Filtering
|
||||
ENABLE_SENSITIVE_DATA_FILTER: bool = os.getenv("ENABLE_SENSITIVE_DATA_FILTER", "true").lower() == "true"
|
||||
|
||||
@@ -184,35 +142,29 @@ class Settings:
|
||||
LOG_STREAM_BUFFER_SIZE: int = int(os.getenv("LOG_STREAM_BUFFER_SIZE", "8192")) # 8KB
|
||||
LOG_FILE_MAX_SIZE_MB: int = int(os.getenv("LOG_FILE_MAX_SIZE_MB", "10")) # 10MB
|
||||
|
||||
|
||||
# Celery configuration (internal)
|
||||
CELERY_BROKER: int = int(os.getenv("CELERY_BROKER", "1"))
|
||||
CELERY_BACKEND: int = int(os.getenv("CELERY_BACKEND", "2"))
|
||||
|
||||
REFLECTION_INTERVAL_SECONDS: float = float(os.getenv("REFLECTION_INTERVAL_SECONDS", "300"))
|
||||
HEALTH_CHECK_SECONDS: float = float(os.getenv("HEALTH_CHECK_SECONDS", "600"))
|
||||
MEMORY_INCREMENT_INTERVAL_HOURS: float = float(os.getenv("MEMORY_INCREMENT_INTERVAL_HOURS", "24"))
|
||||
DEFAULT_WORKSPACE_ID: Optional[str] = os.getenv("DEFAULT_WORKSPACE_ID", None)
|
||||
REFLECTION_INTERVAL_TIME: Optional[str] = int(os.getenv("REFLECTION_INTERVAL_TIME", 30))
|
||||
|
||||
REFLECTION_INTERVAL_TIME:Optional[str] = int(os.getenv("REFLECTION_INTERVAL_TIME", 30))
|
||||
|
||||
# Memory Cache Regeneration Configuration
|
||||
MEMORY_CACHE_REGENERATION_HOURS: int = int(os.getenv("MEMORY_CACHE_REGENERATION_HOURS", "24"))
|
||||
|
||||
# Memory Module Configuration (internal)
|
||||
MEMORY_OUTPUT_DIR: str = os.getenv("MEMORY_OUTPUT_DIR", "logs/memory-output")
|
||||
MEMORY_CONFIG_DIR: str = os.getenv("MEMORY_CONFIG_DIR", "app/core/memory")
|
||||
|
||||
|
||||
# Tool Management Configuration
|
||||
TOOL_CONFIG_DIR: str = os.getenv("TOOL_CONFIG_DIR", "app/core/tools")
|
||||
TOOL_EXECUTION_TIMEOUT: int = int(os.getenv("TOOL_EXECUTION_TIMEOUT", "60"))
|
||||
TOOL_MAX_CONCURRENCY: int = int(os.getenv("TOOL_MAX_CONCURRENCY", "10"))
|
||||
ENABLE_TOOL_MANAGEMENT: bool = os.getenv("ENABLE_TOOL_MANAGEMENT", "true").lower() == "true"
|
||||
|
||||
# official environment system version
|
||||
SYSTEM_VERSION: str = os.getenv("SYSTEM_VERSION", "v0.2.1")
|
||||
|
||||
# workflow config
|
||||
WORKFLOW_NODE_TIMEOUT: int = int(os.getenv("WORKFLOW_NODE_TIMEOUT", 600))
|
||||
|
||||
|
||||
def get_memory_output_path(self, filename: str = "") -> str:
|
||||
"""
|
||||
Get the full path for memory module output files.
|
||||
@@ -227,7 +179,7 @@ class Settings:
|
||||
if filename:
|
||||
return str(base_path / filename)
|
||||
return str(base_path)
|
||||
|
||||
|
||||
def ensure_memory_output_dir(self) -> None:
|
||||
"""
|
||||
Ensure the memory output directory exists.
|
||||
|
||||
@@ -82,13 +82,6 @@ class BizCode(IntEnum):
|
||||
MEMORY_WRITE_FAILED = 9501
|
||||
MEMORY_READ_FAILED = 9502
|
||||
MEMORY_CONFIG_NOT_FOUND = 9503
|
||||
|
||||
# Implicit Memory API（96xx）
|
||||
INVALID_USER_ID = 9601
|
||||
INSUFFICIENT_DATA = 9602
|
||||
INVALID_FILTER_PARAMS = 9603
|
||||
ANALYSIS_FAILED = 9604
|
||||
PROFILE_STORAGE_ERROR = 9605
|
||||
|
||||
# 系统（100xx）
|
||||
INTERNAL_ERROR = 10001
|
||||
@@ -110,24 +103,24 @@ HTTP_MAPPING = {
|
||||
BizCode.TOKEN_EXPIRED: 401,
|
||||
BizCode.TOKEN_BLACKLISTED: 401,
|
||||
BizCode.FORBIDDEN: 403,
|
||||
BizCode.TENANT_NOT_FOUND: 400,
|
||||
BizCode.TENANT_NOT_FOUND: 404,
|
||||
BizCode.WORKSPACE_NO_ACCESS: 403,
|
||||
BizCode.NOT_FOUND: 400,
|
||||
BizCode.NOT_FOUND: 404,
|
||||
BizCode.USER_NOT_FOUND: 200,
|
||||
BizCode.WORKSPACE_NOT_FOUND: 400,
|
||||
BizCode.MODEL_NOT_FOUND: 400,
|
||||
BizCode.KNOWLEDGE_NOT_FOUND: 400,
|
||||
BizCode.DOCUMENT_NOT_FOUND: 400,
|
||||
BizCode.FILE_NOT_FOUND: 400,
|
||||
BizCode.APP_NOT_FOUND: 400,
|
||||
BizCode.RELEASE_NOT_FOUND: 400,
|
||||
BizCode.WORKSPACE_NOT_FOUND: 404,
|
||||
BizCode.MODEL_NOT_FOUND: 404,
|
||||
BizCode.KNOWLEDGE_NOT_FOUND: 404,
|
||||
BizCode.DOCUMENT_NOT_FOUND: 404,
|
||||
BizCode.FILE_NOT_FOUND: 404,
|
||||
BizCode.APP_NOT_FOUND: 404,
|
||||
BizCode.RELEASE_NOT_FOUND: 404,
|
||||
BizCode.DUPLICATE_NAME: 409,
|
||||
BizCode.RESOURCE_ALREADY_EXISTS: 409,
|
||||
BizCode.VERSION_ALREADY_EXISTS: 409,
|
||||
BizCode.STATE_CONFLICT: 409,
|
||||
BizCode.PUBLISH_FAILED: 500,
|
||||
BizCode.NO_DRAFT_TO_PUBLISH: 400,
|
||||
BizCode.ROLLBACK_TARGET_NOT_FOUND: 400,
|
||||
BizCode.ROLLBACK_TARGET_NOT_FOUND: 404,
|
||||
BizCode.APP_TYPE_NOT_SUPPORTED: 400,
|
||||
BizCode.AGENT_CONFIG_MISSING: 400,
|
||||
BizCode.SHARE_DISABLED: 403,
|
||||
@@ -166,13 +159,6 @@ HTTP_MAPPING = {
|
||||
BizCode.MEMORY_READ_FAILED: 500,
|
||||
BizCode.MEMORY_CONFIG_NOT_FOUND: 400,
|
||||
|
||||
# Implicit Memory API 错误码映射
|
||||
BizCode.INVALID_USER_ID: 400,
|
||||
BizCode.INSUFFICIENT_DATA: 400,
|
||||
BizCode.INVALID_FILTER_PARAMS: 400,
|
||||
BizCode.ANALYSIS_FAILED: 500,
|
||||
BizCode.PROFILE_STORAGE_ERROR: 500,
|
||||
|
||||
BizCode.INTERNAL_ERROR: 500,
|
||||
BizCode.DB_ERROR: 500,
|
||||
BizCode.SERVICE_UNAVAILABLE: 503,
|
||||
|
||||
16
api/app/core/memory/agent/langgraph_graph/__init__.py
Normal file
16
api/app/core/memory/agent/langgraph_graph/__init__.py
Normal file
@@ -0,0 +1,16 @@
|
||||
"""
|
||||
LangGraph Graph package for memory agent.
|
||||
|
||||
This package provides the LangGraph workflow orchestrator with modular
|
||||
node implementations, routing logic, and state management.
|
||||
|
||||
Package structure:
|
||||
- read_graph: Main graph factory for read operations
|
||||
- write_graph: Main graph factory for write operations
|
||||
- nodes: LangGraph node implementations
|
||||
- routing: State routing logic
|
||||
- state: State management utilities
|
||||
"""
|
||||
from app.core.memory.agent.langgraph_graph.read_graph import make_read_graph
|
||||
|
||||
__all__ = ['make_read_graph']
|
||||
@@ -4,7 +4,7 @@ LangGraph node implementations.
|
||||
This module contains custom node implementations for the LangGraph workflow.
|
||||
"""
|
||||
|
||||
# from app.core.memory.agent.langgraph_graph.nodes.tool_node import ToolExecutionNode
|
||||
# from app.core.memory.agent.langgraph_graph.nodes.input_node import create_input_message
|
||||
#
|
||||
# __all__ = ["ToolExecutionNode", "create_input_message"]
|
||||
from app.core.memory.agent.langgraph_graph.nodes.tool_node import ToolExecutionNode
|
||||
from app.core.memory.agent.langgraph_graph.nodes.input_node import create_input_message
|
||||
|
||||
__all__ = ["ToolExecutionNode", "create_input_message"]
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
from app.core.memory.agent.utils.llm_tools import ReadState, WriteState
|
||||
|
||||
|
||||
def content_input_node(state: ReadState) -> ReadState:
|
||||
"""开始节点 - 提取内容并保持状态信息"""
|
||||
|
||||
content = state['messages'][0].content if state.get('messages') else ''
|
||||
# 返回内容并保持所有状态信息
|
||||
return {"data": content}
|
||||
|
||||
def content_input_write(state: WriteState) -> WriteState:
|
||||
"""开始节点 - 提取内容并保持状态信息"""
|
||||
|
||||
content = state['messages'][0].content if state.get('messages') else ''
|
||||
# 返回内容并保持所有状态信息
|
||||
return {"data": content}
|
||||
150
api/app/core/memory/agent/langgraph_graph/nodes/input_node.py
Normal file
150
api/app/core/memory/agent/langgraph_graph/nodes/input_node.py
Normal file
@@ -0,0 +1,150 @@
|
||||
"""
|
||||
Input node for LangGraph workflow entry point.
|
||||
|
||||
This module provides the create_input_message function which processes initial
|
||||
user input with multimodal support and creates the first tool call message.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import re
|
||||
import uuid
|
||||
from datetime import datetime
|
||||
from typing import Any, Dict
|
||||
|
||||
from app.core.memory.agent.utils.multimodal import MultimodalProcessor
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from langchain_core.messages import AIMessage
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
async def create_input_message(
|
||||
state: Dict[str, Any],
|
||||
tool_name: str,
|
||||
session_id: str,
|
||||
search_switch: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
multimodal_processor: MultimodalProcessor,
|
||||
memory_config: MemoryConfig,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Create initial tool call message from user input.
|
||||
|
||||
This function:
|
||||
1. Extracts the last message content from state
|
||||
2. Processes multimodal inputs (images/audio) using the multimodal processor
|
||||
3. Generates a unique message ID
|
||||
4. Extracts namespace from session_id
|
||||
5. Handles verified_data extraction for backward compatibility
|
||||
6. Returns AIMessage with complete tool_calls structure
|
||||
|
||||
Args:
|
||||
state: LangGraph state dictionary containing messages
|
||||
tool_name: Name of the tool to invoke (typically "Split_The_Problem")
|
||||
session_id: Session identifier (format: "call_id_{namespace}")
|
||||
search_switch: Search routing parameter
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
multimodal_processor: Processor for handling image/audio inputs
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
|
||||
Returns:
|
||||
State update with AIMessage containing tool_call
|
||||
|
||||
Examples:
|
||||
>>> state = {"messages": [HumanMessage(content="What is AI?")]}
|
||||
>>> result = await create_input_message(
|
||||
... state, "Split_The_Problem", "call_id_user123", "0", "app1", "group1", processor, config
|
||||
... )
|
||||
>>> result["messages"][0].tool_calls[0]["name"]
|
||||
'Split_The_Problem'
|
||||
"""
|
||||
messages = state.get("messages", [])
|
||||
|
||||
# Extract last message content
|
||||
if messages:
|
||||
last_message = messages[-1].content if hasattr(messages[-1], 'content') else str(messages[-1])
|
||||
else:
|
||||
logger.warning("[create_input_message] No messages in state, using empty string")
|
||||
last_message = ""
|
||||
|
||||
logger.debug(f"[create_input_message] Original input: {last_message[:100]}...")
|
||||
|
||||
# Process multimodal input (images/audio)
|
||||
try:
|
||||
processed_content = await multimodal_processor.process_input(last_message)
|
||||
if processed_content != last_message:
|
||||
logger.info(
|
||||
f"[create_input_message] Multimodal processing converted input "
|
||||
f"from {len(last_message)} to {len(processed_content)} chars"
|
||||
)
|
||||
last_message = processed_content
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"[create_input_message] Multimodal processing failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Continue with original content
|
||||
|
||||
# Generate unique message ID
|
||||
uuid_str = uuid.uuid4()
|
||||
time_str = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
|
||||
# Extract namespace from session_id
|
||||
# Expected format: "call_id_{namespace}" or similar
|
||||
try:
|
||||
namespace = str(session_id).split('_id_')[1]
|
||||
except (IndexError, AttributeError):
|
||||
logger.warning(
|
||||
f"[create_input_message] Could not extract namespace from session_id: {session_id}"
|
||||
)
|
||||
namespace = "unknown"
|
||||
|
||||
# Handle verified_data extraction (backward compatibility)
|
||||
# This regex-based extraction is kept for compatibility with existing data formats
|
||||
if 'verified_data' in str(last_message):
|
||||
try:
|
||||
messages_last = str(last_message).replace('\\n', '').replace('\\', '')
|
||||
query_match = re.findall(r'"query": "(.*?)",', messages_last)
|
||||
if query_match:
|
||||
last_message = query_match[0]
|
||||
logger.debug(
|
||||
f"[create_input_message] Extracted query from verified_data: {last_message}"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
f"[create_input_message] Failed to extract query from verified_data: {e}"
|
||||
)
|
||||
|
||||
# Construct tool call message
|
||||
tool_call_id = f"{session_id}_{uuid_str}"
|
||||
|
||||
logger.info(
|
||||
f"[create_input_message] Creating tool call for '{tool_name}' "
|
||||
f"with ID: {tool_call_id}"
|
||||
)
|
||||
|
||||
# Build tool arguments
|
||||
tool_args = {
|
||||
"sentence": last_message,
|
||||
"sessionid": session_id,
|
||||
"messages_id": str(uuid_str),
|
||||
"search_switch": search_switch,
|
||||
"apply_id": apply_id,
|
||||
"group_id": group_id,
|
||||
"memory_config": memory_config,
|
||||
}
|
||||
|
||||
return {
|
||||
"messages": [
|
||||
AIMessage(
|
||||
content="",
|
||||
tool_calls=[{
|
||||
"name": tool_name,
|
||||
"args": tool_args,
|
||||
"id": tool_call_id
|
||||
}]
|
||||
)
|
||||
]
|
||||
}
|
||||
@@ -1,249 +0,0 @@
|
||||
import os
|
||||
import json
|
||||
import time
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.db import get_db
|
||||
|
||||
from app.core.memory.agent.models.problem_models import ProblemExtensionResponse
|
||||
from app.core.memory.agent.utils.llm_tools import (
|
||||
PROJECT_ROOT_,
|
||||
ReadState,
|
||||
)
|
||||
from app.core.memory.agent.utils.redis_tool import store
|
||||
from app.core.memory.agent.utils.session_tools import SessionService
|
||||
from app.core.memory.agent.utils.template_tools import TemplateService
|
||||
from app.core.memory.agent.services.optimized_llm_service import LLMServiceMixin
|
||||
|
||||
template_root = os.path.join(PROJECT_ROOT_, 'memory', 'agent', 'utils', 'prompt')
|
||||
db_session = next(get_db())
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
class ProblemNodeService(LLMServiceMixin):
|
||||
"""问题处理节点服务类"""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.template_service = TemplateService(template_root)
|
||||
|
||||
|
||||
# 创建全局服务实例
|
||||
problem_service = ProblemNodeService()
|
||||
|
||||
|
||||
async def Split_The_Problem(state: ReadState) -> ReadState:
|
||||
"""问题分解节点"""
|
||||
# 从状态中获取数据
|
||||
content = state.get('data', '')
|
||||
end_user_id = state.get('end_user_id', '')
|
||||
memory_config = state.get('memory_config', None)
|
||||
|
||||
history = await SessionService(store).get_history(end_user_id, end_user_id, end_user_id)
|
||||
|
||||
# 生成 JSON schema 以指导 LLM 输出正确格式
|
||||
json_schema = ProblemExtensionResponse.model_json_schema()
|
||||
|
||||
system_prompt = await problem_service.template_service.render_template(
|
||||
template_name='problem_breakdown_prompt.jinja2',
|
||||
operation_name='split_the_problem',
|
||||
history=history,
|
||||
sentence=content,
|
||||
json_schema=json_schema
|
||||
)
|
||||
|
||||
try:
|
||||
# 使用优化的LLM服务
|
||||
structured = await problem_service.call_llm_structured(
|
||||
state=state,
|
||||
db_session=db_session,
|
||||
system_prompt=system_prompt,
|
||||
response_model=ProblemExtensionResponse,
|
||||
fallback_value=[]
|
||||
)
|
||||
|
||||
# 添加更详细的日志记录
|
||||
logger.info(f"Split_The_Problem: 开始处理问题分解，内容长度: {len(content)}")
|
||||
|
||||
# 验证结构化响应
|
||||
if not structured or not hasattr(structured, 'root'):
|
||||
logger.warning("Split_The_Problem: 结构化响应为空或格式不正确")
|
||||
split_result = json.dumps([], ensure_ascii=False)
|
||||
elif not structured.root:
|
||||
logger.warning("Split_The_Problem: 结构化响应的root为空")
|
||||
split_result = json.dumps([], ensure_ascii=False)
|
||||
else:
|
||||
split_result = json.dumps(
|
||||
[item.model_dump() for item in structured.root],
|
||||
ensure_ascii=False
|
||||
)
|
||||
|
||||
split_result_dict = []
|
||||
for index, item in enumerate(json.loads(split_result)):
|
||||
split_data = {
|
||||
"id": f"Q{index + 1}",
|
||||
"question": item['extended_question'],
|
||||
"type": item['type'],
|
||||
"reason": item['reason']
|
||||
}
|
||||
split_result_dict.append(split_data)
|
||||
|
||||
logger.info(f"Split_The_Problem: 成功生成 {len(structured.root) if structured.root else 0} 个分解项")
|
||||
|
||||
result = {
|
||||
"context": split_result,
|
||||
"original": content,
|
||||
"_intermediate": {
|
||||
"type": "problem_split",
|
||||
"title": "问题拆分",
|
||||
"data": split_result_dict,
|
||||
"original_query": content
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Split_The_Problem failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
|
||||
# 提供更详细的错误信息
|
||||
error_details = {
|
||||
"error_type": type(e).__name__,
|
||||
"error_message": str(e),
|
||||
"content_length": len(content),
|
||||
"llm_model_id": memory_config.llm_model_id if memory_config else None
|
||||
}
|
||||
|
||||
logger.error(f"Split_The_Problem error details: {error_details}")
|
||||
|
||||
# 创建默认的空结果
|
||||
result = {
|
||||
"context": json.dumps([], ensure_ascii=False),
|
||||
"original": content,
|
||||
"error": str(e),
|
||||
"_intermediate": {
|
||||
"type": "problem_split",
|
||||
"title": "问题拆分",
|
||||
"data": [],
|
||||
"original_query": content,
|
||||
"error": error_details
|
||||
}
|
||||
}
|
||||
|
||||
# 返回更新后的状态，包含spit_context字段
|
||||
return {"spit_data": result}
|
||||
|
||||
|
||||
async def Problem_Extension(state: ReadState) -> ReadState:
|
||||
"""问题扩展节点"""
|
||||
# 获取原始数据和分解结果
|
||||
start = time.time()
|
||||
content = state.get('data', '')
|
||||
data = state.get('spit_data', '')['context']
|
||||
end_user_id = state.get('end_user_id', '')
|
||||
storage_type = state.get('storage_type', '')
|
||||
user_rag_memory_id = state.get('user_rag_memory_id', '')
|
||||
memory_config = state.get('memory_config', None)
|
||||
|
||||
databasets = {}
|
||||
try:
|
||||
data = json.loads(data)
|
||||
for i in data:
|
||||
databasets[i['extended_question']] = i['type']
|
||||
except (json.JSONDecodeError, KeyError, TypeError) as e:
|
||||
logger.error(f"Problem_Extension: 数据解析失败: {e}")
|
||||
# 使用空字典作为fallback
|
||||
databasets = {}
|
||||
data = []
|
||||
|
||||
history = await SessionService(store).get_history(end_user_id, end_user_id, end_user_id)
|
||||
|
||||
# 生成 JSON schema 以指导 LLM 输出正确格式
|
||||
json_schema = ProblemExtensionResponse.model_json_schema()
|
||||
|
||||
system_prompt = await problem_service.template_service.render_template(
|
||||
template_name='Problem_Extension_prompt.jinja2',
|
||||
operation_name='problem_extension',
|
||||
history=history,
|
||||
questions=databasets,
|
||||
json_schema=json_schema
|
||||
)
|
||||
|
||||
try:
|
||||
# 使用优化的LLM服务
|
||||
response_content = await problem_service.call_llm_structured(
|
||||
state=state,
|
||||
db_session=db_session,
|
||||
system_prompt=system_prompt,
|
||||
response_model=ProblemExtensionResponse,
|
||||
fallback_value=[]
|
||||
)
|
||||
|
||||
logger.info(f"Problem_Extension: 开始处理问题扩展，问题数量: {len(databasets)}")
|
||||
|
||||
# 验证结构化响应
|
||||
if not response_content or not hasattr(response_content, 'root'):
|
||||
logger.warning("Problem_Extension: 结构化响应为空或格式不正确")
|
||||
aggregated_dict = {}
|
||||
elif not response_content.root:
|
||||
logger.warning("Problem_Extension: 结构化响应的root为空")
|
||||
aggregated_dict = {}
|
||||
else:
|
||||
# Aggregate results by original question
|
||||
aggregated_dict = {}
|
||||
for item in response_content.root:
|
||||
try:
|
||||
key = getattr(item, "original_question", None) or (
|
||||
item.get("original_question") if isinstance(item, dict) else None
|
||||
)
|
||||
value = getattr(item, "extended_question", None) or (
|
||||
item.get("extended_question") if isinstance(item, dict) else None
|
||||
)
|
||||
if not key or not value:
|
||||
logger.warning(f"Problem_Extension: 跳过无效项: key={key}, value={value}")
|
||||
continue
|
||||
aggregated_dict.setdefault(key, []).append(value)
|
||||
except Exception as item_error:
|
||||
logger.warning(f"Problem_Extension: 处理项目时出错: {item_error}")
|
||||
continue
|
||||
|
||||
logger.info(f"Problem_Extension: 成功生成 {len(aggregated_dict)} 个扩展问题组")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"LLM call failed for Problem_Extension: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
|
||||
# 提供更详细的错误信息
|
||||
error_details = {
|
||||
"error_type": type(e).__name__,
|
||||
"error_message": str(e),
|
||||
"questions_count": len(databasets),
|
||||
"llm_model_id": memory_config.llm_model_id if memory_config else None
|
||||
}
|
||||
|
||||
logger.error(f"Problem_Extension error details: {error_details}")
|
||||
aggregated_dict = {}
|
||||
|
||||
logger.info("Problem extension")
|
||||
logger.info(f"Problem extension result: {aggregated_dict}")
|
||||
|
||||
# Emit intermediate output for frontend
|
||||
print(time.time() - start)
|
||||
result = {
|
||||
"context": aggregated_dict,
|
||||
"original": data,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"_intermediate": {
|
||||
"type": "problem_extension",
|
||||
"title": "问题扩展",
|
||||
"data": aggregated_dict,
|
||||
"original_query": content,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
}
|
||||
|
||||
return {"problem_extension": result}
|
||||
@@ -1,417 +0,0 @@
|
||||
# ===== 标准库 =====
|
||||
import asyncio
|
||||
import json
|
||||
import os
|
||||
|
||||
# ===== 第三方库 =====
|
||||
from langchain.agents import create_agent
|
||||
from langchain_openai import ChatOpenAI
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.db import get_db, get_db_context
|
||||
|
||||
from app.schemas import model_schema
|
||||
from app.services.memory_config_service import MemoryConfigService
|
||||
from app.services.model_service import ModelConfigService
|
||||
|
||||
from app.core.memory.agent.services.search_service import SearchService
|
||||
from app.core.memory.agent.utils.llm_tools import (
|
||||
COUNTState,
|
||||
ReadState,
|
||||
deduplicate_entries,
|
||||
merge_to_key_value_pairs,
|
||||
)
|
||||
from app.core.memory.agent.langgraph_graph.tools.tool import (
|
||||
create_hybrid_retrieval_tool_sync,
|
||||
create_time_retrieval_tool,
|
||||
extract_tool_message_content,
|
||||
)
|
||||
|
||||
from app.core.rag.nlp.search import knowledge_retrieval
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
db = next(get_db())
|
||||
|
||||
|
||||
|
||||
async def rag_config(state):
|
||||
user_rag_memory_id = state.get('user_rag_memory_id', '')
|
||||
kb_config = {
|
||||
"knowledge_bases": [
|
||||
{
|
||||
"kb_id": user_rag_memory_id,
|
||||
"similarity_threshold": 0.7,
|
||||
"vector_similarity_weight": 0.5,
|
||||
"top_k": 10,
|
||||
"retrieve_type": "participle"
|
||||
}
|
||||
],
|
||||
"merge_strategy": "weight",
|
||||
"reranker_id": os.getenv('reranker_id'),
|
||||
"reranker_top_k": 10
|
||||
}
|
||||
return kb_config
|
||||
async def rag_knowledge(state,question):
|
||||
kb_config = await rag_config(state)
|
||||
end_user_id = state.get('end_user_id', '')
|
||||
user_rag_memory_id=state.get("user_rag_memory_id",'')
|
||||
retrieve_chunks_result = knowledge_retrieval(question, kb_config, [str(end_user_id)])
|
||||
try:
|
||||
retrieval_knowledge = [i.page_content for i in retrieve_chunks_result]
|
||||
clean_content = '\n\n'.join(retrieval_knowledge)
|
||||
cleaned_query = question
|
||||
raw_results = clean_content
|
||||
logger.info(f" Using RAG storage with memory_id={user_rag_memory_id}")
|
||||
except Exception :
|
||||
retrieval_knowledge=[]
|
||||
clean_content = ''
|
||||
raw_results = ''
|
||||
cleaned_query = question
|
||||
logger.info(f"No content retrieved from knowledge base: {user_rag_memory_id}")
|
||||
return retrieval_knowledge,clean_content,cleaned_query,raw_results
|
||||
|
||||
|
||||
async def llm_infomation(state: ReadState) -> ReadState:
|
||||
memory_config = state.get('memory_config', None)
|
||||
model_id = memory_config.llm_model_id
|
||||
tenant_id = memory_config.tenant_id
|
||||
|
||||
# 使用现有的 memory_config 而不是重新查询数据库
|
||||
# 或者使用线程安全的数据库访问
|
||||
with get_db_context() as db:
|
||||
result_orm = ModelConfigService.get_model_by_id(db=db, model_id=model_id, tenant_id=tenant_id)
|
||||
result_pydantic = model_schema.ModelConfig.model_validate(result_orm)
|
||||
return result_pydantic
|
||||
|
||||
|
||||
async def clean_databases(data) -> str:
|
||||
"""
|
||||
简化的数据库搜索结果清理函数
|
||||
|
||||
Args:
|
||||
data: 搜索结果数据
|
||||
|
||||
Returns:
|
||||
清理后的内容字符串
|
||||
"""
|
||||
try:
|
||||
# 解析JSON字符串
|
||||
if isinstance(data, str):
|
||||
try:
|
||||
data = json.loads(data)
|
||||
except json.JSONDecodeError:
|
||||
return data
|
||||
|
||||
if not isinstance(data, dict):
|
||||
return str(data)
|
||||
|
||||
# 获取结果数据
|
||||
# with open("搜索结果.json","w",encoding='utf-8') as f:
|
||||
# f.write(json.dumps(data, indent=4, ensure_ascii=False))
|
||||
results = data.get('results', data)
|
||||
if not isinstance(results, dict):
|
||||
return str(results)
|
||||
|
||||
# 收集所有内容
|
||||
content_list = []
|
||||
|
||||
# 处理重排序结果
|
||||
reranked = results.get('reranked_results', {})
|
||||
if reranked:
|
||||
for category in ['summaries', 'statements', 'chunks', 'entities']:
|
||||
items = reranked.get(category, [])
|
||||
if isinstance(items, list):
|
||||
content_list.extend(items)
|
||||
# 处理时间搜索结果
|
||||
time_search = results.get('time_search', {})
|
||||
if time_search:
|
||||
if isinstance(time_search, dict):
|
||||
statements = time_search.get('statements', time_search.get('time_search', []))
|
||||
if isinstance(statements, list):
|
||||
content_list.extend(statements)
|
||||
elif isinstance(time_search, list):
|
||||
content_list.extend(time_search)
|
||||
|
||||
# 提取文本内容
|
||||
text_parts = []
|
||||
for item in content_list:
|
||||
if isinstance(item, dict):
|
||||
text = item.get('statement') or item.get('content', '')
|
||||
if text:
|
||||
text_parts.append(text)
|
||||
elif isinstance(item, str):
|
||||
text_parts.append(item)
|
||||
|
||||
|
||||
return '\n'.join(text_parts).strip()
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"clean_databases failed: {e}", exc_info=True)
|
||||
return str(data)
|
||||
|
||||
|
||||
async def retrieve_nodes(state: ReadState) -> ReadState:
|
||||
|
||||
'''
|
||||
|
||||
模型信息
|
||||
'''
|
||||
|
||||
problem_extension=state.get('problem_extension', '')['context']
|
||||
storage_type=state.get('storage_type', '')
|
||||
user_rag_memory_id=state.get('user_rag_memory_id', '')
|
||||
end_user_id=state.get('end_user_id', '')
|
||||
memory_config = state.get('memory_config', None)
|
||||
original=state.get('data', '')
|
||||
problem_list=[]
|
||||
for key,values in problem_extension.items():
|
||||
for data in values:
|
||||
problem_list.append(data)
|
||||
logger.info(f"Retrieve: storage_type={storage_type}, user_rag_memory_id={user_rag_memory_id}")
|
||||
# 创建异步任务处理单个问题
|
||||
async def process_question_nodes(idx, question):
|
||||
try:
|
||||
# Prepare search parameters based on storage type
|
||||
search_params = {
|
||||
"end_user_id": end_user_id,
|
||||
"question": question,
|
||||
"return_raw_results": True
|
||||
}
|
||||
if storage_type == "rag" and user_rag_memory_id:
|
||||
retrieval_knowledge, clean_content, cleaned_query, raw_results = await rag_knowledge(state, question)
|
||||
else:
|
||||
clean_content, cleaned_query, raw_results = await SearchService().execute_hybrid_search(
|
||||
**search_params, memory_config=memory_config
|
||||
)
|
||||
|
||||
return {
|
||||
"Query_small": cleaned_query,
|
||||
"Result_small": clean_content,
|
||||
"_intermediate": {
|
||||
"type": "search_result",
|
||||
"query": cleaned_query,
|
||||
"raw_results": raw_results,
|
||||
"index": idx + 1,
|
||||
"total": len(problem_list)
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Retrieve: hybrid_search failed for question '{question}': {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Return empty result for this question
|
||||
return {
|
||||
"Query_small": question,
|
||||
"Result_small": "",
|
||||
"_intermediate": {
|
||||
"type": "search_result",
|
||||
"query": question,
|
||||
"raw_results": [],
|
||||
"index": idx + 1,
|
||||
"total": len(problem_list)
|
||||
}
|
||||
}
|
||||
|
||||
# 并发处理所有问题
|
||||
tasks = [process_question_nodes(idx, question) for idx, question in enumerate(problem_list)]
|
||||
databases_anser = await asyncio.gather(*tasks)
|
||||
databases_data = {
|
||||
"Query": original,
|
||||
"Expansion_issue": databases_anser
|
||||
}
|
||||
|
||||
# Collect intermediate outputs before deduplication
|
||||
intermediate_outputs = []
|
||||
for item in databases_anser:
|
||||
if '_intermediate' in item:
|
||||
intermediate_outputs.append(item['_intermediate'])
|
||||
|
||||
# Deduplicate and merge results
|
||||
deduplicated_data = deduplicate_entries(databases_data['Expansion_issue'])
|
||||
deduplicated_data_merged = merge_to_key_value_pairs(
|
||||
deduplicated_data,
|
||||
'Query_small',
|
||||
'Result_small'
|
||||
)
|
||||
|
||||
# Restructure for Verify/Retrieve_Summary compatibility
|
||||
keys, val = [], []
|
||||
for item in deduplicated_data_merged:
|
||||
for items_key, items_value in item.items():
|
||||
keys.append(items_key)
|
||||
val.append(items_value)
|
||||
|
||||
send_verify = []
|
||||
for i, j in zip(keys, val, strict=False):
|
||||
if j!=['']:
|
||||
send_verify.append({
|
||||
"Query_small": i,
|
||||
"Answer_Small": j
|
||||
})
|
||||
|
||||
dup_databases = {
|
||||
"Query": original,
|
||||
"Expansion_issue": send_verify,
|
||||
"_intermediate_outputs": intermediate_outputs # Preserve intermediate outputs
|
||||
}
|
||||
|
||||
logger.info(f"Collected {len(intermediate_outputs)} intermediate outputs from search results")
|
||||
return {'retrieve':dup_databases}
|
||||
|
||||
|
||||
|
||||
|
||||
async def retrieve(state: ReadState) -> ReadState:
|
||||
# 从state中获取end_user_id
|
||||
import time
|
||||
start=time.time()
|
||||
problem_extension = state.get('problem_extension', '')['context']
|
||||
storage_type = state.get('storage_type', '')
|
||||
user_rag_memory_id = state.get('user_rag_memory_id', '')
|
||||
end_user_id = state.get('end_user_id', '')
|
||||
memory_config = state.get('memory_config', None)
|
||||
original = state.get('data', '')
|
||||
problem_list = []
|
||||
for key, values in problem_extension.items():
|
||||
for data in values:
|
||||
problem_list.append(data)
|
||||
logger.info(f"Retrieve: storage_type={storage_type}, user_rag_memory_id={user_rag_memory_id}")
|
||||
databases_anser = []
|
||||
|
||||
async def get_llm_info():
|
||||
with get_db_context() as db: # 使用同步数据库上下文管理器
|
||||
config_service = MemoryConfigService(db)
|
||||
return await llm_infomation(state)
|
||||
llm_config = await get_llm_info()
|
||||
api_key_obj = llm_config.api_keys[0]
|
||||
api_key = api_key_obj.api_key
|
||||
api_base = api_key_obj.api_base
|
||||
model_name = api_key_obj.model_name
|
||||
llm = ChatOpenAI(
|
||||
model=model_name,
|
||||
api_key=api_key,
|
||||
base_url=api_base,
|
||||
temperature=0.2,
|
||||
)
|
||||
|
||||
time_retrieval_tool = create_time_retrieval_tool(end_user_id)
|
||||
search_params = { "end_user_id": end_user_id, "return_raw_results": True }
|
||||
hybrid_retrieval=create_hybrid_retrieval_tool_sync(memory_config, **search_params)
|
||||
agent = create_agent(
|
||||
llm,
|
||||
tools=[time_retrieval_tool,hybrid_retrieval],
|
||||
system_prompt=f"我是检索专家，可以根据适合的工具进行检索。当前使用的end_user_id是: {end_user_id}"
|
||||
)
|
||||
|
||||
# 创建异步任务处理单个问题
|
||||
import asyncio
|
||||
|
||||
# 在模块级别定义信号量，限制最大并发数
|
||||
SEMAPHORE = asyncio.Semaphore(5) # 限制最多5个并发数据库操作
|
||||
|
||||
async def process_question(idx, question):
|
||||
async with SEMAPHORE: # 限制并发
|
||||
try:
|
||||
if storage_type == "rag" and user_rag_memory_id:
|
||||
retrieval_knowledge, clean_content, cleaned_query, raw_results = await rag_knowledge(state, question)
|
||||
else:
|
||||
cleaned_query = question
|
||||
# 使用 asyncio 在线程池中运行同步的 agent.invoke
|
||||
import asyncio
|
||||
response = await asyncio.get_event_loop().run_in_executor(
|
||||
None,
|
||||
lambda: agent.invoke({"messages": question})
|
||||
)
|
||||
tool_results = extract_tool_message_content(response)
|
||||
if tool_results == None:
|
||||
raw_results = []
|
||||
clean_content = ''
|
||||
else:
|
||||
raw_results = tool_results['content']
|
||||
clean_content = await clean_databases(raw_results)
|
||||
|
||||
try:
|
||||
raw_results = raw_results['results']
|
||||
except Exception:
|
||||
raw_results = []
|
||||
|
||||
return {
|
||||
"Query_small": cleaned_query,
|
||||
"Result_small": clean_content,
|
||||
"_intermediate": {
|
||||
"type": "search_result",
|
||||
"query": cleaned_query,
|
||||
"raw_results": raw_results,
|
||||
"index": idx + 1,
|
||||
"total": len(problem_list)
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Retrieve: hybrid_search failed for question '{question}': {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Return empty result for this question
|
||||
return {
|
||||
"Query_small": question,
|
||||
"Result_small": "",
|
||||
"_intermediate": {
|
||||
"type": "search_result",
|
||||
"query": question,
|
||||
"raw_results": [],
|
||||
"index": idx + 1,
|
||||
"total": len(problem_list)
|
||||
}
|
||||
}
|
||||
|
||||
# 并发处理所有问题
|
||||
import asyncio
|
||||
tasks = [process_question(idx, question) for idx, question in enumerate(problem_list)]
|
||||
databases_anser = await asyncio.gather(*tasks)
|
||||
databases_data = {
|
||||
"Query": original,
|
||||
"Expansion_issue": databases_anser
|
||||
}
|
||||
|
||||
# Collect intermediate outputs before deduplication
|
||||
intermediate_outputs = []
|
||||
for item in databases_anser:
|
||||
if '_intermediate' in item:
|
||||
intermediate_outputs.append(item['_intermediate'])
|
||||
|
||||
# Deduplicate and merge results
|
||||
deduplicated_data = deduplicate_entries(databases_data['Expansion_issue'])
|
||||
deduplicated_data_merged = merge_to_key_value_pairs(
|
||||
deduplicated_data,
|
||||
'Query_small',
|
||||
'Result_small'
|
||||
)
|
||||
|
||||
# Restructure for Verify/Retrieve_Summary compatibility
|
||||
keys, val = [], []
|
||||
for item in deduplicated_data_merged:
|
||||
for items_key, items_value in item.items():
|
||||
keys.append(items_key)
|
||||
val.append(items_value)
|
||||
|
||||
send_verify = []
|
||||
for i, j in zip(keys, val, strict=False):
|
||||
if j != ['']:
|
||||
send_verify.append({
|
||||
"Query_small": i,
|
||||
"Answer_Small": j
|
||||
})
|
||||
|
||||
dup_databases = {
|
||||
"Query": original,
|
||||
"Expansion_issue": send_verify,
|
||||
"_intermediate_outputs": intermediate_outputs # Preserve intermediate outputs
|
||||
}
|
||||
# with open('retrieve_text.json', 'w') as f:
|
||||
# json.dump(dup_databases, f, indent=4)
|
||||
logger.info(f"Collected {len(intermediate_outputs)} intermediate outputs from search results")
|
||||
return {'retrieve': dup_databases}
|
||||
|
||||
|
||||
@@ -1,320 +0,0 @@
|
||||
|
||||
|
||||
import os
|
||||
import time
|
||||
|
||||
from app.core.logging_config import get_agent_logger, log_time
|
||||
from app.core.memory.agent.models.summary_models import (
|
||||
RetrieveSummaryResponse,
|
||||
SummaryResponse,
|
||||
)
|
||||
from app.core.memory.agent.services.optimized_llm_service import LLMServiceMixin
|
||||
from app.core.memory.agent.services.search_service import SearchService
|
||||
from app.core.memory.agent.utils.llm_tools import (
|
||||
PROJECT_ROOT_,
|
||||
ReadState,
|
||||
)
|
||||
from app.core.memory.agent.utils.redis_tool import store
|
||||
from app.core.memory.agent.utils.session_tools import SessionService
|
||||
from app.core.memory.agent.utils.template_tools import TemplateService
|
||||
from app.db import get_db
|
||||
|
||||
template_root = os.path.join(PROJECT_ROOT_, 'memory', 'agent', 'utils', 'prompt')
|
||||
logger = get_agent_logger(__name__)
|
||||
db_session = next(get_db())
|
||||
|
||||
class SummaryNodeService(LLMServiceMixin):
|
||||
"""总结节点服务类"""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.template_service = TemplateService(template_root)
|
||||
|
||||
# 创建全局服务实例
|
||||
summary_service = SummaryNodeService()
|
||||
|
||||
async def summary_history(state: ReadState) -> ReadState:
|
||||
end_user_id = state.get("end_user_id", '')
|
||||
history = await SessionService(store).get_history(end_user_id, end_user_id, end_user_id)
|
||||
return history
|
||||
|
||||
async def summary_llm(state: ReadState, history, retrieve_info, template_name, operation_name, response_model,search_mode) -> str:
|
||||
"""
|
||||
增强的summary_llm函数，包含更好的错误处理和数据验证
|
||||
"""
|
||||
data = state.get("data", '')
|
||||
|
||||
# 构建系统提示词
|
||||
if str(search_mode) == "0":
|
||||
system_prompt = await summary_service.template_service.render_template(
|
||||
template_name=template_name,
|
||||
operation_name=operation_name,
|
||||
data=retrieve_info,
|
||||
query=data
|
||||
)
|
||||
else:
|
||||
system_prompt = await summary_service.template_service.render_template(
|
||||
template_name=template_name,
|
||||
operation_name=operation_name,
|
||||
query=data,
|
||||
history=history,
|
||||
retrieve_info=retrieve_info
|
||||
)
|
||||
try:
|
||||
# 使用优化的LLM服务进行结构化输出
|
||||
structured = await summary_service.call_llm_structured(
|
||||
state=state,
|
||||
db_session=db_session,
|
||||
system_prompt=system_prompt,
|
||||
response_model=response_model,
|
||||
fallback_value=None
|
||||
)
|
||||
# 验证结构化响应
|
||||
if structured is None:
|
||||
logger.warning(f"LLM返回None，使用默认回答")
|
||||
return "信息不足，无法回答"
|
||||
|
||||
# 根据操作类型提取答案
|
||||
if operation_name == "summary":
|
||||
aimessages = getattr(structured, 'query_answer', None) or "信息不足，无法回答"
|
||||
else:
|
||||
# 处理RetrieveSummaryResponse
|
||||
if hasattr(structured, 'data') and structured.data:
|
||||
aimessages = getattr(structured.data, 'query_answer', None) or "信息不足，无法回答"
|
||||
else:
|
||||
logger.warning(f"结构化响应缺少data字段")
|
||||
aimessages = "信息不足，无法回答"
|
||||
|
||||
# 验证答案不为空
|
||||
if not aimessages or aimessages.strip() == "":
|
||||
aimessages = "信息不足，无法回答"
|
||||
|
||||
return aimessages
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"结构化输出失败: {e}", exc_info=True)
|
||||
|
||||
# 尝试非结构化输出作为fallback
|
||||
try:
|
||||
logger.info("尝试非结构化输出作为fallback")
|
||||
response = await summary_service.call_llm_simple(
|
||||
state=state,
|
||||
db_session=db_session,
|
||||
system_prompt=system_prompt,
|
||||
fallback_message="信息不足，无法回答"
|
||||
)
|
||||
|
||||
if response and response.strip():
|
||||
# 简单清理响应
|
||||
cleaned_response = response.strip()
|
||||
# 移除可能的JSON标记
|
||||
if cleaned_response.startswith('```'):
|
||||
lines = cleaned_response.split('\n')
|
||||
cleaned_response = '\n'.join(lines[1:-1])
|
||||
|
||||
return cleaned_response
|
||||
else:
|
||||
return "信息不足，无法回答"
|
||||
|
||||
except Exception as fallback_error:
|
||||
logger.error(f"Fallback也失败: {fallback_error}")
|
||||
return "信息不足，无法回答"
|
||||
|
||||
async def summary_redis_save(state: ReadState,aimessages) -> ReadState:
|
||||
data = state.get("data", '')
|
||||
end_user_id = state.get("end_user_id", '')
|
||||
await SessionService(store).save_session(
|
||||
user_id=end_user_id,
|
||||
query=data,
|
||||
apply_id=end_user_id,
|
||||
end_user_id=end_user_id,
|
||||
ai_response=aimessages
|
||||
)
|
||||
await SessionService(store).cleanup_duplicates()
|
||||
logger.info(f"sessionid: {aimessages} 写入成功")
|
||||
async def summary_prompt(state: ReadState,aimessages,raw_results) -> ReadState:
|
||||
storage_type=state.get("storage_type",'')
|
||||
user_rag_memory_id=state.get("user_rag_memory_id",'')
|
||||
data=state.get("data", '')
|
||||
input_summary = {
|
||||
"status": "success",
|
||||
"summary_result": aimessages,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"_intermediate": {
|
||||
"type": "input_summary",
|
||||
"title": "快速答案",
|
||||
"summary": aimessages,
|
||||
"query": data,
|
||||
"raw_results": raw_results,
|
||||
"search_mode": "quick_search",
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
}
|
||||
retrieve={
|
||||
"status": "success",
|
||||
"summary_result": aimessages,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"_intermediate": {
|
||||
"type": "retrieval_summary",
|
||||
"title":"快速检索",
|
||||
"summary": aimessages,
|
||||
"query": data,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
}
|
||||
|
||||
return input_summary,retrieve
|
||||
|
||||
async def Input_Summary(state: ReadState) -> ReadState:
|
||||
start=time.time()
|
||||
storage_type=state.get("storage_type",'')
|
||||
memory_config = state.get('memory_config', None)
|
||||
user_rag_memory_id=state.get("user_rag_memory_id",'')
|
||||
data=state.get("data", '')
|
||||
end_user_id=state.get("end_user_id", '')
|
||||
logger.info(f"Input_Summary: storage_type={storage_type}, user_rag_memory_id={user_rag_memory_id}")
|
||||
history = await summary_history( state)
|
||||
search_params = {
|
||||
"end_user_id": end_user_id,
|
||||
"question": data,
|
||||
"return_raw_results": True,
|
||||
"include": ["summaries"] # Only search summary nodes for faster performance
|
||||
}
|
||||
|
||||
try:
|
||||
retrieve_info, question, raw_results = await SearchService().execute_hybrid_search(**search_params, memory_config=memory_config)
|
||||
except Exception as e:
|
||||
logger.error( f"Input_Summary: hybrid_search failed, using empty results: {e}", exc_info=True )
|
||||
retrieve_info, question, raw_results = "", data, []
|
||||
|
||||
|
||||
try:
|
||||
# aimessages=await summary_llm(state,history,retrieve_info,'Retrieve_Summary_prompt.jinja2',
|
||||
# 'input_summary',RetrieveSummaryResponse)
|
||||
# logger.info(f"快速答案总结==>>:{storage_type}--{user_rag_memory_id}--{aimessages}")
|
||||
summary_result = await summary_prompt(state, retrieve_info, retrieve_info)
|
||||
summary = summary_result[0]
|
||||
except Exception as e:
|
||||
logger.error( f"Input_Summary failed: {e}", exc_info=True )
|
||||
summary= {
|
||||
"status": "fail",
|
||||
"summary_result": "信息不足，无法回答",
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"error": str(e)
|
||||
}
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('检索', duration)
|
||||
return {"summary":summary}
|
||||
|
||||
async def Retrieve_Summary(state: ReadState)-> ReadState:
|
||||
retrieve=state.get("retrieve", '')
|
||||
history = await summary_history( state)
|
||||
import json
|
||||
with open("检索.json","w",encoding='utf-8') as f:
|
||||
f.write(json.dumps(retrieve, indent=4, ensure_ascii=False))
|
||||
retrieve=retrieve.get("Expansion_issue", [])
|
||||
start=time.time()
|
||||
retrieve_info_str=[]
|
||||
for data in retrieve:
|
||||
if data=='':
|
||||
retrieve_info_str=''
|
||||
else:
|
||||
for key, value in data.items():
|
||||
if key=='Answer_Small':
|
||||
for i in value:
|
||||
retrieve_info_str.append(i)
|
||||
retrieve_info_str=list(set(retrieve_info_str))
|
||||
retrieve_info_str='\n'.join(retrieve_info_str)
|
||||
|
||||
aimessages=await summary_llm(state,history,retrieve_info_str,
|
||||
'direct_summary_prompt.jinja2','retrieve_summary',RetrieveSummaryResponse,"1")
|
||||
if '信息不足，无法回答' not in str(aimessages) or str(aimessages) != "":
|
||||
await summary_redis_save(state, aimessages)
|
||||
if aimessages == '':
|
||||
aimessages = '信息不足，无法回答'
|
||||
logger.info(f"Summary after retrieval: {aimessages}")
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Retrieval summary', duration)
|
||||
|
||||
# 修复协程调用 - 先await，然后访问返回值
|
||||
summary_result = await summary_prompt(state, aimessages, retrieve_info_str)
|
||||
summary = summary_result[1]
|
||||
return {"summary":summary}
|
||||
|
||||
|
||||
async def Summary(state: ReadState)-> ReadState:
|
||||
start=time.time()
|
||||
query = state.get("data", '')
|
||||
verify=state.get("verify", '')
|
||||
verify_expansion_issue=verify.get("verified_data", '')
|
||||
retrieve_info_str=''
|
||||
for data in verify_expansion_issue:
|
||||
for key, value in data.items():
|
||||
if key=='answer_small':
|
||||
for i in value:
|
||||
retrieve_info_str+=i+'\n'
|
||||
history=await summary_history(state)
|
||||
|
||||
data = {
|
||||
"query": query,
|
||||
"history": history,
|
||||
"retrieve_info": retrieve_info_str
|
||||
}
|
||||
aimessages=await summary_llm(state,history,data,
|
||||
'summary_prompt.jinja2','summary',SummaryResponse,0)
|
||||
|
||||
if '信息不足，无法回答' not in str(aimessages) or str(aimessages) != "":
|
||||
await summary_redis_save(state, aimessages)
|
||||
if aimessages == '':
|
||||
aimessages = '信息不足，无法回答'
|
||||
try:
|
||||
duration = time.time() - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Retrieval summary', duration)
|
||||
|
||||
# 修复协程调用 - 先await，然后访问返回值
|
||||
summary_result = await summary_prompt(state, aimessages, retrieve_info_str)
|
||||
summary = summary_result[1]
|
||||
return {"summary":summary}
|
||||
|
||||
async def Summary_fails(state: ReadState)-> ReadState:
|
||||
storage_type=state.get("storage_type", '')
|
||||
user_rag_memory_id=state.get("user_rag_memory_id", '')
|
||||
history = await summary_history(state)
|
||||
query = state.get("data", '')
|
||||
verify = state.get("verify", '')
|
||||
verify_expansion_issue = verify.get("verified_data", '')
|
||||
retrieve_info_str = ''
|
||||
for data in verify_expansion_issue:
|
||||
for key, value in data.items():
|
||||
if key == 'answer_small':
|
||||
for i in value:
|
||||
retrieve_info_str += i + '\n'
|
||||
data = {
|
||||
"query": query,
|
||||
"history": history,
|
||||
"retrieve_info": retrieve_info_str
|
||||
}
|
||||
aimessages = await summary_llm(state, history, data,
|
||||
'fail_summary_prompt.jinja2', 'summary', SummaryResponse, 0)
|
||||
result= {
|
||||
"status": "success",
|
||||
"summary_result": aimessages,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
return {"summary":result}
|
||||
234
api/app/core/memory/agent/langgraph_graph/nodes/tool_node.py
Normal file
234
api/app/core/memory/agent/langgraph_graph/nodes/tool_node.py
Normal file
@@ -0,0 +1,234 @@
|
||||
"""
|
||||
Tool execution node for LangGraph workflow.
|
||||
|
||||
This module provides the ToolExecutionNode class which wraps tool execution
|
||||
with parameter transformation logic using the ParameterBuilder service.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import time
|
||||
from typing import Any, Callable, Dict
|
||||
|
||||
from app.core.memory.agent.langgraph_graph.state.extractors import (
|
||||
extract_content_payload,
|
||||
extract_tool_call_id,
|
||||
)
|
||||
from app.core.memory.agent.mcp_server.services.parameter_builder import ParameterBuilder
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from langchain_core.messages import AIMessage
|
||||
from langgraph.prebuilt import ToolNode
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ToolExecutionNode:
|
||||
"""
|
||||
Custom LangGraph node that wraps tool execution with parameter transformation.
|
||||
|
||||
This node extracts content from previous tool results, transforms parameters
|
||||
based on tool type using ParameterBuilder, and invokes the tool with the
|
||||
correct argument structure.
|
||||
|
||||
Attributes:
|
||||
tool_node: LangGraph ToolNode wrapping the actual tool
|
||||
id: Node identifier for message IDs
|
||||
tool_name: Name of the tool being executed
|
||||
namespace: Namespace for session management
|
||||
search_switch: Search routing parameter
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
parameter_builder: Service for building tool-specific arguments
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
tool: Callable,
|
||||
node_id: str,
|
||||
namespace: str,
|
||||
search_switch: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
parameter_builder: ParameterBuilder,
|
||||
storage_type: str,
|
||||
user_rag_memory_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
):
|
||||
"""
|
||||
Initialize the tool execution node.
|
||||
|
||||
Args:
|
||||
tool: The tool function to execute
|
||||
node_id: Identifier for this node (used in message IDs)
|
||||
namespace: Namespace for session management
|
||||
search_switch: Search routing parameter
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
parameter_builder: Service for building tool-specific arguments
|
||||
storage_type: Storage type for the workspace
|
||||
user_rag_memory_id: User RAG memory identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
"""
|
||||
self.tool_node = ToolNode([tool])
|
||||
self.id = node_id
|
||||
self.tool_name = tool.name if hasattr(tool, 'name') else str(tool)
|
||||
self.namespace = namespace
|
||||
self.search_switch = search_switch
|
||||
self.apply_id = apply_id
|
||||
self.group_id = group_id
|
||||
self.parameter_builder = parameter_builder
|
||||
self.storage_type = storage_type
|
||||
self.user_rag_memory_id = user_rag_memory_id
|
||||
self.memory_config = memory_config
|
||||
|
||||
logger.info(
|
||||
f"[ToolExecutionNode] Initialized node '{self.id}' for tool '{self.tool_name}'"
|
||||
)
|
||||
|
||||
async def __call__(self, state: Dict[str, Any]) -> Dict[str, Any]:
|
||||
"""
|
||||
Execute the tool with transformed parameters.
|
||||
|
||||
This method:
|
||||
1. Extracts the last message from state
|
||||
2. Extracts tool call ID using state extractors
|
||||
3. Extracts content payload using state extractors
|
||||
4. Builds tool arguments using parameter builder
|
||||
5. Constructs AIMessage with tool_calls
|
||||
6. Invokes the tool and returns the result
|
||||
|
||||
Args:
|
||||
state: LangGraph state dictionary
|
||||
|
||||
Returns:
|
||||
Updated state with tool result in messages
|
||||
"""
|
||||
messages = state.get("messages", [])
|
||||
logger.debug( self.tool_name)
|
||||
|
||||
if not messages:
|
||||
logger.warning(f"[ToolExecutionNode] {self.id} - No messages in state")
|
||||
return {"messages": [AIMessage(content="Error: No messages in state")]}
|
||||
|
||||
last_message = messages[-1]
|
||||
logger.debug(
|
||||
f"[ToolExecutionNode] {self.id} - Processing message at {time.time()}"
|
||||
)
|
||||
|
||||
try:
|
||||
# Extract tool call ID using state extractors
|
||||
tool_call_id = extract_tool_call_id(last_message)
|
||||
logger.debug(f"[ToolExecutionNode] {self.id} - Extracted tool_call_id: {tool_call_id}")
|
||||
|
||||
except ValueError as e:
|
||||
logger.error(
|
||||
f"[ToolExecutionNode] {self.id} - Failed to extract tool call ID: {e}"
|
||||
)
|
||||
return {"messages": [AIMessage(content=f"Error: {str(e)}")]}
|
||||
|
||||
try:
|
||||
# Extract content payload using state extractors
|
||||
content = extract_content_payload(last_message)
|
||||
logger.debug(
|
||||
f"[ToolExecutionNode] {self.id} - Extracted content type: {type(content)}, content_keys: {list(content.keys()) if isinstance(content, dict) else 'N/A'}"
|
||||
)
|
||||
# Log raw message content for debugging
|
||||
if hasattr(last_message, 'content'):
|
||||
raw = last_message.content
|
||||
logger.debug(f"[ToolExecutionNode] {self.id} - Raw message content (first 500 chars): {str(raw)[:500]}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"[ToolExecutionNode] {self.id} - Failed to extract content: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
content = {}
|
||||
|
||||
try:
|
||||
# Build tool arguments using parameter builder
|
||||
tool_args = self.parameter_builder.build_tool_args(
|
||||
tool_name=self.tool_name,
|
||||
content=content,
|
||||
tool_call_id=tool_call_id,
|
||||
search_switch=self.search_switch,
|
||||
apply_id=self.apply_id,
|
||||
group_id=self.group_id,
|
||||
memory_config=self.memory_config,
|
||||
storage_type=self.storage_type,
|
||||
user_rag_memory_id=self.user_rag_memory_id,
|
||||
)
|
||||
logger.debug(
|
||||
f"[ToolExecutionNode] {self.id} - Built tool args with keys: {list(tool_args.keys())}"
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"[ToolExecutionNode] {self.id} - Failed to build tool args: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {"messages": [AIMessage(content=f"Error building arguments: {str(e)}")]}
|
||||
|
||||
# Construct tool input message
|
||||
tool_input = {
|
||||
"messages": [
|
||||
AIMessage(
|
||||
content="",
|
||||
tool_calls=[{
|
||||
"name": self.tool_name,
|
||||
"args": tool_args,
|
||||
"id": f"{self.id}_{tool_call_id}",
|
||||
}]
|
||||
)
|
||||
]
|
||||
}
|
||||
|
||||
try:
|
||||
# Invoke the tool
|
||||
result = await self.tool_node.ainvoke(tool_input)
|
||||
|
||||
logger.debug(
|
||||
f"[ToolExecutionNode] {self.id} - Tool execution completed"
|
||||
)
|
||||
|
||||
# Check for error in tool response
|
||||
error_entry = None
|
||||
if result and "messages" in result:
|
||||
for msg in result["messages"]:
|
||||
if hasattr(msg, 'content'):
|
||||
try:
|
||||
import json
|
||||
content = msg.content
|
||||
if isinstance(content, str):
|
||||
parsed = json.loads(content)
|
||||
if isinstance(parsed, dict) and "error" in parsed:
|
||||
error_msg = parsed["error"]
|
||||
logger.warning(
|
||||
f"[ToolExecutionNode] {self.id} - Tool returned error: {error_msg}"
|
||||
)
|
||||
error_entry = {"tool": self.tool_name, "error": error_msg, "node_id": self.id}
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
pass
|
||||
|
||||
# Return result with error tracking if error was found
|
||||
if error_entry:
|
||||
result["errors"] = [error_entry]
|
||||
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"[ToolExecutionNode] {self.id} - Tool execution failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Track error in state and return error message
|
||||
from langchain_core.messages import ToolMessage
|
||||
error_entry = {"tool": self.tool_name, "error": str(e), "node_id": self.id}
|
||||
return {
|
||||
"messages": [
|
||||
ToolMessage(
|
||||
content=f"Error executing tool: {str(e)}",
|
||||
tool_call_id=f"{self.id}_{tool_call_id}"
|
||||
)
|
||||
],
|
||||
"errors": [error_entry]
|
||||
}
|
||||
@@ -1,155 +0,0 @@
|
||||
import os
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.db import get_db
|
||||
|
||||
from app.core.memory.agent.models.verification_models import VerificationResult
|
||||
from app.core.memory.agent.utils.llm_tools import (
|
||||
PROJECT_ROOT_,
|
||||
ReadState,
|
||||
)
|
||||
from app.core.memory.agent.utils.redis_tool import store
|
||||
from app.core.memory.agent.utils.session_tools import SessionService
|
||||
from app.core.memory.agent.utils.template_tools import TemplateService
|
||||
from app.core.memory.agent.services.optimized_llm_service import LLMServiceMixin
|
||||
|
||||
template_root = os.path.join(PROJECT_ROOT_, 'memory', 'agent', 'utils', 'prompt')
|
||||
db_session = next(get_db())
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
class VerificationNodeService(LLMServiceMixin):
|
||||
"""验证节点服务类"""
|
||||
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.template_service = TemplateService(template_root)
|
||||
|
||||
# 创建全局服务实例
|
||||
verification_service = VerificationNodeService()
|
||||
|
||||
async def Verify_prompt(state: ReadState, messages_deal: VerificationResult):
|
||||
"""处理验证结果并生成输出格式"""
|
||||
storage_type = state.get('storage_type', '')
|
||||
user_rag_memory_id = state.get('user_rag_memory_id', '')
|
||||
data = state.get('data', '')
|
||||
|
||||
# 将 VerificationItem 对象转换为字典列表
|
||||
verified_data = []
|
||||
if messages_deal.expansion_issue:
|
||||
for item in messages_deal.expansion_issue:
|
||||
if hasattr(item, 'model_dump'):
|
||||
verified_data.append(item.model_dump())
|
||||
elif isinstance(item, dict):
|
||||
verified_data.append(item)
|
||||
|
||||
Verify_result = {
|
||||
"status": messages_deal.split_result,
|
||||
"verified_data": verified_data,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"_intermediate": {
|
||||
"type": "verification",
|
||||
"title": "Data Verification",
|
||||
"result": messages_deal.split_result,
|
||||
"reason": messages_deal.reason or "验证完成",
|
||||
"query": messages_deal.query,
|
||||
"verified_count": len(verified_data),
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
}
|
||||
return Verify_result
|
||||
async def Verify(state: ReadState):
|
||||
logger.info("=== Verify 节点开始执行 ===")
|
||||
try:
|
||||
content = state.get('data', '')
|
||||
end_user_id = state.get('end_user_id', '')
|
||||
memory_config = state.get('memory_config', None)
|
||||
|
||||
logger.info(f"Verify: content={content[:50] if content else 'empty'}..., end_user_id={end_user_id}")
|
||||
|
||||
history = await SessionService(store).get_history(end_user_id, end_user_id, end_user_id)
|
||||
logger.info(f"Verify: 获取历史记录完成，history length={len(history)}")
|
||||
|
||||
retrieve = state.get("retrieve", {})
|
||||
logger.info(f"Verify: retrieve data type={type(retrieve)}, keys={retrieve.keys() if isinstance(retrieve, dict) else 'N/A'}")
|
||||
|
||||
retrieve_expansion = retrieve.get("Expansion_issue", []) if isinstance(retrieve, dict) else []
|
||||
logger.info(f"Verify: Expansion_issue length={len(retrieve_expansion)}")
|
||||
|
||||
messages = {
|
||||
"Query": content,
|
||||
"Expansion_issue": retrieve_expansion
|
||||
}
|
||||
|
||||
logger.info("Verify: 开始渲染模板")
|
||||
|
||||
# 生成 JSON schema 以指导 LLM 输出正确格式
|
||||
json_schema = VerificationResult.model_json_schema()
|
||||
|
||||
system_prompt = await verification_service.template_service.render_template(
|
||||
template_name='split_verify_prompt.jinja2',
|
||||
operation_name='split_verify_prompt',
|
||||
history=history,
|
||||
sentence=messages,
|
||||
json_schema=json_schema
|
||||
)
|
||||
logger.info(f"Verify: 模板渲染完成，prompt length={len(system_prompt)}")
|
||||
|
||||
# 使用优化的LLM服务，添加超时保护
|
||||
logger.info("Verify: 开始调用 LLM")
|
||||
try:
|
||||
# 添加 asyncio.wait_for 超时包裹，防止无限等待
|
||||
# 超时时间设置为 150 秒（比 LLM 配置的 120 秒稍长）
|
||||
import asyncio
|
||||
structured = await asyncio.wait_for(
|
||||
verification_service.call_llm_structured(
|
||||
state=state,
|
||||
db_session=db_session,
|
||||
system_prompt=system_prompt,
|
||||
response_model=VerificationResult,
|
||||
fallback_value={
|
||||
"query": content,
|
||||
"history": history if isinstance(history, list) else [],
|
||||
"expansion_issue": [],
|
||||
"split_result": "failed",
|
||||
"reason": "验证失败或超时"
|
||||
}
|
||||
),
|
||||
timeout=150.0 # 150秒超时
|
||||
)
|
||||
logger.info(f"Verify: LLM 调用完成，result={structured}")
|
||||
except asyncio.TimeoutError:
|
||||
logger.error("Verify: LLM 调用超时（150秒），使用 fallback 值")
|
||||
structured = VerificationResult(
|
||||
query=content,
|
||||
history=history if isinstance(history, list) else [],
|
||||
expansion_issue=[],
|
||||
split_result="failed",
|
||||
reason="LLM调用超时"
|
||||
)
|
||||
|
||||
result = await Verify_prompt(state, structured)
|
||||
logger.info("=== Verify 节点执行完成 ===")
|
||||
return {"verify": result}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Verify 节点执行失败: {e}", exc_info=True)
|
||||
# 返回失败的验证结果
|
||||
return {
|
||||
"verify": {
|
||||
"status": "failed",
|
||||
"verified_data": [],
|
||||
"storage_type": state.get('storage_type', ''),
|
||||
"user_rag_memory_id": state.get('user_rag_memory_id', ''),
|
||||
"_intermediate": {
|
||||
"type": "verification",
|
||||
"title": "Data Verification",
|
||||
"result": "failed",
|
||||
"reason": f"验证过程出错: {str(e)}",
|
||||
"query": state.get('data', ''),
|
||||
"verified_count": 0,
|
||||
"storage_type": state.get('storage_type', ''),
|
||||
"user_rag_memory_id": state.get('user_rag_memory_id', '')
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,55 +0,0 @@
|
||||
from app.core.memory.agent.utils.llm_tools import WriteState
|
||||
from app.core.memory.agent.utils.write_tools import write
|
||||
from app.core.logging_config import get_agent_logger
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
async def write_node(state: WriteState) -> WriteState:
|
||||
"""
|
||||
Write data to the database/file system.
|
||||
|
||||
Args:
|
||||
state: WriteState containing messages, end_user_id, and memory_config
|
||||
|
||||
Returns:
|
||||
dict: Contains 'write_result' with status and data fields
|
||||
"""
|
||||
messages = state.get('messages', [])
|
||||
end_user_id = state.get('end_user_id', '')
|
||||
memory_config = state.get('memory_config', '')
|
||||
|
||||
# Convert LangChain messages to structured format expected by write()
|
||||
structured_messages = []
|
||||
for msg in messages:
|
||||
if hasattr(msg, 'type') and hasattr(msg, 'content'):
|
||||
# Map LangChain message types to role names
|
||||
role = 'user' if msg.type == 'human' else 'assistant' if msg.type == 'ai' else msg.type
|
||||
structured_messages.append({
|
||||
"role": role,
|
||||
"content": msg.content # content is now guaranteed to be a string
|
||||
})
|
||||
|
||||
try:
|
||||
result = await write(
|
||||
messages=structured_messages,
|
||||
end_user_id=end_user_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
logger.info(f"Write completed successfully! Config: {memory_config.config_name}")
|
||||
|
||||
write_result = {
|
||||
"status": "success",
|
||||
"data": structured_messages,
|
||||
"config_id": memory_config.config_id,
|
||||
"config_name": memory_config.config_name,
|
||||
}
|
||||
return {"write_result": write_result}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Data_write failed: {e}", exc_info=True)
|
||||
write_result = {
|
||||
"status": "error",
|
||||
"message": str(e),
|
||||
}
|
||||
return {"write_result": write_result}
|
||||
@@ -1,177 +1,469 @@
|
||||
#!/usr/bin/env python3
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import warnings
|
||||
from contextlib import asynccontextmanager
|
||||
from typing import Literal
|
||||
|
||||
from langchain_core.messages import HumanMessage
|
||||
from langgraph.constants import START, END
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.core.memory.agent.langgraph_graph.nodes import (
|
||||
ToolExecutionNode,
|
||||
create_input_message,
|
||||
)
|
||||
from app.core.memory.agent.mcp_server.services.parameter_builder import ParameterBuilder
|
||||
from app.core.memory.agent.utils.llm_tools import COUNTState, ReadState
|
||||
from app.core.memory.agent.utils.multimodal import MultimodalProcessor
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from dotenv import load_dotenv
|
||||
from langchain_core.messages import AIMessage
|
||||
from langgraph.checkpoint.memory import InMemorySaver
|
||||
from langgraph.constants import END, START
|
||||
from langgraph.graph import StateGraph
|
||||
from langgraph.prebuilt import ToolNode
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
warnings.filterwarnings("ignore", category=RuntimeWarning)
|
||||
load_dotenv()
|
||||
redishost=os.getenv("REDISHOST")
|
||||
redisport=os.getenv('REDISPORT')
|
||||
redisdb=os.getenv('REDISDB')
|
||||
redispassword=os.getenv('REDISPASSWORD')
|
||||
counter = COUNTState(limit=3)
|
||||
|
||||
# Update loop count in workflow
|
||||
async def update_loop_count(state):
|
||||
"""Update loop counter"""
|
||||
current_count = state.get("loop_count", 0)
|
||||
return {"loop_count": current_count + 1}
|
||||
|
||||
|
||||
from app.db import get_db
|
||||
from app.services.memory_config_service import MemoryConfigService
|
||||
def Verify_continue(state: ReadState) -> Literal["Summary", "Summary_fails", "content_input"]:
|
||||
messages = state["messages"]
|
||||
|
||||
from app.core.memory.agent.utils.llm_tools import ReadState
|
||||
from app.core.memory.agent.langgraph_graph.nodes.data_nodes import content_input_node
|
||||
from app.core.memory.agent.langgraph_graph.nodes.problem_nodes import (
|
||||
Split_The_Problem,
|
||||
Problem_Extension,
|
||||
)
|
||||
from app.core.memory.agent.langgraph_graph.nodes.retrieve_nodes import (
|
||||
retrieve,
|
||||
)
|
||||
from app.core.memory.agent.langgraph_graph.nodes.summary_nodes import (
|
||||
Input_Summary,
|
||||
Retrieve_Summary,
|
||||
Summary_fails,
|
||||
Summary,
|
||||
)
|
||||
from app.core.memory.agent.langgraph_graph.nodes.verification_nodes import Verify
|
||||
from app.core.memory.agent.langgraph_graph.routing.routers import (
|
||||
Split_continue,
|
||||
Retrieve_continue,
|
||||
Verify_continue,
|
||||
)
|
||||
# Add boundary check
|
||||
if not messages:
|
||||
return END
|
||||
counter.add(1) # Increment by 1
|
||||
|
||||
loop_count = counter.get_total()
|
||||
logger.debug(f"[should_continue] Current loop count: {loop_count}")
|
||||
|
||||
last_message = messages[-1]
|
||||
last_message_str = str(last_message).replace('\\', '')
|
||||
status_tools = re.findall(r'"split_result": "(.*?)"', last_message_str)
|
||||
logger.debug(f"Status tools: {status_tools}")
|
||||
|
||||
if "success" in status_tools:
|
||||
counter.reset()
|
||||
return "Summary"
|
||||
elif "failed" in status_tools:
|
||||
if loop_count < 2: # Maximum loop count is 3
|
||||
return "content_input"
|
||||
else:
|
||||
counter.reset()
|
||||
return "Summary_fails"
|
||||
else:
|
||||
# Add default return value to avoid returning None
|
||||
counter.reset()
|
||||
return "Summary" # Default based on business requirements
|
||||
|
||||
|
||||
def Retrieve_continue(state) -> Literal["Verify", "Retrieve_Summary"]:
|
||||
"""
|
||||
Determine routing based on search_switch value.
|
||||
|
||||
Args:
|
||||
state: State dictionary containing search_switch
|
||||
|
||||
Returns:
|
||||
Next node to execute
|
||||
"""
|
||||
# Direct dictionary access instead of regex parsing
|
||||
search_switch = state.get("search_switch")
|
||||
|
||||
# Handle case where search_switch might be in messages
|
||||
if search_switch is None and "messages" in state:
|
||||
messages = state.get("messages", [])
|
||||
if messages:
|
||||
last_message = messages[-1]
|
||||
# Try to extract from tool_calls args
|
||||
if hasattr(last_message, "tool_calls") and last_message.tool_calls:
|
||||
for tool_call in last_message.tool_calls:
|
||||
if isinstance(tool_call, dict) and "args" in tool_call:
|
||||
search_switch = tool_call["args"].get("search_switch")
|
||||
break
|
||||
|
||||
# Convert to string for comparison if needed
|
||||
if search_switch is not None:
|
||||
search_switch = str(search_switch)
|
||||
if search_switch == '0':
|
||||
return 'Verify'
|
||||
elif search_switch == '1':
|
||||
return 'Retrieve_Summary'
|
||||
|
||||
# Add default return value to avoid returning None
|
||||
return 'Retrieve_Summary' # Default based on business logic
|
||||
|
||||
|
||||
def Split_continue(state) -> Literal["Split_The_Problem", "Input_Summary"]:
|
||||
"""
|
||||
Determine routing based on search_switch value.
|
||||
|
||||
Args:
|
||||
state: State dictionary containing search_switch
|
||||
|
||||
Returns:
|
||||
Next node to execute
|
||||
"""
|
||||
logger.debug(f"Split_continue state: {state}")
|
||||
|
||||
# Direct dictionary access instead of regex parsing
|
||||
search_switch = state.get("search_switch")
|
||||
|
||||
# Handle case where search_switch might be in messages
|
||||
if search_switch is None and "messages" in state:
|
||||
messages = state.get("messages", [])
|
||||
if messages:
|
||||
last_message = messages[-1]
|
||||
# Try to extract from tool_calls args
|
||||
if hasattr(last_message, "tool_calls") and last_message.tool_calls:
|
||||
for tool_call in last_message.tool_calls:
|
||||
if isinstance(tool_call, dict) and "args" in tool_call:
|
||||
search_switch = tool_call["args"].get("search_switch")
|
||||
break
|
||||
|
||||
# Convert to string for comparison if needed
|
||||
if search_switch is not None:
|
||||
search_switch = str(search_switch)
|
||||
if search_switch == '2':
|
||||
return 'Input_Summary'
|
||||
return 'Split_The_Problem' # Default case
|
||||
|
||||
|
||||
class ProblemExtensionNode:
|
||||
def __init__(self, tool, id, namespace, search_switch, apply_id, group_id, storage_type="", user_rag_memory_id=""):
|
||||
self.tool_node = ToolNode([tool])
|
||||
self.id = id
|
||||
self.tool_name = tool.name if hasattr(tool, 'name') else str(tool)
|
||||
self.namespace = namespace
|
||||
self.search_switch = search_switch
|
||||
self.apply_id = apply_id
|
||||
self.group_id = group_id
|
||||
self.storage_type = storage_type
|
||||
self.user_rag_memory_id = user_rag_memory_id
|
||||
|
||||
async def __call__(self, state):
|
||||
messages = state["messages"]
|
||||
last_message = messages[-1] if messages else ""
|
||||
logger.debug(f"ProblemExtensionNode {self.id} - Current time: {time.time()} - Message: {last_message}")
|
||||
if self.tool_name == 'Input_Summary':
|
||||
tool_call = re.findall("'id': '(.*?)'", str(last_message))[0]
|
||||
else:
|
||||
tool_call = str(re.findall(r"tool_call_id=.*?'(.*?)'", str(last_message))[0]).replace('\\', '').split('_id')[1]
|
||||
|
||||
# Try to extract actual content payload from previous tool result
|
||||
raw_msg = last_message.content if hasattr(last_message, 'content') else str(last_message)
|
||||
extracted_payload = None
|
||||
# Capture ToolMessage content field (supports single/double quotes), avoid greedy matching
|
||||
m = re.search(r"content=(?:\"|\')(.*?)(?:\"|\'),\s*name=", raw_msg, flags=re.S)
|
||||
if m:
|
||||
extracted_payload = m.group(1)
|
||||
else:
|
||||
# Fallback: use raw string directly
|
||||
extracted_payload = raw_msg
|
||||
|
||||
# Try to parse content as JSON first
|
||||
try:
|
||||
content = json.loads(extracted_payload)
|
||||
except Exception:
|
||||
# Try to extract JSON fragment from text and parse
|
||||
parsed = None
|
||||
candidates = re.findall(r"[\[{].*[\]}]", extracted_payload, flags=re.S)
|
||||
for cand in candidates:
|
||||
try:
|
||||
parsed = json.loads(cand)
|
||||
break
|
||||
except Exception:
|
||||
continue
|
||||
# If still fails, use raw string as content
|
||||
content = parsed if parsed is not None else extracted_payload
|
||||
|
||||
# Build correct parameters based on tool name
|
||||
tool_args = {}
|
||||
|
||||
if self.tool_name == "Verify":
|
||||
# Verify tool requires context and usermessages parameters
|
||||
if isinstance(content, dict):
|
||||
tool_args["context"] = content
|
||||
else:
|
||||
tool_args["context"] = {"content": content}
|
||||
tool_args["usermessages"] = str(tool_call)
|
||||
tool_args["apply_id"] = str(self.apply_id)
|
||||
tool_args["group_id"] = str(self.group_id)
|
||||
elif self.tool_name == "Retrieve":
|
||||
# Retrieve tool requires context and usermessages parameters
|
||||
if isinstance(content, dict):
|
||||
tool_args["context"] = content
|
||||
else:
|
||||
tool_args["context"] = {"content": content}
|
||||
tool_args["usermessages"] = str(tool_call)
|
||||
tool_args["search_switch"] = str(self.search_switch)
|
||||
tool_args["apply_id"] = str(self.apply_id)
|
||||
tool_args["group_id"] = str(self.group_id)
|
||||
elif self.tool_name == "Summary":
|
||||
# Summary tool requires string type context parameter
|
||||
if isinstance(content, dict):
|
||||
# Convert dict to JSON string
|
||||
tool_args["context"] = json.dumps(content, ensure_ascii=False)
|
||||
else:
|
||||
tool_args["context"] = str(content)
|
||||
tool_args["usermessages"] = str(tool_call)
|
||||
tool_args["apply_id"] = str(self.apply_id)
|
||||
tool_args["group_id"] = str(self.group_id)
|
||||
elif self.tool_name == "Summary_fails":
|
||||
# Summary_fails tool requires string type context parameter
|
||||
if isinstance(content, dict):
|
||||
# Convert dict to JSON string
|
||||
tool_args["context"] = json.dumps(content, ensure_ascii=False)
|
||||
else:
|
||||
tool_args["context"] = str(content)
|
||||
tool_args["usermessages"] = str(tool_call)
|
||||
tool_args["apply_id"] = str(self.apply_id)
|
||||
tool_args["group_id"] = str(self.group_id)
|
||||
elif self.tool_name == 'Input_Summary':
|
||||
tool_args["context"] = str(last_message)
|
||||
tool_args["usermessages"] = str(tool_call)
|
||||
tool_args["search_switch"] = str(self.search_switch)
|
||||
tool_args["apply_id"] = str(self.apply_id)
|
||||
tool_args["group_id"] = str(self.group_id)
|
||||
tool_args["storage_type"] = getattr(self, 'storage_type', "")
|
||||
tool_args["user_rag_memory_id"] = getattr(self, 'user_rag_memory_id', "")
|
||||
elif self.tool_name == 'Retrieve_Summary':
|
||||
# Retrieve_Summary expects dict directly, not JSON string
|
||||
# content might be a JSON string, try to parse it
|
||||
if isinstance(content, str):
|
||||
try:
|
||||
parsed_content = json.loads(content)
|
||||
# Check if it has a "context" key
|
||||
if isinstance(parsed_content, dict) and "context" in parsed_content:
|
||||
tool_args["context"] = parsed_content["context"]
|
||||
else:
|
||||
tool_args["context"] = parsed_content
|
||||
except json.JSONDecodeError:
|
||||
# If parsing fails, wrap the string
|
||||
tool_args["context"] = {"content": content}
|
||||
elif isinstance(content, dict):
|
||||
# Check if content has a "context" key that needs unwrapping
|
||||
if "context" in content:
|
||||
tool_args["context"] = content["context"]
|
||||
else:
|
||||
tool_args["context"] = content
|
||||
else:
|
||||
tool_args["context"] = {"content": str(content)}
|
||||
|
||||
tool_args["usermessages"] = str(tool_call)
|
||||
tool_args["apply_id"] = str(self.apply_id)
|
||||
tool_args["group_id"] = str(self.group_id)
|
||||
else:
|
||||
# Other tools use context parameter
|
||||
if isinstance(content, dict):
|
||||
tool_args["context"] = content
|
||||
else:
|
||||
tool_args["context"] = {"content": content}
|
||||
tool_args["usermessages"] = str(tool_call)
|
||||
tool_args["apply_id"] = str(self.apply_id)
|
||||
tool_args["group_id"] = str(self.group_id)
|
||||
|
||||
|
||||
tool_input = {
|
||||
"messages": [
|
||||
AIMessage(
|
||||
content="",
|
||||
tool_calls=[{
|
||||
"name": self.tool_name,
|
||||
"args": tool_args,
|
||||
"id": self.id + f"{tool_call}",
|
||||
}]
|
||||
)
|
||||
]
|
||||
}
|
||||
result = await self.tool_node.ainvoke(tool_input)
|
||||
result_text = str(result)
|
||||
|
||||
return {"messages": [AIMessage(content=result_text)]}
|
||||
|
||||
|
||||
@asynccontextmanager
|
||||
async def make_read_graph():
|
||||
"""创建并返回 LangGraph 工作流"""
|
||||
try:
|
||||
# Build workflow graph
|
||||
workflow = StateGraph(ReadState)
|
||||
workflow.add_node("content_input", content_input_node)
|
||||
workflow.add_node("Split_The_Problem", Split_The_Problem)
|
||||
workflow.add_node("Problem_Extension", Problem_Extension)
|
||||
workflow.add_node("Input_Summary", Input_Summary)
|
||||
# workflow.add_node("Retrieve", retrieve_nodes)
|
||||
workflow.add_node("Retrieve", retrieve)
|
||||
workflow.add_node("Verify", Verify)
|
||||
workflow.add_node("Retrieve_Summary", Retrieve_Summary)
|
||||
workflow.add_node("Summary", Summary)
|
||||
workflow.add_node("Summary_fails", Summary_fails)
|
||||
|
||||
# 添加边
|
||||
workflow.add_edge(START, "content_input")
|
||||
workflow.add_conditional_edges("content_input", Split_continue)
|
||||
workflow.add_edge("Input_Summary", END)
|
||||
workflow.add_edge("Split_The_Problem", "Problem_Extension")
|
||||
workflow.add_edge("Problem_Extension", "Retrieve")
|
||||
workflow.add_conditional_edges("Retrieve", Retrieve_continue)
|
||||
workflow.add_edge("Retrieve_Summary", END)
|
||||
workflow.add_conditional_edges("Verify", Verify_continue)
|
||||
workflow.add_edge("Summary_fails", END)
|
||||
workflow.add_edge("Summary", END)
|
||||
|
||||
|
||||
'''-----'''
|
||||
# workflow.add_edge("Retrieve", END)
|
||||
|
||||
# 编译工作流
|
||||
graph = workflow.compile()
|
||||
yield graph
|
||||
|
||||
except Exception as e:
|
||||
print(f"创建工作流失败: {e}")
|
||||
raise
|
||||
finally:
|
||||
print("工作流创建完成")
|
||||
|
||||
async def main():
|
||||
"""主函数 - 运行工作流"""
|
||||
message = "昨天有什么好看的电影"
|
||||
end_user_id = '88a459f5_text09' # 组ID
|
||||
storage_type = 'neo4j' # 存储类型
|
||||
search_switch = '1' # 搜索开关
|
||||
user_rag_memory_id = 'wwwwwwww' # 用户RAG记忆ID
|
||||
|
||||
# 获取数据库会话
|
||||
db_session = next(get_db())
|
||||
config_service = MemoryConfigService(db_session)
|
||||
memory_config = config_service.load_memory_config(
|
||||
config_id=17, # 改为整数
|
||||
service_name="MemoryAgentService"
|
||||
async def make_read_graph(namespace, tools, search_switch, apply_id, group_id, memory_config: MemoryConfig, storage_type=None, user_rag_memory_id=None):
|
||||
"""
|
||||
Create a read graph workflow for memory operations.
|
||||
|
||||
Args:
|
||||
namespace: Namespace identifier
|
||||
tools: MCP tools loaded from session
|
||||
search_switch: Search mode switch ("0", "1", or "2")
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
storage_type: Storage type (optional)
|
||||
user_rag_memory_id: User RAG memory ID (optional)
|
||||
"""
|
||||
memory = InMemorySaver()
|
||||
tool = [i.name for i in tools]
|
||||
logger.info(f"Initializing read graph with tools: {tool}")
|
||||
logger.info(f"Using memory_config: {memory_config.config_name} (id={memory_config.config_id})")
|
||||
|
||||
# Extract tool functions
|
||||
Split_The_Problem_ = next((t for t in tools if t.name == "Split_The_Problem"), None)
|
||||
Problem_Extension_ = next((t for t in tools if t.name == "Problem_Extension"), None)
|
||||
Retrieve_ = next((t for t in tools if t.name == "Retrieve"), None)
|
||||
Verify_ = next((t for t in tools if t.name == "Verify"), None)
|
||||
Summary_ = next((t for t in tools if t.name == "Summary"), None)
|
||||
Summary_fails_ = next((t for t in tools if t.name == "Summary_fails"), None)
|
||||
Retrieve_Summary_ = next((t for t in tools if t.name == "Retrieve_Summary"), None)
|
||||
Input_Summary_ = next((t for t in tools if t.name == "Input_Summary"), None)
|
||||
|
||||
# Instantiate services
|
||||
parameter_builder = ParameterBuilder()
|
||||
multimodal_processor = MultimodalProcessor()
|
||||
|
||||
# Create nodes using new modular components
|
||||
Split_The_Problem_node = ToolNode([Split_The_Problem_])
|
||||
|
||||
Problem_Extension_node = ToolExecutionNode(
|
||||
tool=Problem_Extension_,
|
||||
node_id="Problem_Extension_id",
|
||||
namespace=namespace,
|
||||
search_switch=search_switch,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
parameter_builder=parameter_builder,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
import time
|
||||
start=time.time()
|
||||
try:
|
||||
async with make_read_graph() as graph:
|
||||
config = {"configurable": {"thread_id": end_user_id}}
|
||||
# 初始状态 - 包含所有必要字段
|
||||
initial_state = {"messages": [HumanMessage(content=message)] ,"search_switch":search_switch,"end_user_id":end_user_id
|
||||
,"storage_type":storage_type,"user_rag_memory_id":user_rag_memory_id,"memory_config":memory_config}
|
||||
# 获取节点更新信息
|
||||
_intermediate_outputs = []
|
||||
summary = ''
|
||||
|
||||
async for update_event in graph.astream(
|
||||
initial_state,
|
||||
stream_mode="updates",
|
||||
config=config
|
||||
):
|
||||
for node_name, node_data in update_event.items():
|
||||
print(f"处理节点: {node_name}")
|
||||
|
||||
# 处理不同Summary节点的返回结构
|
||||
if 'Summary' in node_name:
|
||||
if 'InputSummary' in node_data and 'summary_result' in node_data['InputSummary']:
|
||||
summary = node_data['InputSummary']['summary_result']
|
||||
elif 'RetrieveSummary' in node_data and 'summary_result' in node_data['RetrieveSummary']:
|
||||
summary = node_data['RetrieveSummary']['summary_result']
|
||||
elif 'summary' in node_data and 'summary_result' in node_data['summary']:
|
||||
summary = node_data['summary']['summary_result']
|
||||
elif 'SummaryFails' in node_data and 'summary_result' in node_data['SummaryFails']:
|
||||
summary = node_data['SummaryFails']['summary_result']
|
||||
|
||||
spit_data = node_data.get('spit_data', {}).get('_intermediate', None)
|
||||
if spit_data and spit_data != [] and spit_data != {}:
|
||||
_intermediate_outputs.append(spit_data)
|
||||
|
||||
# Problem_Extension 节点
|
||||
problem_extension = node_data.get('problem_extension', {}).get('_intermediate', None)
|
||||
if problem_extension and problem_extension != [] and problem_extension != {}:
|
||||
_intermediate_outputs.append(problem_extension)
|
||||
|
||||
# Retrieve 节点
|
||||
retrieve_node = node_data.get('retrieve', {}).get('_intermediate_outputs', None)
|
||||
if retrieve_node and retrieve_node != [] and retrieve_node != {}:
|
||||
_intermediate_outputs.extend(retrieve_node)
|
||||
|
||||
# Verify 节点
|
||||
verify_n = node_data.get('verify', {}).get('_intermediate', None)
|
||||
if verify_n and verify_n != [] and verify_n != {}:
|
||||
_intermediate_outputs.append(verify_n)
|
||||
Retrieve_node = ToolExecutionNode(
|
||||
tool=Retrieve_,
|
||||
node_id="Retrieve_id",
|
||||
namespace=namespace,
|
||||
search_switch=search_switch,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
parameter_builder=parameter_builder,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
|
||||
|
||||
# Summary 节点
|
||||
summary_n = node_data.get('summary', {}).get('_intermediate', None)
|
||||
if summary_n and summary_n != [] and summary_n != {}:
|
||||
_intermediate_outputs.append(summary_n)
|
||||
Verify_node = ToolExecutionNode(
|
||||
tool=Verify_,
|
||||
node_id="Verify_id",
|
||||
namespace=namespace,
|
||||
search_switch=search_switch,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
parameter_builder=parameter_builder,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
|
||||
Summary_node = ToolExecutionNode(
|
||||
tool=Summary_,
|
||||
node_id="Summary_id",
|
||||
namespace=namespace,
|
||||
search_switch=search_switch,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
parameter_builder=parameter_builder,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
|
||||
# # 过滤掉空值
|
||||
# _intermediate_outputs = [item for item in _intermediate_outputs if item and item != [] and item != {}]
|
||||
#
|
||||
# # 优化搜索结果
|
||||
# print("=== 开始优化搜索结果 ===")
|
||||
# optimized_outputs = merge_multiple_search_results(_intermediate_outputs)
|
||||
# result=reorder_output_results(optimized_outputs)
|
||||
# # 保存优化后的结果到文件
|
||||
# with open('_intermediate_outputs_optimized.json', 'w', encoding='utf-8') as f:
|
||||
# import json
|
||||
# f.write(json.dumps(result, indent=4, ensure_ascii=False))
|
||||
#
|
||||
print(f"=== 最终摘要 ===")
|
||||
print(summary)
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
Summary_fails_node = ToolExecutionNode(
|
||||
tool=Summary_fails_,
|
||||
node_id="Summary_fails_id",
|
||||
namespace=namespace,
|
||||
search_switch=search_switch,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
parameter_builder=parameter_builder,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
|
||||
end=time.time()
|
||||
print(100*'y')
|
||||
print(f"总耗时: {end-start}s")
|
||||
print(100*'y')
|
||||
Retrieve_Summary_node = ToolExecutionNode(
|
||||
tool=Retrieve_Summary_,
|
||||
node_id="Retrieve_Summary_id",
|
||||
namespace=namespace,
|
||||
search_switch=search_switch,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
parameter_builder=parameter_builder,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
|
||||
Input_Summary_node = ToolExecutionNode(
|
||||
tool=Input_Summary_,
|
||||
node_id="Input_Summary_id",
|
||||
namespace=namespace,
|
||||
search_switch=search_switch,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
parameter_builder=parameter_builder,
|
||||
storage_type=storage_type,
|
||||
user_rag_memory_id=user_rag_memory_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import asyncio
|
||||
asyncio.run(main())
|
||||
async def content_input_node(state):
|
||||
state_search_switch = state.get("search_switch", search_switch)
|
||||
|
||||
tool_name = "Input_Summary" if state_search_switch == '2' else "Split_The_Problem"
|
||||
session_prefix = "input_summary_call_id" if state_search_switch == '2' else "split_call_id"
|
||||
|
||||
return await create_input_message(
|
||||
state=state,
|
||||
tool_name=tool_name,
|
||||
session_id=f"{session_prefix}_{namespace}",
|
||||
search_switch=search_switch,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
multimodal_processor=multimodal_processor,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
|
||||
|
||||
# Build workflow graph
|
||||
workflow = StateGraph(ReadState)
|
||||
workflow.add_node("content_input", content_input_node)
|
||||
workflow.add_node("Split_The_Problem", Split_The_Problem_node)
|
||||
workflow.add_node("Problem_Extension", Problem_Extension_node)
|
||||
workflow.add_node("Retrieve", Retrieve_node)
|
||||
workflow.add_node("Verify", Verify_node)
|
||||
workflow.add_node("Summary", Summary_node)
|
||||
workflow.add_node("Summary_fails", Summary_fails_node)
|
||||
workflow.add_node("Retrieve_Summary", Retrieve_Summary_node)
|
||||
workflow.add_node("Input_Summary", Input_Summary_node)
|
||||
|
||||
# Add edges using imported routers
|
||||
workflow.add_edge(START, "content_input")
|
||||
workflow.add_conditional_edges("content_input", Split_continue)
|
||||
workflow.add_edge("Input_Summary", END)
|
||||
workflow.add_edge("Split_The_Problem", "Problem_Extension")
|
||||
workflow.add_edge("Problem_Extension", "Retrieve")
|
||||
workflow.add_conditional_edges("Retrieve", Retrieve_continue)
|
||||
workflow.add_edge("Retrieve_Summary", END)
|
||||
workflow.add_conditional_edges("Verify", Verify_continue)
|
||||
workflow.add_edge("Summary_fails", END)
|
||||
workflow.add_edge("Summary", END)
|
||||
|
||||
graph = workflow.compile(checkpointer=memory)
|
||||
yield graph
|
||||
|
||||
@@ -0,0 +1,13 @@
|
||||
"""LangGraph routing logic."""
|
||||
|
||||
from app.core.memory.agent.langgraph_graph.routing.routers import (
|
||||
Verify_continue,
|
||||
Retrieve_continue,
|
||||
Split_continue,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"Verify_continue",
|
||||
"Retrieve_continue",
|
||||
"Split_continue",
|
||||
]
|
||||
@@ -1,61 +1,123 @@
|
||||
"""
|
||||
Routing functions for LangGraph conditional edges.
|
||||
|
||||
This module provides routing functions that determine the next node to execute
|
||||
based on state values. All functions return Literal types for type safety.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import re
|
||||
from typing import Literal
|
||||
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.core.memory.agent.langgraph_graph.state.extractors import extract_search_switch
|
||||
from app.core.memory.agent.utils.llm_tools import ReadState, COUNTState
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
# Global counter for Verify routing
|
||||
counter = COUNTState(limit=3)
|
||||
def Split_continue(state:ReadState) -> Literal["Split_The_Problem", "Input_Summary"]:
|
||||
"""
|
||||
Determine routing based on search_switch value.
|
||||
|
||||
Args:
|
||||
state: State dictionary containing search_switch
|
||||
|
||||
Returns:
|
||||
Next node to execute
|
||||
"""
|
||||
logger.debug(f"Split_continue state: {state}")
|
||||
search_switch = state.get('search_switch', '')
|
||||
if search_switch is not None:
|
||||
search_switch = str(search_switch)
|
||||
if search_switch == '2':
|
||||
return 'Input_Summary'
|
||||
return 'Split_The_Problem' # 默认情况
|
||||
|
||||
def Retrieve_continue(state) -> Literal["Verify", "Retrieve_Summary"]:
|
||||
"""
|
||||
Determine routing based on search_switch value.
|
||||
|
||||
Args:
|
||||
state: State dictionary containing search_switch
|
||||
|
||||
Returns:
|
||||
Next node to execute
|
||||
"""
|
||||
search_switch = state.get('search_switch', '')
|
||||
if search_switch is not None:
|
||||
search_switch = str(search_switch)
|
||||
if search_switch == '0':
|
||||
return 'Verify'
|
||||
elif search_switch == '1':
|
||||
return 'Retrieve_Summary'
|
||||
return 'Retrieve_Summary' # Default based on business logic
|
||||
def Verify_continue(state: ReadState) -> Literal["Summary", "Summary_fails", "content_input"]:
|
||||
status=state.get('verify', '')['status']
|
||||
# loop_count = counter.get_total()
|
||||
if "success" in status:
|
||||
# counter.reset()
|
||||
"""
|
||||
Determine routing after Verify node based on verification result.
|
||||
|
||||
This function checks the verification result in the last message and routes to:
|
||||
- Summary: if verification succeeded
|
||||
- content_input: if verification failed and retry limit not reached
|
||||
- Summary_fails: if verification failed and retry limit reached
|
||||
|
||||
Args:
|
||||
state: LangGraph state containing messages
|
||||
|
||||
Returns:
|
||||
Next node name as Literal type
|
||||
"""
|
||||
messages = state.get("messages", [])
|
||||
|
||||
# Boundary check
|
||||
if not messages:
|
||||
logger.warning("[Verify_continue] No messages in state, defaulting to Summary")
|
||||
counter.reset()
|
||||
return "Summary"
|
||||
elif "failed" in status:
|
||||
# if loop_count < 2: # Maximum loop count is 3
|
||||
# return "content_input"
|
||||
# else:
|
||||
# counter.reset()
|
||||
return "Summary_fails"
|
||||
|
||||
# Increment counter
|
||||
counter.add(1)
|
||||
loop_count = counter.get_total()
|
||||
logger.debug(f"[Verify_continue] Current loop count: {loop_count}")
|
||||
|
||||
# Extract verification result from last message
|
||||
last_message = messages[-1]
|
||||
last_message_str = str(last_message).replace('\\', '')
|
||||
status_tools = re.findall(r'"split_result": "(.*?)"', last_message_str)
|
||||
logger.debug(f"[Verify_continue] Status tools: {status_tools}")
|
||||
|
||||
# Route based on verification result
|
||||
if "success" in status_tools:
|
||||
counter.reset()
|
||||
return "Summary"
|
||||
elif "failed" in status_tools:
|
||||
if loop_count < 2: # Max retry count is 2
|
||||
return "content_input"
|
||||
else:
|
||||
counter.reset()
|
||||
return "Summary_fails"
|
||||
else:
|
||||
# Add default return value to avoid returning None
|
||||
# counter.reset()
|
||||
return "Summary" # Default based on business requirements
|
||||
# Default to Summary if status is unclear
|
||||
counter.reset()
|
||||
return "Summary"
|
||||
|
||||
|
||||
def Retrieve_continue(state: dict) -> Literal["Verify", "Retrieve_Summary"]:
|
||||
"""
|
||||
Determine routing after Retrieve node based on search_switch value.
|
||||
|
||||
This function routes based on the search_switch parameter:
|
||||
- search_switch == '0': Route to Verify (verification needed)
|
||||
- search_switch == '1': Route to Retrieve_Summary (direct summary)
|
||||
|
||||
Args:
|
||||
state: LangGraph state dictionary
|
||||
|
||||
Returns:
|
||||
Next node name as Literal type
|
||||
"""
|
||||
search_switch = extract_search_switch(state)
|
||||
|
||||
logger.debug(f"[Retrieve_continue] search_switch: {search_switch}")
|
||||
|
||||
if search_switch == '0':
|
||||
return 'Verify'
|
||||
elif search_switch == '1':
|
||||
return 'Retrieve_Summary'
|
||||
|
||||
# Default to Retrieve_Summary
|
||||
logger.debug("[Retrieve_continue] No valid search_switch, defaulting to Retrieve_Summary")
|
||||
return 'Retrieve_Summary'
|
||||
|
||||
|
||||
def Split_continue(state: dict) -> Literal["Split_The_Problem", "Input_Summary"]:
|
||||
"""
|
||||
Determine routing after content_input node based on search_switch value.
|
||||
|
||||
This function routes based on the search_switch parameter:
|
||||
- search_switch == '2': Route to Input_Summary (direct input summary)
|
||||
- Otherwise: Route to Split_The_Problem (problem decomposition)
|
||||
|
||||
Args:
|
||||
state: LangGraph state dictionary
|
||||
|
||||
Returns:
|
||||
Next node name as Literal type
|
||||
"""
|
||||
logger.debug(f"[Split_continue] state keys: {state.keys()}")
|
||||
|
||||
search_switch = extract_search_switch(state)
|
||||
|
||||
logger.debug(f"[Split_continue] search_switch: {search_switch}")
|
||||
|
||||
if search_switch == '2':
|
||||
return 'Input_Summary'
|
||||
|
||||
# Default to Split_The_Problem
|
||||
return 'Split_The_Problem'
|
||||
|
||||
13
api/app/core/memory/agent/langgraph_graph/state/__init__.py
Normal file
13
api/app/core/memory/agent/langgraph_graph/state/__init__.py
Normal file
@@ -0,0 +1,13 @@
|
||||
"""LangGraph state management utilities."""
|
||||
|
||||
from app.core.memory.agent.langgraph_graph.state.extractors import (
|
||||
extract_search_switch,
|
||||
extract_tool_call_id,
|
||||
extract_content_payload,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"extract_search_switch",
|
||||
"extract_tool_call_id",
|
||||
"extract_content_payload",
|
||||
]
|
||||
179
api/app/core/memory/agent/langgraph_graph/state/extractors.py
Normal file
179
api/app/core/memory/agent/langgraph_graph/state/extractors.py
Normal file
@@ -0,0 +1,179 @@
|
||||
"""
|
||||
State extraction utilities for type-safe access to LangGraph state values.
|
||||
|
||||
This module provides utility functions for extracting values from LangGraph state
|
||||
dictionaries with proper error handling and sensible defaults.
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
from typing import Any, Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
def extract_search_switch(state: dict) -> Optional[str]:
|
||||
"""
|
||||
Extract search_switch from state or messages.
|
||||
"""
|
||||
|
||||
search_switch = state.get("search_switch")
|
||||
|
||||
if search_switch is not None:
|
||||
return str(search_switch)
|
||||
|
||||
# Try to extract from messages
|
||||
messages = state.get("messages", [])
|
||||
if not messages:
|
||||
return None
|
||||
|
||||
# 从最新的消息开始查找
|
||||
for message in reversed(messages):
|
||||
# 尝试从 tool_calls 中提取
|
||||
if hasattr(message, "tool_calls") and message.tool_calls:
|
||||
for tool_call in message.tool_calls:
|
||||
if isinstance(tool_call, dict):
|
||||
# 从 tool_call 的 args 中提取
|
||||
if "args" in tool_call and isinstance(tool_call["args"], dict):
|
||||
search_switch = tool_call["args"].get("search_switch")
|
||||
if search_switch is not None:
|
||||
return str(search_switch)
|
||||
# 直接从 tool_call 中提取
|
||||
search_switch = tool_call.get("search_switch")
|
||||
if search_switch is not None:
|
||||
return str(search_switch)
|
||||
|
||||
# 尝试从 content 中提取（如果是 JSON 格式）
|
||||
if hasattr(message, "content"):
|
||||
try:
|
||||
import json
|
||||
if isinstance(message.content, str):
|
||||
content_data = json.loads(message.content)
|
||||
if isinstance(content_data, dict):
|
||||
search_switch = content_data.get("search_switch")
|
||||
if search_switch is not None:
|
||||
return str(search_switch)
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
pass
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def extract_tool_call_id(message: Any) -> str:
|
||||
"""
|
||||
Extract tool call ID from message using structured attributes.
|
||||
|
||||
This function extracts the tool call ID from a message object, handling both
|
||||
direct attribute access and tool_calls list structures.
|
||||
|
||||
Args:
|
||||
message: Message object (typically ToolMessage or AIMessage)
|
||||
|
||||
Returns:
|
||||
Tool call ID as string
|
||||
|
||||
Raises:
|
||||
ValueError: If tool call ID cannot be extracted
|
||||
|
||||
Examples:
|
||||
>>> message = ToolMessage(content="...", tool_call_id="call_123")
|
||||
>>> extract_tool_call_id(message)
|
||||
'call_123'
|
||||
"""
|
||||
# Try direct attribute access for ToolMessage
|
||||
if hasattr(message, "tool_call_id"):
|
||||
tool_call_id = message.tool_call_id
|
||||
if tool_call_id:
|
||||
return str(tool_call_id)
|
||||
|
||||
# Try extracting from tool_calls list for AIMessage
|
||||
if hasattr(message, "tool_calls") and message.tool_calls:
|
||||
tool_call = message.tool_calls[0]
|
||||
if isinstance(tool_call, dict) and "id" in tool_call:
|
||||
return str(tool_call["id"])
|
||||
|
||||
# Try extracting from id attribute
|
||||
if hasattr(message, "id"):
|
||||
message_id = message.id
|
||||
if message_id:
|
||||
return str(message_id)
|
||||
|
||||
# If all else fails, raise an error
|
||||
raise ValueError(f"Could not extract tool call ID from message: {type(message)}")
|
||||
|
||||
|
||||
def extract_content_payload(message: Any) -> Any:
|
||||
"""
|
||||
Extract content payload from ToolMessage, parsing JSON if needed.
|
||||
|
||||
This function extracts the content from a message and attempts to parse it as JSON
|
||||
if it appears to be a JSON string. It handles various message formats and provides
|
||||
sensible fallbacks.
|
||||
|
||||
Args:
|
||||
message: Message object (typically ToolMessage)
|
||||
|
||||
Returns:
|
||||
Parsed content (dict, list, or str)
|
||||
|
||||
Examples:
|
||||
>>> message = ToolMessage(content='{"key": "value"}')
|
||||
>>> extract_content_payload(message)
|
||||
{'key': 'value'}
|
||||
|
||||
>>> message = ToolMessage(content='plain text')
|
||||
>>> extract_content_payload(message)
|
||||
'plain text'
|
||||
"""
|
||||
# Extract raw content
|
||||
# For ToolMessages (responses from tools), extract from content
|
||||
if hasattr(message, "content"):
|
||||
raw_content = message.content
|
||||
logger.info(f"extract_content_payload: raw_content type={type(raw_content)}, value={str(raw_content)[:500]}")
|
||||
|
||||
# Handle MCP content format: [{'type': 'text', 'text': '...'}]
|
||||
if isinstance(raw_content, list):
|
||||
for block in raw_content:
|
||||
if isinstance(block, dict) and block.get('type') == 'text':
|
||||
raw_content = block.get('text', '')
|
||||
logger.info(f"extract_content_payload: extracted text from MCP format: {str(raw_content)[:300]}")
|
||||
break
|
||||
|
||||
# If content is empty and this is an AIMessage with tool_calls,
|
||||
# extract from args (this handles the initial tool call from content_input)
|
||||
if not raw_content and hasattr(message, "tool_calls") and message.tool_calls:
|
||||
tool_call = message.tool_calls[0]
|
||||
if isinstance(tool_call, dict) and "args" in tool_call:
|
||||
return tool_call["args"]
|
||||
else:
|
||||
raw_content = str(message)
|
||||
|
||||
# If content is already a dict or list, return it directly
|
||||
if isinstance(raw_content, (dict, list)):
|
||||
logger.info(f"extract_content_payload: returning raw dict/list with keys={list(raw_content.keys()) if isinstance(raw_content, dict) else 'list'}")
|
||||
return raw_content
|
||||
|
||||
# Try to parse as JSON
|
||||
if isinstance(raw_content, str):
|
||||
# First, try direct JSON parsing
|
||||
try:
|
||||
parsed = json.loads(raw_content)
|
||||
logger.info(f"extract_content_payload: parsed JSON, keys={list(parsed.keys()) if isinstance(parsed, dict) else 'list'}")
|
||||
return parsed
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
pass
|
||||
|
||||
# If that fails, try to extract JSON from the string
|
||||
# This handles cases where the content is embedded in a larger string
|
||||
import re
|
||||
json_candidates = re.findall(r'[\[{].*[\]}]', raw_content, flags=re.DOTALL)
|
||||
for candidate in json_candidates:
|
||||
try:
|
||||
parsed = json.loads(candidate)
|
||||
logger.info(f"extract_content_payload: parsed JSON from candidate, keys={list(parsed.keys()) if isinstance(parsed, dict) else 'list'}")
|
||||
return parsed
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
continue
|
||||
|
||||
# If all parsing attempts fail, return the raw content
|
||||
logger.info(f"extract_content_payload: returning raw content (parsing failed)")
|
||||
return raw_content
|
||||
@@ -1,320 +0,0 @@
|
||||
import asyncio
|
||||
import json
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
|
||||
from langchain.tools import tool
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
from app.core.memory.src.search import (
|
||||
search_by_temporal,
|
||||
search_by_keyword_temporal,
|
||||
)
|
||||
|
||||
def extract_tool_message_content(response):
|
||||
"""从agent响应中提取ToolMessage内容和工具名称"""
|
||||
messages = response.get('messages', [])
|
||||
|
||||
for message in messages:
|
||||
if hasattr(message, 'tool_call_id') and hasattr(message, 'content'):
|
||||
# 这是一个ToolMessage
|
||||
tool_content = message.content
|
||||
tool_name = None
|
||||
|
||||
# 尝试获取工具名称
|
||||
if hasattr(message, 'name'):
|
||||
tool_name = message.name
|
||||
elif hasattr(message, 'tool_name'):
|
||||
tool_name = message.tool_name
|
||||
|
||||
try:
|
||||
# 解析JSON内容
|
||||
parsed_content = json.loads(tool_content)
|
||||
return {
|
||||
'tool_name': tool_name,
|
||||
'content': parsed_content
|
||||
}
|
||||
except json.JSONDecodeError:
|
||||
# 如果不是JSON格式，直接返回内容
|
||||
return {
|
||||
'tool_name': tool_name,
|
||||
'content': tool_content
|
||||
}
|
||||
|
||||
return None
|
||||
|
||||
|
||||
class TimeRetrievalInput(BaseModel):
|
||||
"""时间检索工具的输入模式"""
|
||||
context: str = Field(description="用户输入的查询内容")
|
||||
end_user_id: str = Field(default="88a459f5_text09", description="组ID，用于过滤搜索结果")
|
||||
|
||||
def create_time_retrieval_tool(end_user_id: str):
|
||||
"""
|
||||
创建一个带有特定end_user_id的TimeRetrieval工具（同步版本），用于按时间范围搜索语句(Statements)
|
||||
"""
|
||||
|
||||
def clean_temporal_result_fields(data):
|
||||
"""
|
||||
清理时间搜索结果中不需要的字段，并修改结构
|
||||
|
||||
Args:
|
||||
data: 要清理的数据
|
||||
|
||||
Returns:
|
||||
清理后的数据
|
||||
"""
|
||||
# 需要过滤的字段列表
|
||||
fields_to_remove = {
|
||||
'id', 'apply_id', 'user_id', 'chunk_id', 'created_at',
|
||||
'valid_at', 'invalid_at', 'statement_ids'
|
||||
}
|
||||
|
||||
if isinstance(data, dict):
|
||||
cleaned = {}
|
||||
for key, value in data.items():
|
||||
if key == 'statements' and isinstance(value, dict) and 'statements' in value:
|
||||
# 将 statements: {"statements": [...]} 改为 time_search: {"statements": [...]}
|
||||
cleaned_value = clean_temporal_result_fields(value)
|
||||
# 进一步将内部的 statements 改为 time_search
|
||||
if 'statements' in cleaned_value:
|
||||
cleaned['results'] = {
|
||||
'time_search': cleaned_value['statements']
|
||||
}
|
||||
else:
|
||||
cleaned['results'] = cleaned_value
|
||||
elif key not in fields_to_remove:
|
||||
cleaned[key] = clean_temporal_result_fields(value)
|
||||
return cleaned
|
||||
elif isinstance(data, list):
|
||||
return [clean_temporal_result_fields(item) for item in data]
|
||||
else:
|
||||
return data
|
||||
|
||||
@tool
|
||||
def TimeRetrievalWithGroupId(context: str, start_date: str = None, end_date: str = None, end_user_id_param: str = None, clean_output: bool = True) -> str:
|
||||
"""
|
||||
优化的时间检索工具，只结合时间范围搜索（同步版本），自动过滤不需要的元数据字段
|
||||
显式接收参数：
|
||||
- context: 查询上下文内容
|
||||
- start_date: 开始时间（可选，格式：YYYY-MM-DD）
|
||||
- end_date: 结束时间（可选，格式：YYYY-MM-DD）
|
||||
- end_user_id_param: 组ID（可选，用于覆盖默认组ID）
|
||||
- clean_output: 是否清理输出中的元数据字段
|
||||
-end_date 需要根据用户的描述获取结束的时间，输出格式用strftime("%Y-%m-%d")
|
||||
"""
|
||||
async def _async_search():
|
||||
# 使用传入的参数或默认值
|
||||
actual_end_user_id = end_user_id_param or end_user_id
|
||||
actual_end_date = end_date or datetime.now().strftime("%Y-%m-%d")
|
||||
actual_start_date = start_date or (datetime.now() - timedelta(days=7)).strftime("%Y-%m-%d")
|
||||
|
||||
# 基本时间搜索
|
||||
results = await search_by_temporal(
|
||||
end_user_id=actual_end_user_id,
|
||||
start_date=actual_start_date,
|
||||
end_date=actual_end_date,
|
||||
limit=10
|
||||
)
|
||||
|
||||
# 清理结果中不需要的字段
|
||||
if clean_output:
|
||||
cleaned_results = clean_temporal_result_fields(results)
|
||||
else:
|
||||
cleaned_results = results
|
||||
|
||||
return json.dumps(cleaned_results, ensure_ascii=False, indent=2)
|
||||
|
||||
return asyncio.run(_async_search())
|
||||
|
||||
@tool
|
||||
def KeywordTimeRetrieval(context: str, days_back: int = 7, start_date: str = None, end_date: str = None, clean_output: bool = True) -> str:
|
||||
"""
|
||||
优化的关键词时间检索工具，结合关键词和时间范围搜索（同步版本），自动过滤不需要的元数据字段
|
||||
显式接收参数：
|
||||
- context: 查询内容
|
||||
- days_back: 向前搜索的天数，默认7天
|
||||
- start_date: 开始时间（可选，格式：YYYY-MM-DD）
|
||||
- end_date: 结束时间（可选，格式：YYYY-MM-DD）
|
||||
- clean_output: 是否清理输出中的元数据字段
|
||||
- end_date 需要根据用户的描述获取结束的时间，输出格式用strftime("%Y-%m-%d")
|
||||
"""
|
||||
async def _async_search():
|
||||
actual_end_date = end_date or datetime.now().strftime("%Y-%m-%d")
|
||||
actual_start_date = start_date or (datetime.now() - timedelta(days=days_back)).strftime("%Y-%m-%d")
|
||||
|
||||
# 关键词时间搜索
|
||||
results = await search_by_keyword_temporal(
|
||||
query_text=context,
|
||||
end_user_id=end_user_id,
|
||||
start_date=actual_start_date,
|
||||
end_date=actual_end_date,
|
||||
limit=15
|
||||
)
|
||||
|
||||
# 清理结果中不需要的字段
|
||||
if clean_output:
|
||||
cleaned_results = clean_temporal_result_fields(results)
|
||||
else:
|
||||
cleaned_results = results
|
||||
|
||||
return json.dumps(cleaned_results, ensure_ascii=False, indent=2)
|
||||
|
||||
return asyncio.run(_async_search())
|
||||
|
||||
return TimeRetrievalWithGroupId
|
||||
|
||||
|
||||
def create_hybrid_retrieval_tool_async(memory_config, **search_params):
|
||||
"""
|
||||
创建混合检索工具，使用run_hybrid_search进行混合检索，优化输出格式并过滤不需要的字段
|
||||
|
||||
Args:
|
||||
memory_config: 内存配置对象
|
||||
**search_params: 搜索参数，包含end_user_id, limit, include等
|
||||
"""
|
||||
|
||||
def clean_result_fields(data):
|
||||
"""
|
||||
递归清理结果中不需要的字段
|
||||
|
||||
Args:
|
||||
data: 要清理的数据（可能是字典、列表或其他类型）
|
||||
|
||||
Returns:
|
||||
清理后的数据
|
||||
"""
|
||||
# 需要过滤的字段列表
|
||||
fields_to_remove = {
|
||||
'invalid_at', 'valid_at', 'chunk_id_from_rel', 'entity_ids',
|
||||
'expired_at', 'created_at', 'chunk_id', 'id', 'apply_id',
|
||||
'user_id', 'statement_ids', 'updated_at',"chunk_ids","fact_summary"
|
||||
}
|
||||
|
||||
if isinstance(data, dict):
|
||||
# 对字典进行清理
|
||||
cleaned = {}
|
||||
for key, value in data.items():
|
||||
if key not in fields_to_remove:
|
||||
cleaned[key] = clean_result_fields(value) # 递归清理嵌套数据
|
||||
return cleaned
|
||||
elif isinstance(data, list):
|
||||
# 对列表中的每个元素进行清理
|
||||
return [clean_result_fields(item) for item in data]
|
||||
else:
|
||||
# 其他类型直接返回
|
||||
return data
|
||||
|
||||
@tool
|
||||
async def HybridSearch(
|
||||
context: str,
|
||||
search_type: str = "hybrid",
|
||||
limit: int = 10,
|
||||
end_user_id: str = None,
|
||||
rerank_alpha: float = 0.6,
|
||||
use_forgetting_rerank: bool = False,
|
||||
use_llm_rerank: bool = False,
|
||||
clean_output: bool = True # 新增：是否清理输出字段
|
||||
) -> str:
|
||||
"""
|
||||
优化的混合检索工具，支持关键词、向量和混合搜索，自动过滤不需要的元数据字段
|
||||
|
||||
Args:
|
||||
context: 查询内容
|
||||
search_type: 搜索类型 ('keyword', 'embedding', 'hybrid')
|
||||
limit: 结果数量限制
|
||||
end_user_id: 组ID，用于过滤搜索结果
|
||||
rerank_alpha: 重排序权重参数
|
||||
use_forgetting_rerank: 是否使用遗忘重排序
|
||||
use_llm_rerank: 是否使用LLM重排序
|
||||
clean_output: 是否清理输出中的元数据字段
|
||||
"""
|
||||
try:
|
||||
# 导入run_hybrid_search函数
|
||||
from app.core.memory.src.search import run_hybrid_search
|
||||
|
||||
# 合并参数，优先使用传入的参数
|
||||
final_params = {
|
||||
"query_text": context,
|
||||
"search_type": search_type,
|
||||
"end_user_id": end_user_id or search_params.get("end_user_id"),
|
||||
"limit": limit or search_params.get("limit", 10),
|
||||
"include": search_params.get("include", ["summaries", "statements", "chunks", "entities"]),
|
||||
"output_path": None, # 不保存到文件
|
||||
"memory_config": memory_config,
|
||||
"rerank_alpha": rerank_alpha,
|
||||
"use_forgetting_rerank": use_forgetting_rerank,
|
||||
"use_llm_rerank": use_llm_rerank
|
||||
}
|
||||
|
||||
# 执行混合检索
|
||||
raw_results = await run_hybrid_search(**final_params)
|
||||
|
||||
# 清理结果中不需要的字段
|
||||
if clean_output:
|
||||
cleaned_results = clean_result_fields(raw_results)
|
||||
else:
|
||||
cleaned_results = raw_results
|
||||
|
||||
# 格式化返回结果
|
||||
formatted_results = {
|
||||
"search_query": context,
|
||||
"search_type": search_type,
|
||||
"results": cleaned_results
|
||||
}
|
||||
|
||||
return json.dumps(formatted_results, ensure_ascii=False, indent=2, default=str)
|
||||
|
||||
except Exception as e:
|
||||
error_result = {
|
||||
"error": f"混合检索失败: {str(e)}",
|
||||
"search_query": context,
|
||||
"search_type": search_type,
|
||||
"timestamp": datetime.now().isoformat()
|
||||
}
|
||||
return json.dumps(error_result, ensure_ascii=False, indent=2)
|
||||
|
||||
return HybridSearch
|
||||
|
||||
|
||||
def create_hybrid_retrieval_tool_sync(memory_config, **search_params):
|
||||
"""
|
||||
创建同步版本的混合检索工具，优化输出格式并过滤不需要的字段
|
||||
|
||||
Args:
|
||||
memory_config: 内存配置对象
|
||||
**search_params: 搜索参数
|
||||
"""
|
||||
@tool
|
||||
def HybridSearchSync(
|
||||
context: str,
|
||||
search_type: str = "hybrid",
|
||||
limit: int = 10,
|
||||
end_user_id: str = None,
|
||||
clean_output: bool = True
|
||||
) -> str:
|
||||
"""
|
||||
优化的混合检索工具（同步版本），自动过滤不需要的元数据字段
|
||||
|
||||
Args:
|
||||
context: 查询内容
|
||||
search_type: 搜索类型 ('keyword', 'embedding', 'hybrid')
|
||||
limit: 结果数量限制
|
||||
end_user_id: 组ID，用于过滤搜索结果
|
||||
clean_output: 是否清理输出中的元数据字段
|
||||
"""
|
||||
async def _async_search():
|
||||
# 创建异步工具并执行
|
||||
async_tool = create_hybrid_retrieval_tool_async(memory_config, **search_params)
|
||||
return await async_tool.ainvoke({
|
||||
"context": context,
|
||||
"search_type": search_type,
|
||||
"limit": limit,
|
||||
"end_user_id": end_user_id,
|
||||
"clean_output": clean_output
|
||||
})
|
||||
|
||||
return asyncio.run(_async_search())
|
||||
|
||||
return HybridSearchSync
|
||||
@@ -1,93 +1,80 @@
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import sys
|
||||
import warnings
|
||||
from contextlib import asynccontextmanager
|
||||
|
||||
|
||||
from langchain_core.messages import HumanMessage
|
||||
from langgraph.constants import END, START
|
||||
from langgraph.graph import StateGraph
|
||||
|
||||
|
||||
from app.db import get_db
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.core.memory.agent.utils.llm_tools import WriteState
|
||||
from app.core.memory.agent.langgraph_graph.nodes.write_nodes import write_node
|
||||
from app.core.memory.agent.langgraph_graph.nodes.data_nodes import content_input_write
|
||||
from app.services.memory_config_service import MemoryConfigService
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from langchain_core.messages import AIMessage
|
||||
from langgraph.constants import END, START
|
||||
from langgraph.graph import StateGraph
|
||||
from langgraph.prebuilt import ToolNode
|
||||
|
||||
warnings.filterwarnings("ignore", category=RuntimeWarning)
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
if sys.platform.startswith("win"):
|
||||
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
|
||||
|
||||
|
||||
@asynccontextmanager
|
||||
async def make_write_graph():
|
||||
async def make_write_graph(user_id, tools, apply_id, group_id, memory_config: MemoryConfig):
|
||||
"""
|
||||
Create a write graph workflow for memory operations.
|
||||
|
||||
|
||||
Args:
|
||||
user_id: User identifier
|
||||
tools: MCP tools loaded from session
|
||||
apply_id: Application identifier
|
||||
end_user_id: Group identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
"""
|
||||
# workflow = StateGraph(WriteState)
|
||||
# workflow.add_node("content_input", content_input_write)
|
||||
# workflow.add_node("save_neo4j", write_node)
|
||||
# workflow.add_edge(START, "content_input")
|
||||
# workflow.add_edge("content_input", "save_neo4j")
|
||||
# workflow.add_edge("save_neo4j", END)
|
||||
#
|
||||
# graph = workflow.compile()
|
||||
logger.info("Loading MCP tools: %s", [t.name for t in tools])
|
||||
logger.info(f"Using memory_config: {memory_config.config_name} (id={memory_config.config_id})")
|
||||
|
||||
data_write_tool = next((t for t in tools if t.name == "Data_write"), None)
|
||||
|
||||
if not data_write_tool:
|
||||
logger.error("Data_write tool not found", exc_info=True)
|
||||
raise ValueError("Data_write tool not found")
|
||||
|
||||
write_node = ToolNode([data_write_tool])
|
||||
|
||||
async def call_model(state):
|
||||
messages = state["messages"]
|
||||
last_message = messages[-1]
|
||||
content = last_message[1] if isinstance(last_message, tuple) else last_message.content
|
||||
|
||||
# Call Data_write directly with memory_config
|
||||
write_params = {
|
||||
"content": content,
|
||||
"apply_id": apply_id,
|
||||
"group_id": group_id,
|
||||
"user_id": user_id,
|
||||
"memory_config": memory_config,
|
||||
}
|
||||
logger.debug(f"Passing memory_config to Data_write: {memory_config.config_id}")
|
||||
|
||||
write_result = await data_write_tool.ainvoke(write_params)
|
||||
|
||||
if isinstance(write_result, dict):
|
||||
result_content = write_result.get("data", str(write_result))
|
||||
else:
|
||||
result_content = str(write_result)
|
||||
logger.info("Write content: %s", result_content)
|
||||
return {"messages": [AIMessage(content=result_content)]}
|
||||
|
||||
workflow = StateGraph(WriteState)
|
||||
workflow.add_node("content_input", call_model)
|
||||
workflow.add_node("save_neo4j", write_node)
|
||||
workflow.add_edge(START, "save_neo4j")
|
||||
workflow.add_edge(START, "content_input")
|
||||
workflow.add_edge("content_input", "save_neo4j")
|
||||
workflow.add_edge("save_neo4j", END)
|
||||
|
||||
graph = workflow.compile()
|
||||
|
||||
|
||||
yield graph
|
||||
|
||||
|
||||
async def main():
|
||||
"""主函数 - 运行工作流"""
|
||||
message = "今天周一"
|
||||
end_user_id = 'new_2025test1103' # 组ID
|
||||
|
||||
|
||||
# 获取数据库会话
|
||||
db_session = next(get_db())
|
||||
config_service = MemoryConfigService(db_session)
|
||||
memory_config = config_service.load_memory_config(
|
||||
config_id=17, # 改为整数
|
||||
service_name="MemoryAgentService"
|
||||
)
|
||||
try:
|
||||
async with make_write_graph() as graph:
|
||||
config = {"configurable": {"thread_id": end_user_id}}
|
||||
# 初始状态 - 包含所有必要字段
|
||||
initial_state = {"messages": [HumanMessage(content=message)], "end_user_id": end_user_id, "memory_config": memory_config}
|
||||
|
||||
# 获取节点更新信息
|
||||
async for update_event in graph.astream(
|
||||
initial_state,
|
||||
stream_mode="updates",
|
||||
config=config
|
||||
):
|
||||
for node_name, node_data in update_event.items():
|
||||
if 'save_neo4j'==node_name:
|
||||
massages=node_data
|
||||
massages=massages.get('write_result')['status']
|
||||
print(massages) # | 更新数据: {node_data}
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import asyncio
|
||||
asyncio.run(main())
|
||||
28
api/app/core/memory/agent/mcp_server/__init__.py
Normal file
28
api/app/core/memory/agent/mcp_server/__init__.py
Normal file
@@ -0,0 +1,28 @@
|
||||
"""
|
||||
MCP Server package for memory agent.
|
||||
|
||||
This package provides the FastMCP server implementation with context-based
|
||||
dependency injection for tool functions.
|
||||
|
||||
Package structure:
|
||||
- server: FastMCP server initialization and context setup
|
||||
- tools: MCP tool implementations
|
||||
- models: Pydantic response models
|
||||
- services: Business logic services
|
||||
"""
|
||||
# from app.core.memory.agent.mcp_server.server import (
|
||||
# mcp,
|
||||
# initialize_context,
|
||||
# main,
|
||||
# get_context_resource
|
||||
# )
|
||||
|
||||
# # Import tools to register them (but don't export them)
|
||||
# from app.core.memory.agent.mcp_server import tools
|
||||
|
||||
# __all__ = [
|
||||
# 'mcp',
|
||||
# 'initialize_context',
|
||||
# 'main',
|
||||
# 'get_context_resource',
|
||||
# ]
|
||||
11
api/app/core/memory/agent/mcp_server/mcp_instance.py
Normal file
11
api/app/core/memory/agent/mcp_server/mcp_instance.py
Normal file
@@ -0,0 +1,11 @@
|
||||
"""
|
||||
MCP Server Instance
|
||||
|
||||
This module contains the FastMCP server instance that is shared across all modules.
|
||||
It's in a separate file to avoid circular import issues.
|
||||
"""
|
||||
from mcp.server.fastmcp import FastMCP
|
||||
|
||||
# Initialize FastMCP server instance
|
||||
# This instance is shared across all tool modules
|
||||
mcp = FastMCP('data_flow')
|
||||
@@ -0,0 +1,14 @@
|
||||
"""Pydantic models for verification operations."""
|
||||
|
||||
from typing import List, Optional, Dict, Any
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class VerificationResult(BaseModel):
|
||||
"""Result model for verification operation."""
|
||||
|
||||
query: str
|
||||
expansion_issue: List[Dict[str, Any]]
|
||||
split_result: str
|
||||
reason: Optional[str] = None
|
||||
history: List[Dict[str, Any]] = Field(default_factory=list)
|
||||
159
api/app/core/memory/agent/mcp_server/server.py
Normal file
159
api/app/core/memory/agent/mcp_server/server.py
Normal file
@@ -0,0 +1,159 @@
|
||||
"""
|
||||
MCP Server initialization with FastMCP context setup.
|
||||
|
||||
This module initializes the FastMCP server and registers shared resources
|
||||
in the context for dependency injection into tool functions.
|
||||
"""
|
||||
import os
|
||||
import sys
|
||||
|
||||
from app.core.config import settings
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.core.memory.agent.mcp_server.mcp_instance import mcp
|
||||
from app.core.memory.agent.mcp_server.services.search_service import SearchService
|
||||
from app.core.memory.agent.mcp_server.services.session_service import SessionService
|
||||
from app.core.memory.agent.mcp_server.services.template_service import TemplateService
|
||||
from app.core.memory.agent.utils.llm_tools import PROJECT_ROOT_
|
||||
from app.core.memory.agent.utils.redis_tool import store
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
def get_context_resource(ctx, resource_name: str):
|
||||
"""
|
||||
Helper function to retrieve a resource from the FastMCP context.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP Context object (passed to tool functions)
|
||||
resource_name: Name of the resource to retrieve
|
||||
|
||||
Returns:
|
||||
The requested resource
|
||||
|
||||
Raises:
|
||||
AttributeError: If the resource doesn't exist
|
||||
|
||||
Example:
|
||||
@mcp.tool()
|
||||
async def my_tool(ctx: Context):
|
||||
template_service = get_context_resource(ctx, 'template_service')
|
||||
llm_client = get_context_resource(ctx, 'llm_client')
|
||||
"""
|
||||
if not hasattr(ctx, 'fastmcp') or ctx.fastmcp is None:
|
||||
raise RuntimeError("Context does not have fastmcp attribute")
|
||||
|
||||
if not hasattr(ctx.fastmcp, resource_name):
|
||||
raise AttributeError(
|
||||
f"Resource '{resource_name}' not found in context. "
|
||||
f"Available resources: {[k for k in dir(ctx.fastmcp) if not k.startswith('_')]}"
|
||||
)
|
||||
|
||||
return getattr(ctx.fastmcp, resource_name)
|
||||
|
||||
|
||||
def initialize_context():
|
||||
"""
|
||||
Initialize and register shared resources in FastMCP context.
|
||||
|
||||
This function sets up all shared resources that will be available
|
||||
to tool functions via dependency injection through the context parameter.
|
||||
|
||||
Resources are stored as attributes on the FastMCP instance and can be
|
||||
accessed via ctx.fastmcp in tool functions.
|
||||
|
||||
Resources registered:
|
||||
- session_store: RedisSessionStore for session management
|
||||
- llm_client: LLM client for structured API calls
|
||||
- app_settings: Application settings (renamed to avoid conflict with FastMCP settings)
|
||||
- template_service: Service for template rendering
|
||||
- search_service: Service for hybrid search
|
||||
- session_service: Service for session operations
|
||||
"""
|
||||
try:
|
||||
# Register Redis session store
|
||||
logger.info("Registering session_store in context")
|
||||
mcp.session_store = store
|
||||
|
||||
# Note: LLM client is NOT loaded at server startup
|
||||
# It should be loaded dynamically when needed, with config_id passed explicitly
|
||||
# to make_write_graph or make_read_graph functions
|
||||
logger.info("LLM client will be loaded dynamically with config_id when needed")
|
||||
mcp.llm_client = None # Placeholder - actual client loaded per-request with config_id
|
||||
|
||||
# Register application settings (renamed to avoid conflict with FastMCP's settings)
|
||||
logger.info("Registering app_settings in context")
|
||||
mcp.app_settings = settings
|
||||
|
||||
# Register template service
|
||||
template_root = PROJECT_ROOT_ + '/agent/utils/prompt'
|
||||
# logger.info(f"Registering template_service in context with root: {template_root}")
|
||||
template_service = TemplateService(template_root)
|
||||
mcp.template_service = template_service
|
||||
|
||||
# Register search service
|
||||
# logger.info("Registering search_service in context")
|
||||
search_service = SearchService()
|
||||
mcp.search_service = search_service
|
||||
|
||||
# Register session service
|
||||
# logger.info("Registering session_service in context")
|
||||
session_service = SessionService(store)
|
||||
mcp.session_service = session_service
|
||||
|
||||
# logger.info("All context resources registered successfully")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to initialize context: {e}", exc_info=True)
|
||||
raise
|
||||
|
||||
|
||||
def main():
|
||||
"""
|
||||
Main entry point for the MCP server.
|
||||
|
||||
Initializes context and starts the server with SSE transport.
|
||||
"""
|
||||
try:
|
||||
logger.info("Starting MCP server initialization")
|
||||
# Initialize context resources
|
||||
initialize_context()
|
||||
|
||||
# Import and register tools (imports trigger tool registration)
|
||||
from app.core.memory.agent.mcp_server.tools import ( # noqa: F401
|
||||
data_tools,
|
||||
problem_tools,
|
||||
retrieval_tools,
|
||||
summary_tools,
|
||||
verification_tools,
|
||||
)
|
||||
|
||||
# Tools are registered via imports above
|
||||
|
||||
# Get MCP port from environment (default: 8081)
|
||||
mcp_port = int(os.getenv("MCP_PORT", "8081"))
|
||||
logger.info(f"Starting MCP server on {settings.SERVER_IP}:{mcp_port} with SSE transport")
|
||||
|
||||
# Configure DNS rebinding protection for Docker container compatibility
|
||||
from mcp.server.fastmcp.server import TransportSecuritySettings
|
||||
|
||||
# Disable DNS rebinding protection to allow Docker container hostnames
|
||||
# This allows containers to connect using service names like 'mcp-server'
|
||||
mcp.settings.transport_security = TransportSecuritySettings(
|
||||
enable_dns_rebinding_protection=False,
|
||||
)
|
||||
logger.info("DNS rebinding protection: disabled for Docker container compatibility")
|
||||
|
||||
# logger.info(f"Starting MCP server on {settings.SERVER_IP}:{mcp_port} with SSE transport")
|
||||
|
||||
# Run the server with SSE transport for HTTP connections
|
||||
import uvicorn
|
||||
app = mcp.sse_app()
|
||||
uvicorn.run(app, host=settings.SERVER_IP, port=mcp_port, log_level="info")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to start MCP server: {e}", exc_info=True)
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -4,19 +4,22 @@ Parameter Builder for constructing tool call arguments.
|
||||
This service provides tool-specific parameter transformation logic
|
||||
to build correct arguments for each tool type.
|
||||
"""
|
||||
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
class ParameterBuilder:
|
||||
"""Service for building tool call arguments based on tool type."""
|
||||
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the parameter builder."""
|
||||
logger.info("ParameterBuilder initialized")
|
||||
|
||||
|
||||
def build_tool_args(
|
||||
self,
|
||||
tool_name: str,
|
||||
@@ -24,9 +27,10 @@ class ParameterBuilder:
|
||||
tool_call_id: str,
|
||||
search_switch: str,
|
||||
apply_id: str,
|
||||
end_user_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
storage_type: Optional[str] = None,
|
||||
user_rag_memory_id: Optional[str] = None
|
||||
user_rag_memory_id: Optional[str] = None,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Build tool arguments based on tool type.
|
||||
@@ -44,7 +48,8 @@ class ParameterBuilder:
|
||||
tool_call_id: Extracted tool call identifier
|
||||
search_switch: Search routing parameter
|
||||
apply_id: Application identifier
|
||||
end_user_id: Group identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
storage_type: Storage type for the workspace (optional)
|
||||
user_rag_memory_id: User RAG memory ID for knowledge base retrieval (optional)
|
||||
|
||||
@@ -55,18 +60,19 @@ class ParameterBuilder:
|
||||
base_args = {
|
||||
"usermessages": tool_call_id,
|
||||
"apply_id": apply_id,
|
||||
"end_user_id": end_user_id
|
||||
"group_id": group_id,
|
||||
"memory_config": memory_config,
|
||||
}
|
||||
|
||||
|
||||
# Always add storage_type and user_rag_memory_id (with defaults if None)
|
||||
base_args["storage_type"] = storage_type if storage_type is not None else ""
|
||||
base_args["user_rag_memory_id"] = user_rag_memory_id if user_rag_memory_id is not None else ""
|
||||
|
||||
# Tool-specific argument construction
|
||||
if tool_name in ["Verify","Summary", "Summary_fails",'Retrieve_Summary']:
|
||||
# Verify expects dict context
|
||||
if tool_name in ["Verify", "Summary", "Summary_fails", "Retrieve_Summary", "Problem_Extension"]:
|
||||
# These tools expect dict context
|
||||
return {
|
||||
"context": content if isinstance(content, dict) else {},
|
||||
"context": content if isinstance(content, dict) else {"content": content},
|
||||
**base_args
|
||||
}
|
||||
|
||||
@@ -4,21 +4,31 @@ Search Service for executing hybrid search and processing results.
|
||||
This service provides clean search result processing with content extraction
|
||||
and deduplication.
|
||||
"""
|
||||
from typing import List, Tuple, Optional
|
||||
|
||||
from typing import TYPE_CHECKING, List, Optional, Tuple
|
||||
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.core.memory.src.search import run_hybrid_search
|
||||
from app.core.memory.utils.data.text_utils import escape_lucene_query
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
class SearchService:
|
||||
"""Service for executing hybrid search and processing results."""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the search service."""
|
||||
|
||||
def __init__(self, memory_config: "MemoryConfig" = None):
|
||||
"""
|
||||
Initialize the search service.
|
||||
|
||||
Args:
|
||||
memory_config: Optional MemoryConfig for embedding model configuration.
|
||||
If not provided, must be passed to execute_hybrid_search.
|
||||
"""
|
||||
self.memory_config = memory_config
|
||||
logger.info("SearchService initialized")
|
||||
|
||||
def extract_content_from_result(self, result: dict) -> str:
|
||||
@@ -91,21 +101,21 @@ class SearchService:
|
||||
|
||||
async def execute_hybrid_search(
|
||||
self,
|
||||
end_user_id: str,
|
||||
group_id: str,
|
||||
question: str,
|
||||
limit: int = 5,
|
||||
limit: int = 15,
|
||||
search_type: str = "hybrid",
|
||||
include: Optional[List[str]] = None,
|
||||
rerank_alpha: float = 0.4,
|
||||
output_path: str = "search_results.json",
|
||||
return_raw_results: bool = False,
|
||||
memory_config = None
|
||||
memory_config: "MemoryConfig" = None,
|
||||
) -> Tuple[str, str, Optional[dict]]:
|
||||
"""
|
||||
Execute hybrid search and return clean content.
|
||||
|
||||
Args:
|
||||
end_user_id: Group identifier for filtering results
|
||||
group_id: Group identifier for filtering results
|
||||
question: Search query text
|
||||
limit: Maximum number of results to return (default: 5)
|
||||
search_type: Type of search - "hybrid", "keyword", or "embedding" (default: "hybrid")
|
||||
@@ -113,7 +123,7 @@ class SearchService:
|
||||
rerank_alpha: Weight for BM25 scores in reranking (default: 0.4)
|
||||
output_path: Path to save search results (default: "search_results.json")
|
||||
return_raw_results: If True, also return the raw search results as third element (default: False)
|
||||
memory_config: Memory configuration object (required)
|
||||
memory_config: MemoryConfig object for embedding model. Falls back to self.memory_config if not provided.
|
||||
|
||||
Returns:
|
||||
Tuple of (clean_content, cleaned_query, raw_results)
|
||||
@@ -121,21 +131,26 @@ class SearchService:
|
||||
"""
|
||||
if include is None:
|
||||
include = ["statements", "chunks", "entities", "summaries"]
|
||||
|
||||
|
||||
# Use provided memory_config or fall back to instance config
|
||||
config = memory_config or self.memory_config
|
||||
if not config:
|
||||
raise ValueError("memory_config is required for search - either pass it to __init__ or execute_hybrid_search")
|
||||
|
||||
# Clean query
|
||||
cleaned_query = self.clean_query(question)
|
||||
|
||||
|
||||
try:
|
||||
# Execute search
|
||||
# Execute search using memory_config
|
||||
answer = await run_hybrid_search(
|
||||
query_text=cleaned_query,
|
||||
search_type=search_type,
|
||||
end_user_id=end_user_id,
|
||||
group_id=group_id,
|
||||
limit=limit,
|
||||
include=include,
|
||||
output_path=output_path,
|
||||
memory_config=memory_config,
|
||||
rerank_alpha=rerank_alpha
|
||||
memory_config=config,
|
||||
rerank_alpha=rerank_alpha,
|
||||
)
|
||||
|
||||
# Extract results based on search type and include parameter
|
||||
@@ -186,7 +201,7 @@ class SearchService:
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Search failed for query '{question}' in group '{end_user_id}': {e}",
|
||||
f"Search failed for query '{question}' in group '{group_id}': {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Return empty results on failure
|
||||
@@ -59,7 +59,7 @@ class SessionService:
|
||||
self,
|
||||
user_id: str,
|
||||
apply_id: str,
|
||||
end_user_id: str
|
||||
group_id: str
|
||||
) -> List[dict]:
|
||||
"""
|
||||
Retrieve conversation history from Redis.
|
||||
@@ -67,20 +67,20 @@ class SessionService:
|
||||
Args:
|
||||
user_id: User identifier
|
||||
apply_id: Application identifier
|
||||
end_user_id: Group identifier
|
||||
group_id: Group identifier
|
||||
|
||||
Returns:
|
||||
List of conversation history items with Query and Answer keys
|
||||
Returns empty list if no history found or on error
|
||||
"""
|
||||
try:
|
||||
history = self.store.find_user_apply_group(user_id, apply_id, end_user_id)
|
||||
history = self.store.find_user_apply_group(user_id, apply_id, group_id)
|
||||
|
||||
# Validate history structure
|
||||
if not isinstance(history, list):
|
||||
logger.warning(
|
||||
f"Invalid history format for user {user_id}, "
|
||||
f"apply {apply_id}, group {end_user_id}: expected list, got {type(history)}"
|
||||
f"apply {apply_id}, group {group_id}: expected list, got {type(history)}"
|
||||
)
|
||||
return []
|
||||
|
||||
@@ -89,7 +89,7 @@ class SessionService:
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Failed to retrieve history for user {user_id}, "
|
||||
f"apply {apply_id}, group {end_user_id}: {e}",
|
||||
f"apply {apply_id}, group {group_id}: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Return empty list on error to allow execution to continue
|
||||
@@ -100,7 +100,7 @@ class SessionService:
|
||||
user_id: str,
|
||||
query: str,
|
||||
apply_id: str,
|
||||
end_user_id: str,
|
||||
group_id: str,
|
||||
ai_response: str
|
||||
) -> Optional[str]:
|
||||
"""
|
||||
@@ -110,7 +110,7 @@ class SessionService:
|
||||
user_id: User identifier
|
||||
query: User query/message
|
||||
apply_id: Application identifier
|
||||
end_user_id: Group identifier
|
||||
group_id: Group identifier
|
||||
ai_response: AI response/answer
|
||||
|
||||
Returns:
|
||||
@@ -131,7 +131,7 @@ class SessionService:
|
||||
userid=user_id,
|
||||
messages=query,
|
||||
apply_id=apply_id,
|
||||
end_user_id=end_user_id,
|
||||
group_id=group_id,
|
||||
aimessages=ai_response
|
||||
)
|
||||
|
||||
@@ -152,7 +152,7 @@ class SessionService:
|
||||
Duplicates are identified by matching:
|
||||
- sessionid
|
||||
- user_id (id field)
|
||||
- end_user_id
|
||||
- group_id
|
||||
- messages
|
||||
- aimessages
|
||||
|
||||
@@ -3,22 +3,12 @@ Template Service for loading and rendering Jinja2 templates.
|
||||
|
||||
This service provides centralized template management with caching and error handling.
|
||||
"""
|
||||
|
||||
import os
|
||||
from functools import lru_cache
|
||||
from typing import Optional
|
||||
from jinja2 import Environment, FileSystemLoader, Template, TemplateNotFound
|
||||
|
||||
from jinja2 import (
|
||||
Environment,
|
||||
FileSystemLoader,
|
||||
Template,
|
||||
TemplateNotFound,
|
||||
)
|
||||
|
||||
from app.core.logging_config import (
|
||||
get_agent_logger,
|
||||
log_prompt_rendering,
|
||||
)
|
||||
|
||||
from app.core.logging_config import get_agent_logger, log_prompt_rendering
|
||||
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
27
api/app/core/memory/agent/mcp_server/tools/__init__.py
Normal file
27
api/app/core/memory/agent/mcp_server/tools/__init__.py
Normal file
@@ -0,0 +1,27 @@
|
||||
"""
|
||||
MCP Tools module.
|
||||
|
||||
This module contains all MCP tool implementations organized by functionality.
|
||||
|
||||
Tools are organized into the following modules:
|
||||
- problem_tools: Question segmentation and extension
|
||||
- retrieval_tools: Database and context retrieval
|
||||
- verification_tools: Data verification
|
||||
- summary_tools: Summarization and summary retrieval
|
||||
- data_tools: Data type differentiation and writing
|
||||
"""
|
||||
|
||||
# Import all tool modules to register them with the MCP server
|
||||
from . import problem_tools
|
||||
from . import retrieval_tools
|
||||
from . import verification_tools
|
||||
from . import summary_tools
|
||||
from . import data_tools
|
||||
|
||||
__all__ = [
|
||||
'problem_tools',
|
||||
'retrieval_tools',
|
||||
'verification_tools',
|
||||
'summary_tools',
|
||||
'data_tools',
|
||||
]
|
||||
155
api/app/core/memory/agent/mcp_server/tools/data_tools.py
Normal file
155
api/app/core/memory/agent/mcp_server/tools/data_tools.py
Normal file
@@ -0,0 +1,155 @@
|
||||
"""
|
||||
Data Tools for data type differentiation and writing.
|
||||
|
||||
This module contains MCP tools for distinguishing data types and writing data.
|
||||
"""
|
||||
|
||||
import os
|
||||
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.core.memory.agent.mcp_server.mcp_instance import mcp
|
||||
from app.core.memory.agent.mcp_server.models.retrieval_models import (
|
||||
DistinguishTypeResponse,
|
||||
)
|
||||
from app.core.memory.agent.mcp_server.server import get_context_resource
|
||||
from app.core.memory.agent.utils.write_tools import write
|
||||
from app.core.memory.utils.llm.llm_utils import MemoryClientFactory
|
||||
from app.db import get_db_context
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from mcp.server.fastmcp import Context
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Data_type_differentiation(
|
||||
ctx: Context,
|
||||
context: str,
|
||||
memory_config: MemoryConfig,
|
||||
) -> dict:
|
||||
"""
|
||||
Distinguish the type of data (read or write).
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
context: Text to analyze for type differentiation
|
||||
memory_config: MemoryConfig object containing LLM configuration
|
||||
|
||||
Returns:
|
||||
dict: Contains 'context' with the original text and 'type' field
|
||||
"""
|
||||
try:
|
||||
# Extract services from context
|
||||
template_service = get_context_resource(ctx, 'template_service')
|
||||
|
||||
# Get LLM client from memory_config using factory pattern
|
||||
with get_db_context() as db:
|
||||
factory = MemoryClientFactory(db)
|
||||
llm_client = factory.get_llm_client_from_config(memory_config)
|
||||
|
||||
# Render template
|
||||
try:
|
||||
system_prompt = await template_service.render_template(
|
||||
template_name='distinguish_types_prompt.jinja2',
|
||||
operation_name='status_typle',
|
||||
user_query=context
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Template rendering failed for Data_type_differentiation: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"type": "error",
|
||||
"message": f"Prompt rendering failed: {str(e)}"
|
||||
}
|
||||
|
||||
# Call LLM with structured response
|
||||
try:
|
||||
structured = await llm_client.response_structured(
|
||||
messages=[{"role": "system", "content": system_prompt}],
|
||||
response_model=DistinguishTypeResponse
|
||||
)
|
||||
|
||||
result = structured.model_dump()
|
||||
|
||||
# Add context to result
|
||||
result["context"] = context
|
||||
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"LLM call failed for Data_type_differentiation: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"context": context,
|
||||
"type": "error",
|
||||
"message": f"LLM call failed: {str(e)}"
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Data_type_differentiation failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"context": context,
|
||||
"type": "error",
|
||||
"message": str(e)
|
||||
}
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Data_write(
|
||||
ctx: Context,
|
||||
content: str,
|
||||
user_id: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
) -> dict:
|
||||
"""
|
||||
Write data to the database/file system.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
content: Data content to write
|
||||
user_id: User identifier
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
|
||||
Returns:
|
||||
dict: Contains 'status', 'saved_to', and 'data' fields
|
||||
"""
|
||||
try:
|
||||
# Ensure output directory exists
|
||||
os.makedirs("data_output", exist_ok=True)
|
||||
file_path = os.path.join("data_output", "user_data.csv")
|
||||
|
||||
# Write data - clients are constructed inside write() from memory_config
|
||||
await write(
|
||||
content=content,
|
||||
user_id=user_id,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
memory_config=memory_config,
|
||||
)
|
||||
logger.info(f"Write completed successfully! Config: {memory_config.config_name}")
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"saved_to": file_path,
|
||||
"data": content,
|
||||
"config_id": memory_config.config_id,
|
||||
"config_name": memory_config.config_name,
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Data_write failed: {e}", exc_info=True)
|
||||
return {
|
||||
"status": "error",
|
||||
"message": str(e),
|
||||
}
|
||||
304
api/app/core/memory/agent/mcp_server/tools/problem_tools.py
Normal file
304
api/app/core/memory/agent/mcp_server/tools/problem_tools.py
Normal file
@@ -0,0 +1,304 @@
|
||||
"""
|
||||
Problem Tools for question segmentation and extension.
|
||||
|
||||
This module contains MCP tools for breaking down and extending user questions.
|
||||
LLM clients are constructed from MemoryConfig when needed.
|
||||
"""
|
||||
|
||||
import json
|
||||
import time
|
||||
|
||||
from app.core.logging_config import get_agent_logger, log_time
|
||||
from app.core.memory.agent.mcp_server.mcp_instance import mcp
|
||||
from app.core.memory.agent.mcp_server.models.problem_models import (
|
||||
ProblemBreakdownResponse,
|
||||
ProblemExtensionResponse,
|
||||
)
|
||||
from app.core.memory.agent.mcp_server.server import get_context_resource
|
||||
from app.core.memory.agent.utils.messages_tool import Problem_Extension_messages_deal
|
||||
from app.core.memory.utils.llm.llm_utils import MemoryClientFactory
|
||||
from app.db import get_db_context
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from mcp.server.fastmcp import Context
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Split_The_Problem(
|
||||
ctx: Context,
|
||||
sentence: str,
|
||||
sessionid: str,
|
||||
messages_id: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
) -> dict:
|
||||
"""
|
||||
Segment the dialogue or sentence into sub-problems.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
sentence: Original sentence to split
|
||||
sessionid: Session identifier
|
||||
messages_id: Message identifier
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
|
||||
Returns:
|
||||
dict: Contains 'context' (JSON string of split results) and 'original' sentence
|
||||
"""
|
||||
start = time.time()
|
||||
|
||||
try:
|
||||
# Extract services from context
|
||||
template_service = get_context_resource(ctx, "template_service")
|
||||
session_service = get_context_resource(ctx, "session_service")
|
||||
|
||||
# Get LLM client from memory_config
|
||||
with get_db_context() as db:
|
||||
factory = MemoryClientFactory(db)
|
||||
llm_client = factory.get_llm_client_from_config(memory_config)
|
||||
|
||||
# Extract user ID from session
|
||||
user_id = session_service.resolve_user_id(sessionid)
|
||||
|
||||
# Get conversation history
|
||||
history = await session_service.get_history(user_id, apply_id, group_id)
|
||||
# Override with empty list for now (as in original)
|
||||
history = []
|
||||
|
||||
# Render template
|
||||
try:
|
||||
system_prompt = await template_service.render_template(
|
||||
template_name='problem_breakdown_prompt.jinja2',
|
||||
operation_name='split_the_problem',
|
||||
history=history,
|
||||
sentence=sentence
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Template rendering failed for Split_The_Problem: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"context": json.dumps([], ensure_ascii=False),
|
||||
"original": sentence,
|
||||
"error": f"Prompt rendering failed: {str(e)}"
|
||||
}
|
||||
|
||||
# Call LLM with structured response
|
||||
try:
|
||||
structured = await llm_client.response_structured(
|
||||
messages=[{"role": "system", "content": system_prompt}],
|
||||
response_model=ProblemBreakdownResponse
|
||||
)
|
||||
|
||||
# Handle RootModel response with .root attribute access
|
||||
if structured is None:
|
||||
# LLM returned None, use empty list as fallback
|
||||
split_result = json.dumps([], ensure_ascii=False)
|
||||
elif hasattr(structured, 'root') and structured.root is not None:
|
||||
split_result = json.dumps(
|
||||
[item.model_dump() for item in structured.root],
|
||||
ensure_ascii=False
|
||||
)
|
||||
elif isinstance(structured, list):
|
||||
# Fallback: treat structured itself as the list
|
||||
split_result = json.dumps(
|
||||
[item.model_dump() for item in structured],
|
||||
ensure_ascii=False
|
||||
)
|
||||
else:
|
||||
# Last resort: use empty list
|
||||
split_result = json.dumps([], ensure_ascii=False)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"LLM call failed for Split_The_Problem: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
split_result = json.dumps([], ensure_ascii=False)
|
||||
|
||||
logger.info("Problem splitting")
|
||||
logger.info(f"Problem split result: {split_result}")
|
||||
|
||||
# Emit intermediate output for frontend
|
||||
result = {
|
||||
"context": split_result,
|
||||
"original": sentence,
|
||||
"_intermediate": {
|
||||
"type": "problem_split",
|
||||
"data": json.loads(split_result) if split_result else [],
|
||||
"original_query": sentence
|
||||
}
|
||||
}
|
||||
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Split_The_Problem failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"context": json.dumps([], ensure_ascii=False),
|
||||
"original": sentence,
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
finally:
|
||||
# Log execution time
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Problem splitting', duration)
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Problem_Extension(
|
||||
ctx: Context,
|
||||
context: dict,
|
||||
usermessages: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
storage_type: str = "",
|
||||
user_rag_memory_id: str = "",
|
||||
) -> dict:
|
||||
"""
|
||||
Extend the problem with additional sub-questions.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
context: Dictionary containing split problem results
|
||||
usermessages: User messages identifier
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
storage_type: Storage type for the workspace (optional)
|
||||
user_rag_memory_id: User RAG memory identifier (optional)
|
||||
|
||||
Returns:
|
||||
dict: Contains 'context' (aggregated questions) and 'original' question
|
||||
"""
|
||||
start = time.time()
|
||||
|
||||
try:
|
||||
# Extract services from context
|
||||
template_service = get_context_resource(ctx, "template_service")
|
||||
session_service = get_context_resource(ctx, "session_service")
|
||||
|
||||
# Get LLM client from memory_config
|
||||
with get_db_context() as db:
|
||||
factory = MemoryClientFactory(db)
|
||||
llm_client = factory.get_llm_client_from_config(memory_config)
|
||||
|
||||
# Resolve session ID from usermessages
|
||||
from app.core.memory.agent.utils.messages_tool import Resolve_username
|
||||
sessionid = Resolve_username(usermessages)
|
||||
|
||||
# Get conversation history
|
||||
history = await session_service.get_history(sessionid, apply_id, group_id)
|
||||
# Override with empty list for now (as in original)
|
||||
history = []
|
||||
|
||||
# Process context to extract questions
|
||||
extent_quest, original = await Problem_Extension_messages_deal(context)
|
||||
|
||||
# Format questions for template rendering
|
||||
questions_formatted = []
|
||||
for msg in extent_quest:
|
||||
if msg.get("role") == "user":
|
||||
questions_formatted.append(msg.get("content", ""))
|
||||
|
||||
# Render template
|
||||
try:
|
||||
system_prompt = await template_service.render_template(
|
||||
template_name='Problem_Extension_prompt.jinja2',
|
||||
operation_name='problem_extension',
|
||||
history=history,
|
||||
questions=questions_formatted
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Template rendering failed for Problem_Extension: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"context": {},
|
||||
"original": original,
|
||||
"error": f"Prompt rendering failed: {str(e)}"
|
||||
}
|
||||
|
||||
# Call LLM with structured response
|
||||
try:
|
||||
response_content = await llm_client.response_structured(
|
||||
messages=[{"role": "system", "content": system_prompt}],
|
||||
response_model=ProblemExtensionResponse
|
||||
)
|
||||
|
||||
# Aggregate results by original question
|
||||
aggregated_dict = {}
|
||||
for item in response_content.root:
|
||||
key = getattr(item, "original_question", None) or (
|
||||
item.get("original_question") if isinstance(item, dict) else None
|
||||
)
|
||||
value = getattr(item, "extended_question", None) or (
|
||||
item.get("extended_question") if isinstance(item, dict) else None
|
||||
)
|
||||
if not key or not value:
|
||||
continue
|
||||
aggregated_dict.setdefault(key, []).append(value)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"LLM call failed for Problem_Extension: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
aggregated_dict = {}
|
||||
|
||||
logger.info("Problem extension")
|
||||
logger.info(f"Problem extension result: {aggregated_dict}")
|
||||
|
||||
# Emit intermediate output for frontend
|
||||
result = {
|
||||
"context": aggregated_dict,
|
||||
"original": original,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"_intermediate": {
|
||||
"type": "problem_extension",
|
||||
"data": aggregated_dict,
|
||||
"original_query": original,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
}
|
||||
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Problem_Extension failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"context": {},
|
||||
"original": context.get("original", ""),
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
finally:
|
||||
# Log execution time
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Problem extension', duration)
|
||||
294
api/app/core/memory/agent/mcp_server/tools/retrieval_tools.py
Normal file
294
api/app/core/memory/agent/mcp_server/tools/retrieval_tools.py
Normal file
@@ -0,0 +1,294 @@
|
||||
"""
|
||||
Retrieval Tools for database and context retrieval.
|
||||
|
||||
This module contains MCP tools for retrieving data using hybrid search.
|
||||
"""
|
||||
|
||||
import os
|
||||
import time
|
||||
|
||||
from app.core.logging_config import get_agent_logger, log_time
|
||||
from app.core.memory.agent.mcp_server.mcp_instance import mcp
|
||||
from app.core.memory.agent.mcp_server.server import get_context_resource
|
||||
from app.core.memory.agent.utils.llm_tools import (
|
||||
deduplicate_entries,
|
||||
merge_to_key_value_pairs,
|
||||
)
|
||||
from app.core.memory.agent.utils.messages_tool import Retriev_messages_deal
|
||||
from app.core.rag.nlp.search import knowledge_retrieval
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from dotenv import load_dotenv
|
||||
from mcp.server.fastmcp import Context
|
||||
|
||||
load_dotenv()
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Retrieve(
|
||||
ctx: Context,
|
||||
context,
|
||||
usermessages: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
storage_type: str = "",
|
||||
user_rag_memory_id: str = "",
|
||||
) -> dict:
|
||||
"""
|
||||
Retrieve data from the database using hybrid search.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
context: Dictionary or string containing query information
|
||||
usermessages: User messages identifier
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
storage_type: Storage type for the workspace (e.g., 'rag', 'vector')
|
||||
user_rag_memory_id: User RAG memory identifier
|
||||
|
||||
Returns:
|
||||
dict: Contains 'context' with Query and Expansion_issue results
|
||||
"""
|
||||
kb_config = {
|
||||
"knowledge_bases": [
|
||||
{
|
||||
"kb_id": user_rag_memory_id,
|
||||
"similarity_threshold": 0.7,
|
||||
"vector_similarity_weight": 0.5,
|
||||
"top_k": 10,
|
||||
"retrieve_type": "participle"
|
||||
}
|
||||
],
|
||||
"merge_strategy": "weight",
|
||||
"reranker_id": os.getenv('reranker_id'),
|
||||
"reranker_top_k": 10
|
||||
}
|
||||
start = time.time()
|
||||
logger.info(f"Retrieve: storage_type={storage_type}, user_rag_memory_id={user_rag_memory_id}")
|
||||
logger.info(f"Retrieve: context type={type(context)}, context={str(context)[:500]}")
|
||||
|
||||
try:
|
||||
# Extract services from context
|
||||
search_service = get_context_resource(ctx, 'search_service')
|
||||
|
||||
databases_anser = []
|
||||
|
||||
# Handle both dict and string context
|
||||
if isinstance(context, dict):
|
||||
# Process dict context with extended questions
|
||||
all_items = []
|
||||
logger.info(f"Retrieve: context keys={list(context.keys())}")
|
||||
content, original = await Retriev_messages_deal(context)
|
||||
logger.info(f"Retrieve: after Retriev_messages_deal - content_type={type(content)}, content={str(content)[:300]}")
|
||||
logger.info(f"Retrieve: original='{original[:100] if original else 'EMPTY'}'")
|
||||
|
||||
if not original:
|
||||
logger.warning(f"Retrieve: original query is empty! context={context}")
|
||||
|
||||
# Extract all query items from content
|
||||
# content is like {original_question: [extended_questions...], ...}
|
||||
for key, values in content.items():
|
||||
if isinstance(values, list):
|
||||
all_items.extend(values)
|
||||
elif isinstance(values, str):
|
||||
all_items.append(values)
|
||||
elif values is not None:
|
||||
# Fallback: convert non-empty non-list values to string
|
||||
all_items.append(str(values))
|
||||
|
||||
# Execute search for each question
|
||||
for idx, question in enumerate(all_items):
|
||||
try:
|
||||
# Prepare search parameters based on storage type
|
||||
search_params = {
|
||||
"group_id": group_id,
|
||||
"question": question,
|
||||
"return_raw_results": True
|
||||
}
|
||||
|
||||
# Add storage-specific parameters
|
||||
if storage_type == "rag" and user_rag_memory_id:
|
||||
retrieve_chunks_result = knowledge_retrieval(question, kb_config,[str(group_id)])
|
||||
try:
|
||||
retrieval_knowledge = [i.page_content for i in retrieve_chunks_result]
|
||||
clean_content = '\n\n'.join(retrieval_knowledge)
|
||||
cleaned_query=question
|
||||
raw_results=clean_content
|
||||
logger.info(f" Using RAG storage with memory_id={user_rag_memory_id}")
|
||||
except:
|
||||
clean_content = ''
|
||||
raw_results=''
|
||||
cleaned_query = question
|
||||
logger.info(f"No content retrieved from knowledge base: {user_rag_memory_id}")
|
||||
else:
|
||||
clean_content, cleaned_query, raw_results = await search_service.execute_hybrid_search(
|
||||
**search_params, memory_config=memory_config
|
||||
)
|
||||
|
||||
databases_anser.append({
|
||||
"Query_small": cleaned_query,
|
||||
"Result_small": clean_content,
|
||||
"_intermediate": {
|
||||
"type": "search_result",
|
||||
"query": cleaned_query,
|
||||
"raw_results": raw_results,
|
||||
"index": idx + 1,
|
||||
"total": len(all_items)
|
||||
}
|
||||
})
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Retrieve: hybrid_search failed for question '{question}': {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Continue with empty result for this question
|
||||
databases_anser.append({
|
||||
"Query_small": question,
|
||||
"Result_small": ""
|
||||
})
|
||||
|
||||
# Build initial database data structure
|
||||
databases_data = {
|
||||
"Query": original,
|
||||
"Expansion_issue": databases_anser
|
||||
}
|
||||
|
||||
# Collect intermediate outputs before deduplication
|
||||
intermediate_outputs = []
|
||||
for item in databases_anser:
|
||||
if '_intermediate' in item:
|
||||
intermediate_outputs.append(item['_intermediate'])
|
||||
|
||||
# Deduplicate and merge results
|
||||
deduplicated_data = deduplicate_entries(databases_data['Expansion_issue'])
|
||||
deduplicated_data_merged = merge_to_key_value_pairs(
|
||||
deduplicated_data,
|
||||
'Query_small',
|
||||
'Result_small'
|
||||
)
|
||||
|
||||
# Restructure for Verify/Retrieve_Summary compatibility
|
||||
keys, val = [], []
|
||||
for item in deduplicated_data_merged:
|
||||
for items_key, items_value in item.items():
|
||||
keys.append(items_key)
|
||||
val.append(items_value)
|
||||
|
||||
send_verify = []
|
||||
for i, j in zip(keys, val, strict=False):
|
||||
send_verify.append({
|
||||
"Query_small": i,
|
||||
"Answer_Small": j
|
||||
})
|
||||
|
||||
dup_databases = {
|
||||
"Query": original,
|
||||
"Expansion_issue": send_verify,
|
||||
"_intermediate_outputs": intermediate_outputs # Preserve intermediate outputs
|
||||
}
|
||||
|
||||
logger.info(f"Collected {len(intermediate_outputs)} intermediate outputs from search results")
|
||||
|
||||
else:
|
||||
# Handle string context (simple query)
|
||||
query = str(context).strip()
|
||||
|
||||
try:
|
||||
# Prepare search parameters based on storage type
|
||||
search_params = {
|
||||
"group_id": group_id,
|
||||
"question": query,
|
||||
"return_raw_results": True
|
||||
}
|
||||
|
||||
# Add storage-specific parameters
|
||||
if storage_type == "rag" and user_rag_memory_id:
|
||||
retrieve_chunks_result = knowledge_retrieval(query, kb_config,[str(group_id)])
|
||||
try:
|
||||
retrieval_knowledge = [i.page_content for i in retrieve_chunks_result]
|
||||
clean_content = '\n\n'.join(retrieval_knowledge)
|
||||
cleaned_query = query
|
||||
raw_results = clean_content
|
||||
logger.info(f" Using RAG storage with memory_id={user_rag_memory_id}")
|
||||
except:
|
||||
clean_content = ''
|
||||
raw_results = ''
|
||||
cleaned_query = query
|
||||
logger.info(f"No content retrieved from knowledge base: {user_rag_memory_id}")
|
||||
else:
|
||||
clean_content, cleaned_query, raw_results = await search_service.execute_hybrid_search(
|
||||
**search_params, memory_config=memory_config
|
||||
)
|
||||
# Keep structure for Verify/Retrieve_Summary compatibility
|
||||
dup_databases = {
|
||||
"Query": cleaned_query,
|
||||
"Expansion_issue": [{
|
||||
"Query_small": cleaned_query,
|
||||
"Answer_Small": clean_content,
|
||||
"_intermediate": {
|
||||
"type": "search_result",
|
||||
"query": cleaned_query,
|
||||
"raw_results": raw_results,
|
||||
"index": 1,
|
||||
"total": 1
|
||||
}
|
||||
}]
|
||||
}
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Retrieve: hybrid_search failed for query '{query}': {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Return empty results on failure
|
||||
dup_databases = {
|
||||
"Query": query,
|
||||
"Expansion_issue": []
|
||||
}
|
||||
|
||||
logger.info(
|
||||
f"Retrieval: {storage_type}--{user_rag_memory_id}--Query={dup_databases.get('Query', '')}, "
|
||||
f"Expansion_issue count={len(dup_databases.get('Expansion_issue', []))}"
|
||||
)
|
||||
|
||||
# Build result with intermediate outputs
|
||||
result = {
|
||||
"context": dup_databases,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
|
||||
# Add intermediate outputs list if they exist
|
||||
intermediate_outputs = dup_databases.get('_intermediate_outputs', [])
|
||||
if intermediate_outputs:
|
||||
result['_intermediates'] = intermediate_outputs
|
||||
logger.info(f"Adding {len(intermediate_outputs)} intermediate outputs to result")
|
||||
else:
|
||||
logger.warning("No intermediate outputs found in dup_databases")
|
||||
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Retrieve failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"context": {
|
||||
"Query": "",
|
||||
"Expansion_issue": []
|
||||
},
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
finally:
|
||||
# Log execution time
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Retrieval', duration)
|
||||
666
api/app/core/memory/agent/mcp_server/tools/summary_tools.py
Normal file
666
api/app/core/memory/agent/mcp_server/tools/summary_tools.py
Normal file
@@ -0,0 +1,666 @@
|
||||
"""
|
||||
Summary Tools for data summarization.
|
||||
|
||||
This module contains MCP tools for summarizing retrieved data and generating responses.
|
||||
LLM clients are constructed from MemoryConfig when needed.
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
|
||||
from app.core.logging_config import get_agent_logger, log_time
|
||||
from app.core.memory.agent.mcp_server.mcp_instance import mcp
|
||||
from app.core.memory.agent.mcp_server.models.summary_models import (
|
||||
RetrieveSummaryResponse,
|
||||
SummaryResponse,
|
||||
)
|
||||
from app.core.memory.agent.mcp_server.server import get_context_resource
|
||||
from app.core.memory.agent.utils.messages_tool import (
|
||||
Resolve_username,
|
||||
Summary_messages_deal,
|
||||
)
|
||||
from app.core.memory.utils.llm.llm_utils import MemoryClientFactory
|
||||
from app.core.rag.nlp.search import knowledge_retrieval
|
||||
from app.db import get_db_context
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from dotenv import load_dotenv
|
||||
from mcp.server.fastmcp import Context
|
||||
|
||||
load_dotenv()
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Summary(
|
||||
ctx: Context,
|
||||
context: str,
|
||||
usermessages: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
storage_type: str = "",
|
||||
user_rag_memory_id: str = "",
|
||||
) -> dict:
|
||||
"""
|
||||
Summarize the verified data.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
context: JSON string containing verified data
|
||||
usermessages: User messages identifier
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
storage_type: Storage type for the workspace (optional)
|
||||
user_rag_memory_id: User RAG memory identifier (optional)
|
||||
|
||||
Returns:
|
||||
dict: Contains 'status' and 'summary_result'
|
||||
"""
|
||||
start = time.time()
|
||||
|
||||
try:
|
||||
# Extract services from context
|
||||
template_service = get_context_resource(ctx, "template_service")
|
||||
session_service = get_context_resource(ctx, "session_service")
|
||||
|
||||
# Get LLM client from memory_config
|
||||
with get_db_context() as db:
|
||||
factory = MemoryClientFactory(db)
|
||||
llm_client = factory.get_llm_client_from_config(memory_config)
|
||||
|
||||
# Resolve session ID
|
||||
sessionid = Resolve_username(usermessages)
|
||||
|
||||
# Process context to extract answer and query
|
||||
answer_small, query = await Summary_messages_deal(context)
|
||||
|
||||
|
||||
start_time= time.time()
|
||||
history = await session_service.get_history(sessionid, apply_id, group_id)
|
||||
end_time=time.time()
|
||||
logger.info(f"Retrieve_Summary-REDIS搜索：{end_time - start_time}")
|
||||
data = {
|
||||
"query": query,
|
||||
"history": history,
|
||||
"retrieve_info": answer_small
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Summary: initialization failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"status": "error",
|
||||
"summary_result": "信息不足，无法回答"
|
||||
}
|
||||
|
||||
try:
|
||||
# Render template
|
||||
system_prompt = await template_service.render_template(
|
||||
template_name='summary_prompt.jinja2',
|
||||
operation_name='summary',
|
||||
data=data,
|
||||
query=query
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Template rendering failed for Summary: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"status": "error",
|
||||
"message": f"Prompt rendering failed: {str(e)}"
|
||||
}
|
||||
|
||||
try:
|
||||
# Call LLM with structured response
|
||||
structured = await llm_client.response_structured(
|
||||
messages=[{"role": "system", "content": system_prompt}],
|
||||
response_model=SummaryResponse
|
||||
)
|
||||
|
||||
aimessages = structured.query_answer or ""
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"LLM call failed for Summary: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
aimessages = ""
|
||||
|
||||
try:
|
||||
# Save session
|
||||
if aimessages != "":
|
||||
await session_service.save_session(
|
||||
user_id=sessionid,
|
||||
query=query,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
ai_response=aimessages
|
||||
)
|
||||
logger.info(f"sessionid: {aimessages} 写入成功")
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"sessionid: {sessionid} 写入失败，错误信息：{str(e)}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"status": "error",
|
||||
"message": str(e)
|
||||
}
|
||||
|
||||
# Cleanup duplicate sessions
|
||||
await session_service.cleanup_duplicates()
|
||||
|
||||
# Use fallback if empty
|
||||
if aimessages == '':
|
||||
aimessages = '信息不足，无法回答'
|
||||
|
||||
logger.info(f"Summary after verification: {aimessages}")
|
||||
|
||||
# Log execution time
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Summary', duration)
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"summary_result": aimessages,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Retrieve_Summary(
|
||||
ctx: Context,
|
||||
context: dict,
|
||||
usermessages: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
storage_type: str = "",
|
||||
user_rag_memory_id: str = "",
|
||||
) -> dict:
|
||||
"""
|
||||
Summarize data directly from retrieval results.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
context: Dictionary containing Query and Expansion_issue from Retrieve
|
||||
usermessages: User messages identifier
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
storage_type: Storage type for the workspace (optional)
|
||||
user_rag_memory_id: User RAG memory identifier (optional)
|
||||
|
||||
Returns:
|
||||
dict: Contains 'status' and 'summary_result'
|
||||
"""
|
||||
start = time.time()
|
||||
|
||||
try:
|
||||
# Extract services from context
|
||||
template_service = get_context_resource(ctx, "template_service")
|
||||
session_service = get_context_resource(ctx, "session_service")
|
||||
|
||||
# Get LLM client from memory_config
|
||||
with get_db_context() as db:
|
||||
factory = MemoryClientFactory(db)
|
||||
llm_client = factory.get_llm_client_from_config(memory_config)
|
||||
|
||||
# Resolve session ID
|
||||
sessionid = Resolve_username(usermessages)
|
||||
|
||||
|
||||
|
||||
# Handle both 'content' and 'context' keys (LangGraph uses 'content')
|
||||
logger.debug(f"Retrieve_Summary: raw context type={type(context)}, keys={list(context.keys()) if isinstance(context, dict) else 'N/A'}")
|
||||
|
||||
if isinstance(context, dict):
|
||||
if "content" in context:
|
||||
inner = context["content"]
|
||||
# If it's a JSON string, parse it
|
||||
if isinstance(inner, str):
|
||||
try:
|
||||
parsed = json.loads(inner)
|
||||
logger.info("Retrieve_Summary: successfully parsed JSON")
|
||||
except json.JSONDecodeError:
|
||||
# Try unescaping first
|
||||
try:
|
||||
unescaped = inner.encode('utf-8').decode('unicode_escape')
|
||||
parsed = json.loads(unescaped)
|
||||
logger.info("Retrieve_Summary: parsed after unescaping")
|
||||
except (json.JSONDecodeError, UnicodeDecodeError) as e:
|
||||
logger.error(
|
||||
f"Retrieve_Summary: parsing failed even after unescape: {e}"
|
||||
)
|
||||
context_dict = {"Query": "", "Expansion_issue": []}
|
||||
parsed = None
|
||||
|
||||
if parsed:
|
||||
# Check if parsed has 'context' wrapper
|
||||
if isinstance(parsed, dict) and "context" in parsed:
|
||||
context_dict = parsed["context"]
|
||||
else:
|
||||
context_dict = parsed
|
||||
elif isinstance(inner, dict):
|
||||
context_dict = inner
|
||||
else:
|
||||
context_dict = {"Query": "", "Expansion_issue": []}
|
||||
elif "context" in context:
|
||||
context_dict = context["context"] if isinstance(context["context"], dict) else context
|
||||
else:
|
||||
context_dict = context
|
||||
else:
|
||||
context_dict = {"Query": "", "Expansion_issue": []}
|
||||
|
||||
query = context_dict.get("Query", "")
|
||||
expansion_issue = context_dict.get("Expansion_issue", [])
|
||||
|
||||
logger.debug(f"Retrieve_Summary: query='{query}', expansion_issue count={len(expansion_issue)}")
|
||||
logger.debug(f"Retrieve_Summary: expansion_issue={expansion_issue[:2] if expansion_issue else 'empty'}")
|
||||
|
||||
# Extract retrieve_info from expansion_issue
|
||||
retrieve_info = []
|
||||
for item in expansion_issue:
|
||||
# Check for both Answer_Small and Answer_Small (typo) for backward compatibility
|
||||
answer = None
|
||||
if isinstance(item, dict):
|
||||
if "Answer_Small" in item:
|
||||
answer = item["Answer_Small"]
|
||||
|
||||
|
||||
if answer is not None:
|
||||
# Handle both string and list formats
|
||||
if isinstance(answer, list):
|
||||
# Join list of characters/strings into a single string
|
||||
retrieve_info.append(''.join(str(x) for x in answer))
|
||||
elif isinstance(answer, str):
|
||||
retrieve_info.append(answer)
|
||||
else:
|
||||
retrieve_info.append(str(answer))
|
||||
|
||||
# Join all retrieve_info into a single string
|
||||
retrieve_info_str = '\n\n'.join(retrieve_info) if retrieve_info else ""
|
||||
|
||||
start_time=time.time()
|
||||
history = await session_service.get_history(sessionid, apply_id, group_id)
|
||||
# Override with empty list for now (as in original)
|
||||
end_time=time.time()
|
||||
logger.info(f"Retrieve_Summary-REDIS搜索：{end_time - start_time}")
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Retrieve_Summary: initialization failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"status": "error",
|
||||
"summary_result": "信息不足，无法回答"
|
||||
}
|
||||
|
||||
try:
|
||||
# Render template
|
||||
system_prompt = await template_service.render_template(
|
||||
template_name='Retrieve_Summary_prompt.jinja2',
|
||||
operation_name='retrieve_summary',
|
||||
query=query,
|
||||
history=history,
|
||||
retrieve_info=retrieve_info_str
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Template rendering failed for Retrieve_Summary: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"status": "error",
|
||||
"message": f"Prompt rendering failed: {str(e)}"
|
||||
}
|
||||
|
||||
try:
|
||||
# Call LLM with structured response
|
||||
structured = await llm_client.response_structured(
|
||||
messages=[{"role": "system", "content": system_prompt}],
|
||||
response_model=RetrieveSummaryResponse
|
||||
)
|
||||
|
||||
# Handle case where structured response might be None or incomplete
|
||||
if structured and hasattr(structured, 'data') and structured.data:
|
||||
aimessages = structured.data.query_answer or ""
|
||||
else:
|
||||
logger.warning("Structured response is None or incomplete, using default message")
|
||||
aimessages = "信息不足，无法回答"
|
||||
|
||||
|
||||
# Check for insufficient information response
|
||||
if '信息不足，无法回答' not in str(aimessages) or str(aimessages)!="":
|
||||
# Save session
|
||||
await session_service.save_session(
|
||||
user_id=sessionid,
|
||||
query=query,
|
||||
apply_id=apply_id,
|
||||
group_id=group_id,
|
||||
ai_response=aimessages
|
||||
)
|
||||
logger.info(f"sessionid: {aimessages} 写入成功")
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Retrieve_Summary: LLM call failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
aimessages = ""
|
||||
# Cleanup duplicate sessions
|
||||
await session_service.cleanup_duplicates()
|
||||
|
||||
# Use fallback if empty
|
||||
if aimessages == '':
|
||||
aimessages = '信息不足，无法回答'
|
||||
|
||||
logger.info(f"Summary after retrieval: {aimessages}")
|
||||
|
||||
# Log execution time
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Retrieval summary', duration)
|
||||
|
||||
# Emit intermediate output for frontend
|
||||
return {
|
||||
"status": "success",
|
||||
"summary_result": aimessages,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"_intermediate": {
|
||||
"type": "retrieval_summary",
|
||||
"summary": aimessages,
|
||||
"query": query,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Input_Summary(
|
||||
ctx: Context,
|
||||
context: str,
|
||||
usermessages: str,
|
||||
search_switch: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
storage_type: str = "",
|
||||
user_rag_memory_id: str = "",
|
||||
) -> dict:
|
||||
"""
|
||||
Generate a quick summary for direct input without verification.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
context: String containing the input sentence
|
||||
usermessages: User messages identifier
|
||||
search_switch: Search switch value for routing ('2' for summaries only)
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
storage_type: Storage type for the workspace (e.g., 'rag', 'vector')
|
||||
user_rag_memory_id: User RAG memory identifier
|
||||
|
||||
Returns:
|
||||
dict: Contains 'query_answer' with the summary result
|
||||
"""
|
||||
start = time.time()
|
||||
logger.info(f"Input_Summary: storage_type={storage_type}, user_rag_memory_id={user_rag_memory_id}")
|
||||
|
||||
try:
|
||||
# Extract services from context
|
||||
template_service = get_context_resource(ctx, "template_service")
|
||||
session_service = get_context_resource(ctx, "session_service")
|
||||
search_service = get_context_resource(ctx, "search_service")
|
||||
|
||||
# Get LLM client from memory_config
|
||||
with get_db_context() as db:
|
||||
factory = MemoryClientFactory(db)
|
||||
llm_client = factory.get_llm_client_from_config(memory_config)
|
||||
|
||||
# Resolve session ID
|
||||
sessionid = Resolve_username(usermessages) or ""
|
||||
sessionid = sessionid.replace('call_id_', '')
|
||||
|
||||
start_time=time.time()
|
||||
history = await session_service.get_history(
|
||||
str(sessionid),
|
||||
str(apply_id),
|
||||
str(group_id)
|
||||
)
|
||||
end_time=time.time()
|
||||
logger.info(f"Input_Summary-REDIS搜索：{end_time - start_time}")
|
||||
# Override with empty list for now (as in original)
|
||||
|
||||
# Log the raw context for debugging
|
||||
logger.info(f"Input_Summary: Received context type={type(context)}, value={context[:200] if isinstance(context, str) else context}")
|
||||
|
||||
# Extract sentence from context
|
||||
# Context can be a string or might contain the sentence in various formats
|
||||
try:
|
||||
# Try to parse as JSON first
|
||||
if isinstance(context, str) and (context.startswith('{') or context.startswith('[')):
|
||||
try:
|
||||
import json
|
||||
context_dict = json.loads(context)
|
||||
if isinstance(context_dict, dict):
|
||||
query = context_dict.get('sentence', context_dict.get('content', context))
|
||||
else:
|
||||
query = context
|
||||
except json.JSONDecodeError:
|
||||
# Not valid JSON, try regex
|
||||
match = re.search(r"'sentence':\s*['\"]?(.*?)['\"]?\s*,", context)
|
||||
query = match.group(1) if match else context
|
||||
else:
|
||||
query = context
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to extract query from context: {e}")
|
||||
query = context
|
||||
|
||||
# Clean query
|
||||
query = str(query).strip().strip("\"'")
|
||||
|
||||
logger.debug(f"Input_Summary: Extracted query='{query}' from context type={type(context)}")
|
||||
|
||||
# Execute search based on search_switch and storage_type
|
||||
try:
|
||||
logger.info(f"search_switch: {search_switch}, storage_type: {storage_type}")
|
||||
|
||||
# Prepare search parameters based on storage type
|
||||
search_params = {
|
||||
"group_id": group_id,
|
||||
"question": query,
|
||||
"return_raw_results": True
|
||||
}
|
||||
|
||||
# Add storage-specific parameters
|
||||
|
||||
# Retrieval
|
||||
if search_switch == '2':
|
||||
search_params["include"] = ["summaries"]
|
||||
if storage_type == "rag" and user_rag_memory_id:
|
||||
raw_results = []
|
||||
retrieve_info = ""
|
||||
kb_config={
|
||||
"knowledge_bases": [
|
||||
{
|
||||
"kb_id": user_rag_memory_id,
|
||||
"similarity_threshold": 0.7,
|
||||
"vector_similarity_weight": 0.5,
|
||||
"top_k": 10,
|
||||
"retrieve_type": "participle"
|
||||
}
|
||||
],
|
||||
"merge_strategy": "weight",
|
||||
"reranker_id":os.getenv('reranker_id'),
|
||||
"reranker_top_k": 10
|
||||
}
|
||||
|
||||
retrieve_chunks_result = knowledge_retrieval(query, kb_config,[str(group_id)])
|
||||
try:
|
||||
retrieval_knowledge = [i.page_content for i in retrieve_chunks_result]
|
||||
retrieve_info = '\n\n'.join(retrieval_knowledge)
|
||||
raw_results=[retrieve_info]
|
||||
logger.info(f"Input_Summary: Using RAG storage with memory_id={user_rag_memory_id}")
|
||||
except:
|
||||
retrieve_info=''
|
||||
raw_results=['']
|
||||
logger.info(f"No content retrieved from knowledge base: {user_rag_memory_id}")
|
||||
else:
|
||||
retrieve_info, question, raw_results = await search_service.execute_hybrid_search(
|
||||
**search_params, memory_config=memory_config
|
||||
)
|
||||
logger.info("Input_Summary: Using summary for retrieval")
|
||||
else:
|
||||
retrieve_info, question, raw_results = await search_service.execute_hybrid_search(
|
||||
**search_params, memory_config=memory_config
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Input_Summary: hybrid_search failed, using empty results: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
retrieve_info, question, raw_results = "", query, []
|
||||
|
||||
|
||||
# Render template
|
||||
system_prompt = await template_service.render_template(
|
||||
template_name='Retrieve_Summary_prompt.jinja2',
|
||||
operation_name='input_summary',
|
||||
query=query,
|
||||
history=history,
|
||||
retrieve_info=retrieve_info
|
||||
)
|
||||
|
||||
# Call LLM with structured response
|
||||
try:
|
||||
structured = await llm_client.response_structured(
|
||||
messages=[{"role": "system", "content": system_prompt}],
|
||||
response_model=RetrieveSummaryResponse
|
||||
)
|
||||
aimessages = structured.data.query_answer or "信息不足，无法回答"
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Input_Summary: response_structured failed, using default answer: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
aimessages = "信息不足，无法回答"
|
||||
|
||||
logger.info(f"Quick answer summary: {storage_type}--{user_rag_memory_id}--{aimessages}")
|
||||
|
||||
# Emit intermediate output for frontend
|
||||
return {
|
||||
"status": "success",
|
||||
"summary_result": aimessages,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"_intermediate": {
|
||||
"type": "input_summary",
|
||||
"title": "快速答案",
|
||||
"summary": aimessages,
|
||||
"query": query,
|
||||
"raw_results": raw_results,
|
||||
"search_mode": "quick_search",
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Input_Summary failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"status": "fail",
|
||||
"summary_result": "信息不足，无法回答",
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
finally:
|
||||
# Log execution time
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Retrieval', duration)
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Summary_fails(
|
||||
ctx: Context,
|
||||
context: str,
|
||||
usermessages: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
storage_type: str = "",
|
||||
user_rag_memory_id: str = ""
|
||||
) -> dict:
|
||||
"""
|
||||
Handle workflow failure when summary cannot be generated.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
context: Failure context string
|
||||
usermessages: User messages identifier
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
storage_type: Storage type for the workspace (optional)
|
||||
user_rag_memory_id: User RAG memory identifier (optional)
|
||||
|
||||
Returns:
|
||||
dict: Contains 'query_answer' with failure message
|
||||
"""
|
||||
try:
|
||||
# Extract services from context
|
||||
session_service = get_context_resource(ctx, 'session_service')
|
||||
|
||||
# Parse session ID from usermessages
|
||||
usermessages_parts = usermessages.split('_')[1:]
|
||||
sessionid = '_'.join(usermessages_parts[:-1])
|
||||
|
||||
# Cleanup duplicate sessions
|
||||
await session_service.cleanup_duplicates()
|
||||
|
||||
logger.info("没有相关数据")
|
||||
logger.debug(f"Summary_fails called with apply_id: {apply_id}, group_id: {group_id}")
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"summary_result": "没有相关数据",
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Summary_fails failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"status": "fail",
|
||||
"summary_result": "没有相关数据",
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"error": str(e)
|
||||
}
|
||||
174
api/app/core/memory/agent/mcp_server/tools/verification_tools.py
Normal file
174
api/app/core/memory/agent/mcp_server/tools/verification_tools.py
Normal file
@@ -0,0 +1,174 @@
|
||||
"""
|
||||
Verification Tools for data verification.
|
||||
|
||||
This module contains MCP tools for verifying retrieved data.
|
||||
"""
|
||||
import time
|
||||
|
||||
from app.core.logging_config import get_agent_logger, log_time
|
||||
from app.core.memory.agent.mcp_server.mcp_instance import mcp
|
||||
from app.core.memory.agent.mcp_server.server import get_context_resource
|
||||
from app.core.memory.agent.utils.llm_tools import PROJECT_ROOT_
|
||||
from app.core.memory.agent.utils.messages_tool import (
|
||||
Resolve_username,
|
||||
Retrieve_verify_tool_messages_deal,
|
||||
Verify_messages_deal,
|
||||
)
|
||||
from app.core.memory.agent.utils.verify_tool import VerifyTool
|
||||
from app.schemas.memory_config_schema import MemoryConfig
|
||||
from jinja2 import Template
|
||||
from mcp.server.fastmcp import Context
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
@mcp.tool()
|
||||
async def Verify(
|
||||
ctx: Context,
|
||||
context: dict,
|
||||
usermessages: str,
|
||||
apply_id: str,
|
||||
group_id: str,
|
||||
memory_config: MemoryConfig,
|
||||
storage_type: str = "",
|
||||
user_rag_memory_id: str = ""
|
||||
) -> dict:
|
||||
"""
|
||||
Verify the retrieved data.
|
||||
|
||||
Args:
|
||||
ctx: FastMCP context for dependency injection
|
||||
context: Dictionary containing query and expansion issues
|
||||
usermessages: User messages identifier
|
||||
apply_id: Application identifier
|
||||
group_id: Group identifier
|
||||
memory_config: MemoryConfig object containing all configuration
|
||||
storage_type: Storage type for the workspace (optional)
|
||||
user_rag_memory_id: User RAG memory identifier (optional)
|
||||
|
||||
Returns:
|
||||
dict: Contains 'status' and 'verified_data' with verification results
|
||||
"""
|
||||
start = time.time()
|
||||
|
||||
|
||||
try:
|
||||
# Extract services from context
|
||||
session_service = get_context_resource(ctx, 'session_service')
|
||||
|
||||
# Load verification prompt template
|
||||
file_path = PROJECT_ROOT_ + '/agent/utils/prompt/split_verify_prompt.jinja2'
|
||||
|
||||
# Read template file directly (VerifyTool expects raw template content)
|
||||
from app.core.memory.agent.utils.messages_tool import read_template_file
|
||||
system_prompt = await read_template_file(file_path)
|
||||
|
||||
|
||||
|
||||
# Resolve session ID
|
||||
sessionid = Resolve_username(usermessages)
|
||||
|
||||
# Get conversation history
|
||||
history = await session_service.get_history(sessionid, apply_id, group_id)
|
||||
|
||||
template = Template(system_prompt)
|
||||
system_prompt = template.render(history=history, sentence=context)
|
||||
|
||||
# Process context to extract query and results
|
||||
Query_small, Result_small, query = await Verify_messages_deal(context)
|
||||
|
||||
# Build query list for verification
|
||||
query_list = []
|
||||
for query_small, anser in zip(Query_small, Result_small, strict=False):
|
||||
query_list.append({
|
||||
'Query_small': query_small,
|
||||
'Answer_Small': anser
|
||||
})
|
||||
|
||||
messages = {
|
||||
"Query": query,
|
||||
"Expansion_issue": query_list
|
||||
}
|
||||
|
||||
|
||||
|
||||
# Call verification workflow with LLM model ID from memory_config
|
||||
verify_tool = VerifyTool(
|
||||
system_prompt=system_prompt,
|
||||
verify_data=messages,
|
||||
llm_model_id=str(memory_config.llm_model_id)
|
||||
)
|
||||
verify_result = await verify_tool.verify()
|
||||
|
||||
# Parse LLM verification result with error handling
|
||||
try:
|
||||
messages_deal = await Retrieve_verify_tool_messages_deal(
|
||||
verify_result,
|
||||
history,
|
||||
query
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Retrieve_verify_tool_messages_deal parsing failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
# Fallback to avoid 500 errors
|
||||
messages_deal = {
|
||||
"data": {
|
||||
"query": query,
|
||||
"expansion_issue": []
|
||||
},
|
||||
"split_result": "failed",
|
||||
"reason": str(e),
|
||||
"history": history,
|
||||
}
|
||||
|
||||
logger.info(f"Verification result: {messages_deal}")
|
||||
|
||||
# Emit intermediate output for frontend
|
||||
return {
|
||||
"status": "success",
|
||||
"verified_data": messages_deal,
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"_intermediate": {
|
||||
"type": "verification",
|
||||
"title": "Data Verification",
|
||||
"result": messages_deal.get("split_result", "unknown"),
|
||||
"reason": messages_deal.get("reason", ""),
|
||||
"query": query,
|
||||
"verified_count": len(query_list),
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id
|
||||
}
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Verify failed: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return {
|
||||
"status": "error",
|
||||
"message": str(e),
|
||||
"storage_type": storage_type,
|
||||
"user_rag_memory_id": user_rag_memory_id,
|
||||
"verified_data": {
|
||||
"data": {
|
||||
"query": "",
|
||||
"expansion_issue": []
|
||||
},
|
||||
"split_result": "failed",
|
||||
"reason": str(e),
|
||||
"history": [],
|
||||
}
|
||||
}
|
||||
|
||||
finally:
|
||||
# Log execution time
|
||||
end = time.time()
|
||||
try:
|
||||
duration = end - start
|
||||
except Exception:
|
||||
duration = 0.0
|
||||
log_time('Verification', duration)
|
||||
@@ -1,32 +0,0 @@
|
||||
"""Pydantic models for verification operations."""
|
||||
|
||||
from typing import List, Optional, Dict, Any
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class VerificationItem(BaseModel):
|
||||
"""Individual verification item for a query-answer pair."""
|
||||
|
||||
query_small: str = Field(..., description="子问题")
|
||||
answer_small: str = Field(..., description="子问题的回答")
|
||||
status: str = Field(..., description="验证状态：True 或 False")
|
||||
query_answer: str = Field(..., description="问题的答案（与 answer_small 相同）")
|
||||
|
||||
|
||||
class VerificationResult(BaseModel):
|
||||
"""Result model for verification operation."""
|
||||
|
||||
query: str = Field(..., description="原始查询问题")
|
||||
history: List[Dict[str, Any]] = Field(default_factory=list, description="历史对话记录")
|
||||
expansion_issue: List[VerificationItem] = Field(
|
||||
default_factory=list,
|
||||
description="验证后的数据列表，包含所有通过验证的问答对"
|
||||
)
|
||||
split_result: str = Field(
|
||||
...,
|
||||
description="验证结果状态：success（expansion_issue 非空）或 failed（expansion_issue 为空）"
|
||||
)
|
||||
reason: Optional[str] = Field(
|
||||
None,
|
||||
description="验证结果的说明和分析"
|
||||
)
|
||||
114
api/app/core/memory/agent/multimodal/oss_picture.py
Normal file
114
api/app/core/memory/agent/multimodal/oss_picture.py
Normal file
@@ -0,0 +1,114 @@
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
import requests
|
||||
|
||||
# from qcloud_cos import CosConfig, CosS3Client
|
||||
# from qcloud_cos.cos_exception import CosClientError, CosServiceError
|
||||
|
||||
# from config.paths import BASE_DIR
|
||||
BASE_DIR = os.path.dirname(os.path.realpath(sys.argv[0]))
|
||||
|
||||
class OSSUploader:
|
||||
"""对象存储文件上传工具类"""
|
||||
|
||||
def __init__(self, env):
|
||||
api = {
|
||||
"test": "https://testlingqi.redbearai.com/api/user/file/common/upload/v2/anon",
|
||||
"prod": "https://lingqi.redbearai.com/api/user/file/common/upload/v2/anon"
|
||||
}
|
||||
self.api = api.get(env, "https://testlingqi.redbearai.com/api/user/file/common/upload/v2/anon")
|
||||
self.privacy = "false"
|
||||
self.headers = {
|
||||
"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
|
||||
'AppleWebKit/537.36 (KHTML, like Gecko)'
|
||||
' Chrome/133.0.6833.84 Safari/537.36'
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _generate_object_key(file_path, prefix='xhs_'):
|
||||
"""
|
||||
生成对象存储的Key
|
||||
|
||||
:param file_path: 本地文件路径
|
||||
:param prefix: 存储前缀，用于分类存储
|
||||
:return: 生成的对象Key
|
||||
"""
|
||||
# 文件md5值.后缀名
|
||||
filename = os.path.basename(file_path)
|
||||
filename = f"{filename}"
|
||||
|
||||
# 组合成完整的对象Key
|
||||
return f"{prefix}{filename}"
|
||||
|
||||
def upload_image(self, file_name, prefix='jd_'):
|
||||
"""
|
||||
上传文件到COS并返回可访问的URL
|
||||
|
||||
:param file_url: 文件路径
|
||||
:param file_name: 文件名称
|
||||
:param media_type: 文件类型
|
||||
:param prefix: 存储前缀，用于分类存储
|
||||
:return: 文件访问URL
|
||||
"""
|
||||
# 检查文件是否存在
|
||||
|
||||
|
||||
|
||||
file_path = os.path.join(BASE_DIR, file_name)
|
||||
|
||||
# response = requests.get(url, headers=self.headers, stream=True)
|
||||
|
||||
# if response.status_code == 200:
|
||||
# with open(file_path, "wb") as f:
|
||||
# for chunk in response.iter_content(1024): # 分块写入，避免内存占用过大
|
||||
# f.write(chunk)
|
||||
# else:
|
||||
# raise Exception(f"文件下载失败,{file_name}")
|
||||
|
||||
# 生成对象Key
|
||||
object_key = self._generate_object_key(file_path, prefix +file_name.split('.')[-1])
|
||||
|
||||
try:
|
||||
upload_response = requests.post(
|
||||
self.api,
|
||||
data={
|
||||
"privacy": self.privacy,
|
||||
"fileName": object_key,
|
||||
}
|
||||
)
|
||||
|
||||
if upload_response.status_code != 200:
|
||||
raise Exception('上传接口请求失败')
|
||||
resp = upload_response.json()
|
||||
name = resp["data"]["name"]
|
||||
file_url = resp["data"]["path"]
|
||||
policy = resp["data"]["policy"]
|
||||
with open(file_path, 'rb') as f:
|
||||
oss_push_resp = requests.post(
|
||||
policy["host"],
|
||||
files={
|
||||
"key": policy["dir"],
|
||||
"OSSAccessKeyId": policy["accessid"],
|
||||
"name": name,
|
||||
"policy": policy["policy"],
|
||||
"success_action_status": 200,
|
||||
"signature": policy["signature"],
|
||||
"file": f,
|
||||
}
|
||||
)
|
||||
if oss_push_resp.status_code == 200:
|
||||
return file_url
|
||||
raise Exception("OSS上传失败")
|
||||
except Exception:
|
||||
raise Exception(f"上传失败: \n{traceback.format_exc()}")
|
||||
finally:
|
||||
print('success')
|
||||
# os.remove(file_path)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
cos_uploader = OSSUploader("prod")
|
||||
url =cos_uploader.upload_image('./example01.jpg')
|
||||
print(url)
|
||||
121
api/app/core/memory/agent/multimodal/speech_model.py
Normal file
121
api/app/core/memory/agent/multimodal/speech_model.py
Normal file
@@ -0,0 +1,121 @@
|
||||
import asyncio
|
||||
import re
|
||||
|
||||
from app.core.memory.agent.utils.llm_tools import PROJECT_ROOT_, picture_model_requests,Picture_recognize, Voice_recognize
|
||||
from app.core.memory.agent.utils.messages_tool import read_template_file
|
||||
|
||||
import requests
|
||||
import json
|
||||
import os
|
||||
import time
|
||||
# file_urls = [
|
||||
# "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav",
|
||||
# "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_male2.wav",
|
||||
# ]
|
||||
class Vico_recognition:
|
||||
def __init__(self,file_urls):
|
||||
self.api_key=''
|
||||
self.backend_model_name=''
|
||||
self.api_base=''
|
||||
self.file_urls=file_urls
|
||||
|
||||
# 提交文件转写任务，包含待转写文件url列表
|
||||
async def submit_task(self) -> str:
|
||||
self.api_key, self.backend_model_name, self.api_base =await Voice_recognize()
|
||||
|
||||
headers = {
|
||||
"Authorization": f"Bearer {self.api_key}",
|
||||
"Content-Type": "application/json",
|
||||
"X-DashScope-Async": "enable",
|
||||
}
|
||||
data = {
|
||||
"model": self.backend_model_name,
|
||||
"input": {"file_urls": self.file_urls},
|
||||
"parameters": {
|
||||
"channel_id": [0],
|
||||
"vocabulary_id": "vocab-Xxxx",
|
||||
},
|
||||
}
|
||||
# 录音文件转写服务url
|
||||
service_url = (
|
||||
"https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription"
|
||||
)
|
||||
response = requests.post(
|
||||
service_url, headers=headers, data=json.dumps(data)
|
||||
)
|
||||
|
||||
# 打印响应内容
|
||||
if response.status_code == 200:
|
||||
return response.json()["output"]["task_id"]
|
||||
else:
|
||||
print("task failed!")
|
||||
print(response.json())
|
||||
return None
|
||||
|
||||
async def download_transcription_result(self, transcription_url):
|
||||
"""
|
||||
Args:
|
||||
transcription_url (str): 转写结果文件URL
|
||||
Returns:
|
||||
dict: 转写结果内容
|
||||
"""
|
||||
try:
|
||||
response = requests.get(transcription_url)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
except Exception as e:
|
||||
print(f"下载转写结果失败: {e}")
|
||||
return None
|
||||
|
||||
# 循环查询任务状态直到成功
|
||||
async def wait_for_complete(self,task_id):
|
||||
self.api_key, self.backend_model_name, self.api_base = await Voice_recognize()
|
||||
headers = {
|
||||
"Authorization": f"Bearer {self.api_key}",
|
||||
"Content-Type": "application/json",
|
||||
"X-DashScope-Async": "enable",
|
||||
}
|
||||
|
||||
pending = True
|
||||
while pending:
|
||||
# 查询任务状态服务url
|
||||
service_url = f"https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}"
|
||||
response = requests.post(
|
||||
service_url, headers=headers
|
||||
)
|
||||
if response.status_code == 200:
|
||||
status = response.json()['output']['task_status']
|
||||
if status == 'SUCCEEDED':
|
||||
print("task succeeded!")
|
||||
pending = False
|
||||
return response.json()['output']['results']
|
||||
elif status == 'RUNNING' or status == 'PENDING':
|
||||
pass
|
||||
else:
|
||||
print("task failed!")
|
||||
pending = False
|
||||
else:
|
||||
print("query failed!")
|
||||
pending = False
|
||||
time.sleep(0.1)
|
||||
async def run(self):
|
||||
self.api_key, self.backend_model_name, self.api_base = await Voice_recognize()
|
||||
task_id=await self.submit_task()
|
||||
result=await self.wait_for_complete(task_id)
|
||||
result_context=[]
|
||||
for i in result:
|
||||
transcription_url=i['transcription_url']
|
||||
print(f"转写URL: {transcription_url}")
|
||||
|
||||
# 下载并打印转写内容
|
||||
content = await self.download_transcription_result(transcription_url)
|
||||
if content:
|
||||
content=json.dumps(content, indent=2, ensure_ascii=False)
|
||||
context=re.findall(r'"text": "(.*?)"', content)
|
||||
result_context.append(context[0])
|
||||
result=''.join(result_context)
|
||||
return (result)
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,277 +0,0 @@
|
||||
"""
|
||||
优化的LLM服务类，用于压缩和统一LLM调用
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
from typing import Any, Dict, List, Optional, Type, TypeVar, Union
|
||||
from pydantic import BaseModel
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from app.core.memory.utils.llm.llm_utils import MemoryClientFactory
|
||||
from app.core.memory.llm_tools.openai_client import OpenAIClient
|
||||
|
||||
T = TypeVar('T', bound=BaseModel)
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
class OptimizedLLMService:
|
||||
"""
|
||||
优化的LLM服务类，提供统一的LLM调用接口
|
||||
|
||||
特性：
|
||||
1. 客户端复用 - 避免重复创建LLM客户端
|
||||
2. 批量处理 - 支持并发处理多个请求
|
||||
3. 错误处理 - 统一的错误处理和降级策略
|
||||
4. 性能优化 - 缓存和连接池优化
|
||||
"""
|
||||
|
||||
def __init__(self, db_session: Session):
|
||||
self.db_session = db_session
|
||||
self.client_factory = MemoryClientFactory(db_session)
|
||||
self._client_cache: Dict[str, OpenAIClient] = {}
|
||||
|
||||
def _get_cached_client(self, llm_model_id: str) -> OpenAIClient:
|
||||
"""获取缓存的LLM客户端，避免重复创建"""
|
||||
if llm_model_id not in self._client_cache:
|
||||
self._client_cache[llm_model_id] = self.client_factory.get_llm_client(llm_model_id)
|
||||
return self._client_cache[llm_model_id]
|
||||
|
||||
async def structured_response(
|
||||
self,
|
||||
llm_model_id: str,
|
||||
system_prompt: str,
|
||||
response_model: Type[T],
|
||||
user_message: Optional[str] = None,
|
||||
fallback_value: Optional[Any] = None
|
||||
) -> T:
|
||||
"""
|
||||
统一的结构化响应接口
|
||||
|
||||
Args:
|
||||
llm_model_id: LLM模型ID
|
||||
system_prompt: 系统提示词
|
||||
response_model: 响应模型类
|
||||
user_message: 用户消息（可选）
|
||||
fallback_value: 失败时的降级值
|
||||
|
||||
Returns:
|
||||
结构化响应对象
|
||||
"""
|
||||
try:
|
||||
llm_client = self._get_cached_client(llm_model_id)
|
||||
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if user_message:
|
||||
messages.append({"role": "user", "content": user_message})
|
||||
|
||||
logger.debug(f"LLM调用: model={llm_model_id}, prompt_length={len(system_prompt)}")
|
||||
|
||||
structured = await llm_client.response_structured(
|
||||
messages=messages,
|
||||
response_model=response_model
|
||||
)
|
||||
|
||||
if structured is None:
|
||||
logger.warning(f"LLM返回None，使用降级值")
|
||||
return self._create_fallback_response(response_model, fallback_value)
|
||||
|
||||
return structured
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"结构化响应失败: {e}", exc_info=True)
|
||||
return self._create_fallback_response(response_model, fallback_value)
|
||||
|
||||
async def batch_structured_response(
|
||||
self,
|
||||
llm_model_id: str,
|
||||
requests: List[Dict[str, Any]],
|
||||
response_model: Type[T],
|
||||
max_concurrent: int = 5
|
||||
) -> List[T]:
|
||||
"""
|
||||
批量处理结构化响应
|
||||
|
||||
Args:
|
||||
llm_model_id: LLM模型ID
|
||||
requests: 请求列表，每个请求包含system_prompt等参数
|
||||
response_model: 响应模型类
|
||||
max_concurrent: 最大并发数
|
||||
|
||||
Returns:
|
||||
结构化响应列表
|
||||
"""
|
||||
semaphore = asyncio.Semaphore(max_concurrent)
|
||||
|
||||
async def process_single_request(request: Dict[str, Any]) -> T:
|
||||
async with semaphore:
|
||||
return await self.structured_response(
|
||||
llm_model_id=llm_model_id,
|
||||
system_prompt=request.get('system_prompt', ''),
|
||||
response_model=response_model,
|
||||
user_message=request.get('user_message'),
|
||||
fallback_value=request.get('fallback_value')
|
||||
)
|
||||
|
||||
tasks = [process_single_request(req) for req in requests]
|
||||
return await asyncio.gather(*tasks)
|
||||
|
||||
async def simple_response(
|
||||
self,
|
||||
llm_model_id: str,
|
||||
system_prompt: str,
|
||||
user_message: Optional[str] = None,
|
||||
fallback_message: str = "信息不足，无法回答"
|
||||
) -> str:
|
||||
"""
|
||||
简单的文本响应接口
|
||||
|
||||
Args:
|
||||
llm_model_id: LLM模型ID
|
||||
system_prompt: 系统提示词
|
||||
user_message: 用户消息（可选）
|
||||
fallback_message: 失败时的降级消息
|
||||
|
||||
Returns:
|
||||
响应文本
|
||||
"""
|
||||
try:
|
||||
llm_client = self._get_cached_client(llm_model_id)
|
||||
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if user_message:
|
||||
messages.append({"role": "user", "content": user_message})
|
||||
|
||||
response = await llm_client.response(messages=messages)
|
||||
|
||||
if not response or not response.strip():
|
||||
return fallback_message
|
||||
|
||||
return response.strip()
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"简单响应失败: {e}", exc_info=True)
|
||||
return fallback_message
|
||||
|
||||
def _create_fallback_response(self, response_model: Type[T], fallback_value: Optional[Any]) -> T:
|
||||
"""创建降级响应"""
|
||||
try:
|
||||
if fallback_value is not None:
|
||||
if isinstance(fallback_value, response_model):
|
||||
return fallback_value
|
||||
elif isinstance(fallback_value, dict):
|
||||
return response_model(**fallback_value)
|
||||
|
||||
# 尝试创建空的响应模型
|
||||
if hasattr(response_model, 'root'):
|
||||
# RootModel类型
|
||||
return response_model([])
|
||||
else:
|
||||
# 普通BaseModel类型
|
||||
return response_model()
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"创建降级响应失败: {e}")
|
||||
# 最后的降级策略
|
||||
if hasattr(response_model, 'root'):
|
||||
return response_model([])
|
||||
else:
|
||||
return response_model()
|
||||
|
||||
def clear_cache(self):
|
||||
"""清理客户端缓存"""
|
||||
self._client_cache.clear()
|
||||
|
||||
|
||||
class LLMServiceMixin:
|
||||
"""
|
||||
LLM服务混入类，为节点提供便捷的LLM调用方法
|
||||
"""
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
self._llm_service: Optional[OptimizedLLMService] = None
|
||||
|
||||
def get_llm_service(self, db_session: Session) -> OptimizedLLMService:
|
||||
"""获取LLM服务实例"""
|
||||
if self._llm_service is None:
|
||||
self._llm_service = OptimizedLLMService(db_session)
|
||||
return self._llm_service
|
||||
|
||||
async def call_llm_structured(
|
||||
self,
|
||||
state: Dict[str, Any],
|
||||
db_session: Session,
|
||||
system_prompt: str,
|
||||
response_model: Type[T],
|
||||
user_message: Optional[str] = None,
|
||||
fallback_value: Optional[Any] = None
|
||||
) -> T:
|
||||
"""
|
||||
便捷的结构化LLM调用方法
|
||||
|
||||
Args:
|
||||
state: 状态字典，包含memory_config
|
||||
db_session: 数据库会话
|
||||
system_prompt: 系统提示词
|
||||
response_model: 响应模型类
|
||||
user_message: 用户消息（可选）
|
||||
fallback_value: 失败时的降级值
|
||||
|
||||
Returns:
|
||||
结构化响应对象
|
||||
"""
|
||||
memory_config = state.get('memory_config')
|
||||
if not memory_config:
|
||||
raise ValueError("State中缺少memory_config")
|
||||
|
||||
llm_model_id = memory_config.llm_model_id
|
||||
if not llm_model_id:
|
||||
raise ValueError("Memory config中缺少llm_model_id")
|
||||
|
||||
llm_service = self.get_llm_service(db_session)
|
||||
return await llm_service.structured_response(
|
||||
llm_model_id=llm_model_id,
|
||||
system_prompt=system_prompt,
|
||||
response_model=response_model,
|
||||
user_message=user_message,
|
||||
fallback_value=fallback_value
|
||||
)
|
||||
|
||||
async def call_llm_simple(
|
||||
self,
|
||||
state: Dict[str, Any],
|
||||
db_session: Session,
|
||||
system_prompt: str,
|
||||
user_message: Optional[str] = None,
|
||||
fallback_message: str = "信息不足，无法回答"
|
||||
) -> str:
|
||||
"""
|
||||
便捷的简单LLM调用方法
|
||||
|
||||
Args:
|
||||
state: 状态字典，包含memory_config
|
||||
db_session: 数据库会话
|
||||
system_prompt: 系统提示词
|
||||
user_message: 用户消息（可选）
|
||||
fallback_message: 失败时的降级消息
|
||||
|
||||
Returns:
|
||||
响应文本
|
||||
"""
|
||||
memory_config = state.get('memory_config')
|
||||
if not memory_config:
|
||||
raise ValueError("State中缺少memory_config")
|
||||
|
||||
llm_model_id = memory_config.llm_model_id
|
||||
if not llm_model_id:
|
||||
raise ValueError("Memory config中缺少llm_model_id")
|
||||
|
||||
llm_service = self.get_llm_service(db_session)
|
||||
return await llm_service.simple_response(
|
||||
llm_model_id=llm_model_id,
|
||||
system_prompt=system_prompt,
|
||||
user_message=user_message,
|
||||
fallback_message=fallback_message
|
||||
)
|
||||
7
api/app/core/memory/agent/utils/__init__.py
Normal file
7
api/app/core/memory/agent/utils/__init__.py
Normal file
@@ -0,0 +1,7 @@
|
||||
"""Agent utilities."""
|
||||
|
||||
from app.core.memory.agent.utils.multimodal import MultimodalProcessor
|
||||
|
||||
__all__ = [
|
||||
"MultimodalProcessor",
|
||||
]
|
||||
@@ -9,59 +9,62 @@ from app.core.memory.models.message_models import DialogData, ConversationContex
|
||||
|
||||
async def get_chunked_dialogs(
|
||||
chunker_strategy: str = "RecursiveChunker",
|
||||
end_user_id: str = "group_1",
|
||||
messages: list = None,
|
||||
group_id: str = "group_1",
|
||||
user_id: str = "user1",
|
||||
apply_id: str = "applyid",
|
||||
content: str = "这是用户的输入",
|
||||
ref_id: str = "wyl_20251027",
|
||||
config_id: str = None
|
||||
) -> List[DialogData]:
|
||||
"""Generate chunks from structured messages using the specified chunker strategy.
|
||||
"""Generate chunks from all test data entries using the specified chunker strategy.
|
||||
|
||||
Args:
|
||||
chunker_strategy: The chunking strategy to use (default: RecursiveChunker)
|
||||
end_user_id: Group identifier
|
||||
messages: Structured message list [{"role": "user", "content": "..."}, ...]
|
||||
group_id: Group identifier
|
||||
user_id: User identifier
|
||||
apply_id: Application identifier
|
||||
content: Dialog content
|
||||
ref_id: Reference identifier
|
||||
config_id: Configuration ID for processing
|
||||
|
||||
Returns:
|
||||
List of DialogData objects with generated chunks
|
||||
List of DialogData objects with generated chunks for each test entry
|
||||
"""
|
||||
from app.core.logging_config import get_agent_logger
|
||||
logger = get_agent_logger(__name__)
|
||||
dialog_data_list = []
|
||||
messages = []
|
||||
|
||||
if not messages or not isinstance(messages, list) or len(messages) == 0:
|
||||
raise ValueError("messages parameter must be a non-empty list")
|
||||
messages.append(ConversationMessage(role="用户", msg=content))
|
||||
|
||||
conversation_messages = []
|
||||
|
||||
for idx, msg in enumerate(messages):
|
||||
if not isinstance(msg, dict) or 'role' not in msg or 'content' not in msg:
|
||||
raise ValueError(f"Message {idx} format error: must contain 'role' and 'content' fields")
|
||||
|
||||
role = msg['role']
|
||||
content = msg['content']
|
||||
|
||||
if role not in ['user', 'assistant']:
|
||||
raise ValueError(f"Message {idx} role must be 'user' or 'assistant', got: {role}")
|
||||
|
||||
if content.strip():
|
||||
conversation_messages.append(ConversationMessage(role=role, msg=content.strip()))
|
||||
|
||||
if not conversation_messages:
|
||||
raise ValueError("Message list cannot be empty after filtering")
|
||||
|
||||
conversation_context = ConversationContext(msgs=conversation_messages)
|
||||
# Create DialogData
|
||||
conversation_context = ConversationContext(msgs=messages)
|
||||
# Create DialogData with group_id based on the entry's id for uniqueness
|
||||
dialog_data = DialogData(
|
||||
context=conversation_context,
|
||||
ref_id=ref_id,
|
||||
end_user_id=end_user_id,
|
||||
group_id=group_id,
|
||||
user_id=user_id,
|
||||
apply_id=apply_id,
|
||||
config_id=config_id
|
||||
)
|
||||
|
||||
# Create DialogueChunker and process the dialogue
|
||||
chunker = DialogueChunker(chunker_strategy)
|
||||
extracted_chunks = await chunker.process_dialogue(dialog_data)
|
||||
dialog_data.chunks = extracted_chunks
|
||||
|
||||
logger.info(f"DialogData created with {len(extracted_chunks)} chunks")
|
||||
dialog_data_list.append(dialog_data)
|
||||
|
||||
return [dialog_data]
|
||||
# Convert to dict with datetime serialized
|
||||
def serialize_datetime(obj):
|
||||
if isinstance(obj, datetime):
|
||||
return obj.isoformat()
|
||||
raise TypeError(f"Object of type {obj.__class__.__name__} is not JSON serializable")
|
||||
|
||||
combined_output = [dd.model_dump() for dd in dialog_data_list]
|
||||
|
||||
print(dialog_data_list)
|
||||
|
||||
# with open(os.path.join(os.path.dirname(__file__), "chunker_test_output.txt"), "w", encoding="utf-8") as f:
|
||||
# json.dump(combined_output, f, ensure_ascii=False, indent=4, default=serialize_datetime)
|
||||
|
||||
|
||||
return dialog_data_list
|
||||
|
||||
@@ -1,56 +0,0 @@
|
||||
|
||||
import asyncio
|
||||
from typing import Dict, Optional
|
||||
from app.core.memory.utils.llm.llm_utils import get_llm_client_fast
|
||||
from app.db import get_db
|
||||
from app.core.logging_config import get_agent_logger
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
class LLMClientPool:
|
||||
"""LLM客户端连接池"""
|
||||
|
||||
def __init__(self, max_size: int = 5):
|
||||
self.max_size = max_size
|
||||
self.pools: Dict[str, asyncio.Queue] = {}
|
||||
self.active_clients: Dict[str, int] = {}
|
||||
|
||||
async def get_client(self, llm_model_id: str):
|
||||
"""获取LLM客户端"""
|
||||
if llm_model_id not in self.pools:
|
||||
self.pools[llm_model_id] = asyncio.Queue(maxsize=self.max_size)
|
||||
self.active_clients[llm_model_id] = 0
|
||||
|
||||
pool = self.pools[llm_model_id]
|
||||
|
||||
try:
|
||||
# 尝试从池中获取客户端
|
||||
client = pool.get_nowait()
|
||||
logger.debug(f"从池中获取LLM客户端: {llm_model_id}")
|
||||
return client
|
||||
except asyncio.QueueEmpty:
|
||||
# 池为空，创建新客户端
|
||||
if self.active_clients[llm_model_id] < self.max_size:
|
||||
db_session = next(get_db())
|
||||
client = get_llm_client_fast(llm_model_id, db_session)
|
||||
self.active_clients[llm_model_id] += 1
|
||||
logger.debug(f"创建新LLM客户端: {llm_model_id}")
|
||||
return client
|
||||
else:
|
||||
# 等待可用客户端
|
||||
logger.debug(f"等待LLM客户端可用: {llm_model_id}")
|
||||
return await pool.get()
|
||||
|
||||
async def return_client(self, llm_model_id: str, client):
|
||||
"""归还LLM客户端到池中"""
|
||||
if llm_model_id in self.pools:
|
||||
try:
|
||||
self.pools[llm_model_id].put_nowait(client)
|
||||
logger.debug(f"归还LLM客户端到池: {llm_model_id}")
|
||||
except asyncio.QueueFull:
|
||||
# 池已满，丢弃客户端
|
||||
self.active_clients[llm_model_id] -= 1
|
||||
logger.debug(f"池已满，丢弃LLM客户端: {llm_model_id}")
|
||||
|
||||
# 全局客户端池
|
||||
llm_client_pool = LLMClientPool()
|
||||
@@ -1,83 +1,82 @@
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
from typing import Annotated, TypedDict
|
||||
|
||||
from app.core.memory.agent.utils.messages_tool import read_template_file
|
||||
from app.core.memory.utils.config.config_utils import (
|
||||
get_picture_config,
|
||||
get_voice_config,
|
||||
)
|
||||
|
||||
# Removed global variable imports - use dependency injection instead
|
||||
from dotenv import load_dotenv
|
||||
from langchain_core.messages import AnyMessage
|
||||
from langgraph.graph import add_messages
|
||||
from openai import OpenAI
|
||||
|
||||
PROJECT_ROOT_ = str(Path(__file__).resolve().parents[3])
|
||||
PROJECT_ROOT_ = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
load_dotenv()
|
||||
|
||||
|
||||
async def picture_model_requests(image_url):
|
||||
'''
|
||||
|
||||
Args:
|
||||
image_url:
|
||||
Returns:
|
||||
|
||||
'''
|
||||
file_path = PROJECT_ROOT_ + '/agent/utils/prompt/Template_for_image_recognition_prompt.jinja2 '
|
||||
system_prompt = await read_template_file(file_path)
|
||||
result = await Picture_recognize(image_url,system_prompt)
|
||||
return (result)
|
||||
class WriteState(TypedDict):
|
||||
'''
|
||||
Langgrapg Writing TypedDict
|
||||
'''
|
||||
messages: Annotated[list[AnyMessage], add_messages]
|
||||
end_user_id: str
|
||||
user_id:str
|
||||
apply_id:str
|
||||
group_id:str
|
||||
errors: list[dict] # Track errors: [{"tool": "tool_name", "error": "message"}]
|
||||
memory_config: object
|
||||
write_result: dict
|
||||
data: str
|
||||
|
||||
class ReadState(TypedDict):
|
||||
"""
|
||||
LangGraph 工作流状态定义
|
||||
|
||||
Attributes:
|
||||
messages: 消息列表，支持自动追加
|
||||
loop_count: 遍历次数
|
||||
search_switch: 搜索类型开关
|
||||
end_user_id: 组标识
|
||||
config_id: 配置ID，用于过滤结果
|
||||
data: 从content_input_node传递的内容数据
|
||||
spit_data: 从Split_The_Problem传递的分解结果
|
||||
tool_calls: 工具调用请求列表
|
||||
tool_results: 工具执行结果列表
|
||||
memory_config: 内存配置对象
|
||||
"""
|
||||
messages: Annotated[list[AnyMessage], add_messages] # 消息追加模式
|
||||
loop_count: int
|
||||
'''
|
||||
Langgrapg READING TypedDict
|
||||
name:
|
||||
id:user id
|
||||
loop_count:Traverse times
|
||||
search_switch：type
|
||||
config_id: configuration id for filtering results
|
||||
errors: list of errors that occurred during workflow execution
|
||||
'''
|
||||
messages: Annotated[list[AnyMessage], add_messages] #消息追加的模式增加消息
|
||||
name: str
|
||||
id: str
|
||||
loop_count:int
|
||||
search_switch: str
|
||||
end_user_id: str
|
||||
user_id: str
|
||||
apply_id: str
|
||||
group_id: str
|
||||
config_id: str
|
||||
data: str # 新增字段用于传递内容
|
||||
spit_data: dict # 新增字段用于传递问题分解结果
|
||||
problem_extension:dict
|
||||
storage_type: str
|
||||
user_rag_memory_id: str
|
||||
llm_id: str
|
||||
embedding_id: str
|
||||
memory_config: object # 新增字段用于传递内存配置对象
|
||||
retrieve:dict
|
||||
RetrieveSummary: dict
|
||||
InputSummary: dict
|
||||
verify: dict
|
||||
SummaryFails: dict
|
||||
summary: dict
|
||||
errors: list[dict] # Track errors: [{"tool": "tool_name", "error": "message"}]
|
||||
|
||||
|
||||
class COUNTState:
|
||||
"""
|
||||
工作流对话检索内容计数器
|
||||
|
||||
用于记录工作流对话检索内容没有正确消息召回遍历的次数。
|
||||
"""
|
||||
|
||||
'''
|
||||
The number of times the workflow dialogue retrieval content has no correct message recall traversal
|
||||
'''
|
||||
def __init__(self, limit: int = 5):
|
||||
"""
|
||||
初始化计数器
|
||||
|
||||
Args:
|
||||
limit: 最大计数限制，默认为5
|
||||
"""
|
||||
self.total: int = 0 # 当前累加值
|
||||
self.limit: int = limit # 最大上限
|
||||
|
||||
def add(self, value: int = 1) -> None:
|
||||
"""
|
||||
累加数字，如果达到上限就保持最大值
|
||||
|
||||
Args:
|
||||
value: 要累加的值，默认为1
|
||||
"""
|
||||
def add(self, value: int = 1):
|
||||
"""累加数字，如果达到上限就保持最大值"""
|
||||
self.total += value
|
||||
print(f"[COUNTState] 当前值: {self.total}")
|
||||
if self.total >= self.limit:
|
||||
@@ -85,19 +84,21 @@ class COUNTState:
|
||||
self.total = self.limit # 达到上限不再增加
|
||||
|
||||
def get_total(self) -> int:
|
||||
"""
|
||||
获取当前累加值
|
||||
|
||||
Returns:
|
||||
当前累加值
|
||||
"""
|
||||
"""获取当前累加值"""
|
||||
return self.total
|
||||
|
||||
def reset(self) -> None:
|
||||
def reset(self):
|
||||
"""手动重置累加值"""
|
||||
self.total = 0
|
||||
print("[COUNTState] 已重置为 0")
|
||||
|
||||
|
||||
def merge_to_key_value_pairs(data, query_key, result_key):
|
||||
grouped = defaultdict(list)
|
||||
for item in data:
|
||||
grouped[item[query_key]].append(item[result_key])
|
||||
return [{key: values} for key, values in grouped.items()]
|
||||
|
||||
def deduplicate_entries(entries):
|
||||
seen = set()
|
||||
deduped = []
|
||||
@@ -108,37 +109,70 @@ def deduplicate_entries(entries):
|
||||
deduped.append(entry)
|
||||
return deduped
|
||||
|
||||
def merge_to_key_value_pairs(data, query_key, result_key):
|
||||
grouped = defaultdict(list)
|
||||
for item in data:
|
||||
grouped[item[query_key]].append(item[result_key])
|
||||
return [{key: values} for key, values in grouped.items()]
|
||||
|
||||
|
||||
def convert_extended_question_to_question(data):
|
||||
async def Picture_recognize(image_path, PROMPT_TICKET_EXTRACTION, picture_model_name: str) -> str:
|
||||
"""
|
||||
递归地将数据中的 extended_question 字段转换为 question 字段
|
||||
|
||||
Updated to eliminate global variables in favor of explicit parameters.
|
||||
|
||||
Args:
|
||||
data: 要转换的数据（可能是字典、列表或其他类型）
|
||||
|
||||
Returns:
|
||||
转换后的数据
|
||||
image_path: Path to image file
|
||||
PROMPT_TICKET_EXTRACTION: Extraction prompt
|
||||
picture_model_name: Picture model name (required, no longer from global variables)
|
||||
"""
|
||||
if isinstance(data, dict):
|
||||
# 创建新字典来存储转换后的数据
|
||||
converted = {}
|
||||
for key, value in data.items():
|
||||
if key == 'extended_question':
|
||||
# 将 extended_question 转换为 question
|
||||
converted['question'] = convert_extended_question_to_question(value)
|
||||
else:
|
||||
# 递归处理其他字段
|
||||
converted[key] = convert_extended_question_to_question(value)
|
||||
return converted
|
||||
elif isinstance(data, list):
|
||||
# 递归处理列表中的每个元素
|
||||
return [convert_extended_question_to_question(item) for item in data]
|
||||
else:
|
||||
# 其他类型直接返回
|
||||
return data
|
||||
try:
|
||||
model_config = get_picture_config(picture_model_name)
|
||||
except Exception as e:
|
||||
err = f"LLM配置不可用：{str(e)}。请检查 config.json 和 runtime.json。"
|
||||
logger.error(err)
|
||||
return err
|
||||
api_key = os.getenv(model_config["api_key"]) # 从环境变量读取对应后端的 API key
|
||||
backend_model_name = model_config["llm_name"].split("/")[-1]
|
||||
api_base=model_config['api_base']
|
||||
|
||||
logger.info(f"model_name: {backend_model_name}")
|
||||
logger.info(f"api_key set: {'yes' if api_key else 'no'}")
|
||||
logger.info(f"base_url: {model_config['api_base']}")
|
||||
|
||||
client = OpenAI(
|
||||
api_key=api_key, base_url=api_base,
|
||||
)
|
||||
completion = client.chat.completions.create(
|
||||
model=backend_model_name,
|
||||
messages=[
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{
|
||||
"type": "image_url",
|
||||
"image_url":image_path,
|
||||
},
|
||||
{"type": "text",
|
||||
"text": PROMPT_TICKET_EXTRACTION}
|
||||
]
|
||||
}
|
||||
])
|
||||
picture_text = completion.choices[0].message.content
|
||||
picture_text = picture_text.replace('```json', '').replace('```', '')
|
||||
picture_text = json.loads(picture_text)
|
||||
return (picture_text['statement'])
|
||||
|
||||
async def Voice_recognize(voice_model_name: str):
|
||||
"""
|
||||
Updated to eliminate global variables in favor of explicit parameters.
|
||||
|
||||
Args:
|
||||
voice_model_name: Voice model name (required, no longer from global variables)
|
||||
"""
|
||||
try:
|
||||
model_config = get_voice_config(voice_model_name)
|
||||
except Exception as e:
|
||||
err = f"LLM配置不可用：{str(e)}。请检查 config.json 和 runtime.json。"
|
||||
logger.error(err)
|
||||
return err
|
||||
api_key = os.getenv(model_config["api_key"]) # 从环境变量读取对应后端的 API key
|
||||
backend_model_name = model_config["llm_name"].split("/")[-1]
|
||||
api_base = model_config['api_base']
|
||||
return api_key,backend_model_name,api_base
|
||||
|
||||
|
||||
|
||||
33
api/app/core/memory/agent/utils/mcp_tools.py
Normal file
33
api/app/core/memory/agent/utils/mcp_tools.py
Normal file
@@ -0,0 +1,33 @@
|
||||
import os
|
||||
from app.core.config import settings
|
||||
|
||||
def get_mcp_server_config():
|
||||
"""
|
||||
Get the MCP server configuration.
|
||||
|
||||
Uses MCP_SERVER_URL environment variable if set (for Docker),
|
||||
otherwise falls back to SERVER_IP and MCP_PORT (for local development).
|
||||
"""
|
||||
# Get MCP port from environment (default: 8081)
|
||||
mcp_port = os.getenv("MCP_PORT", "8081")
|
||||
|
||||
# In Docker: MCP_SERVER_URL=http://mcp-server:8081
|
||||
# In local dev: uses SERVER_IP (127.0.0.1 or localhost)
|
||||
mcp_server_url = os.getenv("MCP_SERVER_URL")
|
||||
|
||||
if mcp_server_url:
|
||||
# Docker environment: use full URL from environment
|
||||
base_url = mcp_server_url
|
||||
else:
|
||||
# Local development: build URL from SERVER_IP and MCP_PORT
|
||||
base_url = f"http://{settings.SERVER_IP}:{mcp_port}"
|
||||
|
||||
mcp_server_config = {
|
||||
"data_flow": {
|
||||
"url": f"{base_url}/sse",
|
||||
"transport": "sse",
|
||||
"timeout": 15000,
|
||||
"sse_read_timeout": 15000,
|
||||
}
|
||||
}
|
||||
return mcp_server_config
|
||||
260
api/app/core/memory/agent/utils/messages_tool.py
Normal file
260
api/app/core/memory/agent/utils/messages_tool.py
Normal file
@@ -0,0 +1,260 @@
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
from typing import Any, List
|
||||
|
||||
from app.core.logging_config import get_agent_logger
|
||||
from langchain_core.messages import AnyMessage
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
|
||||
|
||||
def _to_openai_messages(msgs: List[AnyMessage]) -> List[dict]:
|
||||
out = []
|
||||
for m in msgs:
|
||||
if hasattr(m, "content"):
|
||||
out.append({"role": "user", "content": getattr(m, "content", "")})
|
||||
elif isinstance(m, dict) and "role" in m and "content" in m:
|
||||
out.append(m)
|
||||
else:
|
||||
out.append({"role": "user", "content": str(m)})
|
||||
return out
|
||||
|
||||
|
||||
def _extract_content(resp: Any) -> str:
|
||||
"""Extract LLM content and sanitize to raw JSON/text.
|
||||
|
||||
- Supports both object and dict response shapes.
|
||||
- Removes leading role labels (e.g., "Assistant:").
|
||||
- Strips Markdown code fences like ```json ... ```.
|
||||
- Attempts to isolate the first valid JSON array/object block when extra text is present.
|
||||
"""
|
||||
|
||||
def _to_text(r: Any) -> str:
|
||||
try:
|
||||
# 对象形式: resp.choices[0].message.content
|
||||
if hasattr(r, "choices") and getattr(r, "choices", None):
|
||||
msg = r.choices[0].message
|
||||
if hasattr(msg, "content"):
|
||||
return msg.content
|
||||
if isinstance(msg, dict) and "content" in msg:
|
||||
return msg["content"]
|
||||
# 字典形式: resp["choices"][0]["message"]["content"]
|
||||
if isinstance(r, dict):
|
||||
return r.get("choices", [{}])[0].get("message", {}).get("content", "")
|
||||
except Exception:
|
||||
pass
|
||||
return str(r)
|
||||
|
||||
def _clean_text(text: str) -> str:
|
||||
s = str(text).strip()
|
||||
# 移除可能的角色前缀
|
||||
s = re.sub(r"^\s*(Assistant|assistant)\s*:\s*", "", s)
|
||||
# 提取 ```json ... ``` 代码块
|
||||
m = re.search(r"```json\s*(.*?)\s*```", s, flags=re.S | re.I)
|
||||
if m:
|
||||
s = m.group(1).strip()
|
||||
# 如果仍然包含多余文本，尝试截取第一个 JSON 数组/对象片段
|
||||
if not (s.startswith("{") or s.startswith("[")):
|
||||
left = s.find("[")
|
||||
right = s.rfind("]")
|
||||
if left != -1 and right != -1 and right > left:
|
||||
s = s[left:right + 1].strip()
|
||||
else:
|
||||
left = s.find("{")
|
||||
right = s.rfind("}")
|
||||
if left != -1 and right != -1 and right > left:
|
||||
s = s[left:right + 1].strip()
|
||||
return s
|
||||
|
||||
raw = _to_text(resp)
|
||||
return _clean_text(raw)
|
||||
|
||||
def Resolve_username(usermessages):
|
||||
'''
|
||||
Extract username
|
||||
Args:
|
||||
usermessages: user name
|
||||
|
||||
Returns:
|
||||
|
||||
'''
|
||||
usermessages = usermessages.split('_')[1:]
|
||||
sessionid = '_'.join(usermessages[:-1])
|
||||
return sessionid
|
||||
|
||||
|
||||
# TODO: USE app.core.memory.src.utils.render_template instead
|
||||
async def read_template_file(template_path: str) -> str:
|
||||
"""
|
||||
读取模板文件
|
||||
|
||||
Args:
|
||||
template_path: 模板文件路径
|
||||
|
||||
Returns:
|
||||
模板内容字符串
|
||||
|
||||
Note:
|
||||
建议使用 app.core.memory.utils.template_render 中的统一模板渲染功能
|
||||
"""
|
||||
try:
|
||||
with open(template_path, "r", encoding="utf-8") as f:
|
||||
return f.read()
|
||||
except FileNotFoundError:
|
||||
logger.error(f"模板文件未找到: {template_path}")
|
||||
raise
|
||||
except IOError as e:
|
||||
logger.error(f"读取模板文件失败: {template_path}, 错误: {str(e)}", exc_info=True)
|
||||
raise
|
||||
|
||||
|
||||
async def Problem_Extension_messages_deal(context):
|
||||
'''
|
||||
Extract data
|
||||
Args:
|
||||
context:
|
||||
Returns:
|
||||
'''
|
||||
extent_quest = []
|
||||
original = context.get('original', '')
|
||||
messages = context.get('context', '')
|
||||
|
||||
# Handle empty or non-string messages
|
||||
if not messages:
|
||||
return extent_quest, original
|
||||
|
||||
if isinstance(messages, str):
|
||||
try:
|
||||
messages = json.loads(messages)
|
||||
except json.JSONDecodeError:
|
||||
# If JSON parsing fails, return empty list
|
||||
return extent_quest, original
|
||||
|
||||
if isinstance(messages, list):
|
||||
for message in messages:
|
||||
question = message.get('question', '')
|
||||
type = message.get('type', '')
|
||||
extent_quest.append({"role": "user", "content": f"问题:{question}；问题类型：{type}"})
|
||||
|
||||
return extent_quest, original
|
||||
|
||||
|
||||
async def Retriev_messages_deal(context):
|
||||
'''
|
||||
Extract data
|
||||
Args:
|
||||
context:
|
||||
Returns:
|
||||
'''
|
||||
logger.info(f"Retriev_messages_deal input: type={type(context)}, value={str(context)[:500]}")
|
||||
|
||||
if isinstance(context, dict):
|
||||
logger.info(f"Retriev_messages_deal: context is dict with keys={list(context.keys())}")
|
||||
if 'context' in context or 'original' in context:
|
||||
content = context.get('context', {})
|
||||
original = context.get('original', '')
|
||||
logger.info(f"Retriev_messages_deal output: content_type={type(content)}, content={str(content)[:300]}, original='{original[:50] if original else ''}'")
|
||||
return content, original
|
||||
|
||||
# Return empty defaults if context is not a dict or doesn't have expected keys
|
||||
logger.warning(f"Retriev_messages_deal: context missing expected keys, returning empty defaults")
|
||||
return {}, ''
|
||||
|
||||
async def Verify_messages_deal(context):
|
||||
'''
|
||||
Extract data
|
||||
Args:
|
||||
context:
|
||||
Returns:
|
||||
'''
|
||||
|
||||
query = context['context']['Query']
|
||||
Query_small_list = context['context']['Expansion_issue']
|
||||
Result_small = []
|
||||
Query_small = []
|
||||
for i in Query_small_list:
|
||||
Result_small.append(i['Answer_Small'][0])
|
||||
Query_small.append(i['Query_small'])
|
||||
return Query_small, Result_small, query
|
||||
|
||||
|
||||
async def Summary_messages_deal(context):
|
||||
'''
|
||||
Extract data
|
||||
Args:
|
||||
context:
|
||||
Returns:
|
||||
'''
|
||||
messages = str(context).replace('\\n', '').replace('\n', '').replace('\\', '')
|
||||
query = re.findall(r'"query": (.*?),', messages)[0]
|
||||
query = query.replace('[', '').replace(']', '').strip()
|
||||
matches = re.findall(r'"answer_small"\s*:\s*"(\[.*?\])"', messages)
|
||||
answer_small_texts = []
|
||||
for m in matches:
|
||||
try:
|
||||
parsed = json.loads(m)
|
||||
for item in parsed:
|
||||
answer_small_texts.append(item.strip().replace('\\', '').replace('[', '').replace(']', ''))
|
||||
except Exception:
|
||||
answer_small_texts.append(m.strip().replace('\\', '').replace('[', '').replace(']', ''))
|
||||
|
||||
return answer_small_texts, query
|
||||
|
||||
|
||||
async def VerifyTool_messages_deal(context):
|
||||
'''
|
||||
Extract data
|
||||
Args:
|
||||
context:
|
||||
Returns:
|
||||
'''
|
||||
messages = str(context).replace('\\n', '').replace('\n', '').replace('\\', '')
|
||||
content_messages = messages.split('"context":')[1].replace('""', '"')
|
||||
messages = str(content_messages).split("name='Retrieve'")[0]
|
||||
query = re.findall('"Query": "(.*?)"', messages)[0]
|
||||
Query_small = re.findall('"Query_small": "(.*?)"', messages)
|
||||
Result_small = re.findall('"Result_small": "(.*?)"', messages)
|
||||
return Query_small, Result_small, query
|
||||
|
||||
|
||||
async def Retrieve_Summary_messages_deal(context):
|
||||
pass
|
||||
|
||||
|
||||
async def Retrieve_verify_tool_messages_deal(context, history, query):
|
||||
'''
|
||||
Extract data
|
||||
Args:
|
||||
context:
|
||||
Returns:
|
||||
'''
|
||||
results = []
|
||||
# 统一转为字符串，避免 None 或非字符串导致正则报错
|
||||
text = str(context)
|
||||
blocks = re.findall(r'\{(.*?)\}', text, flags=re.S)
|
||||
for block in blocks:
|
||||
query_small = re.search(r'"Query_small"\s*:\s*"([^"]*)"', block)
|
||||
answer_small = re.search(r'"Answer_Small"\s*:\s*(\[[^\]]*\])', block)
|
||||
status = re.search(r'"status"\s*:\s*"([^"]*)"', block)
|
||||
query_answer = re.search(r'"Query_answer"\s*:\s*"([^"]*)"', block)
|
||||
|
||||
results.append({
|
||||
"query_small": query_small.group(1) if query_small else None,
|
||||
"answer_small": answer_small.group(1) if answer_small else None,
|
||||
# 将缺失的 status 统一为空字符串，后续用字符串判定，避免 NoneType 错误
|
||||
"status": status.group(1) if status else "",
|
||||
"query_answer": query_answer.group(1) if query_answer else None
|
||||
})
|
||||
result = []
|
||||
for r in results:
|
||||
# 统一按字符串判定状态，兼容大小写和缺失情况
|
||||
status_str = str(r.get('status', '')).strip().lower()
|
||||
if status_str == 'false':
|
||||
continue
|
||||
else:
|
||||
result.append(r)
|
||||
split_result = 'failed' if not result else 'success'
|
||||
result = {"data": {"query": query, "expansion_issue": result}, "split_result": split_result, "reason": "",
|
||||
"history": history}
|
||||
return result
|
||||
@@ -1,194 +0,0 @@
|
||||
from typing import List, Dict, Any
|
||||
from app.core.logging_config import get_agent_logger
|
||||
|
||||
logger = get_agent_logger(__name__)
|
||||
async def read_template_file(template_path: str) -> str:
|
||||
"""
|
||||
读取模板文件
|
||||
|
||||
Args:
|
||||
template_path: 模板文件路径
|
||||
|
||||
Returns:
|
||||
模板内容字符串
|
||||
|
||||
Note:
|
||||
建议使用 app.core.memory.utils.template_render 中的统一模板渲染功能
|
||||
"""
|
||||
try:
|
||||
with open(template_path, "r", encoding="utf-8") as f:
|
||||
return f.read()
|
||||
except FileNotFoundError:
|
||||
logger.error(f"模板文件未找到: {template_path}")
|
||||
raise
|
||||
except IOError as e:
|
||||
logger.error(f"读取模板文件失败: {template_path}, 错误: {str(e)}", exc_info=True)
|
||||
raise
|
||||
|
||||
def reorder_output_results(results: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
重新排序输出结果，将 retrieval_summary 类型的数据放到最后面
|
||||
|
||||
Args:
|
||||
results: 原始输出结果列表
|
||||
|
||||
Returns:
|
||||
重新排序后的结果列表
|
||||
"""
|
||||
retrieval_summaries = []
|
||||
other_results = []
|
||||
|
||||
# 分离 retrieval_summary 和其他类型的结果
|
||||
for result in results:
|
||||
if 'summary' in result.get('type'):
|
||||
retrieval_summaries.append(result)
|
||||
else:
|
||||
other_results.append(result)
|
||||
|
||||
# 将 retrieval_summary 放到最后
|
||||
return other_results + retrieval_summaries
|
||||
|
||||
def optimize_search_results(intermediate_outputs):
|
||||
"""
|
||||
优化检索结果，合并多个搜索结果，过滤空结果，统一格式
|
||||
|
||||
Args:
|
||||
intermediate_outputs: 原始的中间输出列表
|
||||
|
||||
Returns:
|
||||
优化后的检索结果列表
|
||||
"""
|
||||
optimized_results = []
|
||||
|
||||
for item in intermediate_outputs:
|
||||
if not item or item == [] or item == {}:
|
||||
continue
|
||||
|
||||
# 检查是否是搜索结果类型
|
||||
if isinstance(item, dict) and item.get('type') == 'search_result':
|
||||
raw_results = item.get('raw_results', {})
|
||||
|
||||
# 如果 raw_results 为空，跳过
|
||||
if not raw_results or raw_results == [] or raw_results == {}:
|
||||
continue
|
||||
|
||||
# 创建优化后的结果结构
|
||||
optimized_item = {
|
||||
"type": "search_result",
|
||||
"title": f"检索结果 ({item.get('index', 1)}/{item.get('total', 1)})",
|
||||
"query": item.get('query', ''),
|
||||
"raw_results": {},
|
||||
"index": item.get('index', 1),
|
||||
"total": item.get('total', 1)
|
||||
}
|
||||
|
||||
# 合并所有搜索结果类型到一个 raw_results 中
|
||||
merged_raw_results = {}
|
||||
|
||||
# 处理 time_search
|
||||
if 'time_search' in raw_results and raw_results['time_search']:
|
||||
merged_raw_results['time_search'] = raw_results['time_search']
|
||||
|
||||
# 处理 keyword_search
|
||||
if 'keyword_search' in raw_results and raw_results['keyword_search']:
|
||||
merged_raw_results['keyword_search'] = raw_results['keyword_search']
|
||||
|
||||
# 处理 embedding_search
|
||||
if 'embedding_search' in raw_results and raw_results['embedding_search']:
|
||||
merged_raw_results['embedding_search'] = raw_results['embedding_search']
|
||||
|
||||
# 处理 combined_summary
|
||||
if 'combined_summary' in raw_results and raw_results['combined_summary']:
|
||||
merged_raw_results['combined_summary'] = raw_results['combined_summary']
|
||||
|
||||
# 处理 reranked_results
|
||||
if 'reranked_results' in raw_results and raw_results['reranked_results']:
|
||||
merged_raw_results['reranked_results'] = raw_results['reranked_results']
|
||||
|
||||
# 如果合并后的结果不为空，添加到优化结果中
|
||||
if merged_raw_results:
|
||||
optimized_item['raw_results'] = merged_raw_results
|
||||
optimized_results.append(optimized_item)
|
||||
else:
|
||||
# 非搜索结果类型，直接添加
|
||||
optimized_results.append(item)
|
||||
|
||||
return optimized_results
|
||||
|
||||
|
||||
def merge_multiple_search_results(intermediate_outputs):
|
||||
"""
|
||||
将多个搜索结果合并为一个统一的搜索结果
|
||||
|
||||
Args:
|
||||
intermediate_outputs: 原始的中间输出列表
|
||||
|
||||
Returns:
|
||||
合并后的结果列表
|
||||
"""
|
||||
search_results = []
|
||||
other_results = []
|
||||
|
||||
# 分离搜索结果和其他结果
|
||||
for item in intermediate_outputs:
|
||||
if isinstance(item, dict) and item.get('type') == 'search_result':
|
||||
raw_results = item.get('raw_results', {})
|
||||
# 只保留有内容的搜索结果
|
||||
if raw_results and raw_results != [] and raw_results != {}:
|
||||
search_results.append(item)
|
||||
else:
|
||||
other_results.append(item)
|
||||
|
||||
# 如果没有搜索结果，返回原始结果
|
||||
if not search_results:
|
||||
return intermediate_outputs
|
||||
|
||||
# 如果只有一个搜索结果，优化格式后返回
|
||||
if len(search_results) == 1:
|
||||
optimized = optimize_search_results(search_results)
|
||||
return other_results + optimized
|
||||
|
||||
# 合并多个搜索结果
|
||||
merged_raw_results = {}
|
||||
all_queries = []
|
||||
|
||||
for result in search_results:
|
||||
query = result.get('query', '')
|
||||
if query:
|
||||
all_queries.append(query)
|
||||
|
||||
raw_results = result.get('raw_results', {})
|
||||
|
||||
# 合并各种搜索类型的结果
|
||||
for search_type in ['time_search', 'keyword_search', 'embedding_search', 'combined_summary',
|
||||
'reranked_results']:
|
||||
if search_type in raw_results and raw_results[search_type]:
|
||||
if search_type not in merged_raw_results:
|
||||
merged_raw_results[search_type] = raw_results[search_type]
|
||||
else:
|
||||
# 如果是字典类型，需要合并
|
||||
if isinstance(raw_results[search_type], dict) and isinstance(merged_raw_results[search_type], dict):
|
||||
for key, value in raw_results[search_type].items():
|
||||
if key not in merged_raw_results[search_type]:
|
||||
merged_raw_results[search_type][key] = value
|
||||
elif isinstance(value, list) and isinstance(merged_raw_results[search_type][key], list):
|
||||
merged_raw_results[search_type][key].extend(value)
|
||||
elif isinstance(raw_results[search_type], list):
|
||||
if isinstance(merged_raw_results[search_type], list):
|
||||
merged_raw_results[search_type].extend(raw_results[search_type])
|
||||
else:
|
||||
merged_raw_results[search_type] = raw_results[search_type]
|
||||
|
||||
# 创建合并后的结果
|
||||
if merged_raw_results:
|
||||
merged_result = {
|
||||
"type": "search_result",
|
||||
"title": f"合并检索结果 (共{len(search_results)}个查询)",
|
||||
"query": " | ".join(all_queries),
|
||||
"raw_results": merged_raw_results,
|
||||
"index": 1,
|
||||
"total": 1
|
||||
}
|
||||
return other_results + [merged_result]
|
||||
|
||||
return other_results
|
||||
38
api/app/core/memory/agent/utils/model_tool.py
Normal file
38
api/app/core/memory/agent/utils/model_tool.py
Normal file
@@ -0,0 +1,38 @@
|
||||
|
||||
|
||||
# project_root = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
# sys.path.insert(0, project_root)
|
||||
|
||||
# load_dotenv()
|
||||
|
||||
# async def llm_client_chat(messages: List[dict]) -> str:
|
||||
# """使用 OpenAI 兼容接口进行对话，返回内容字符串。"""
|
||||
# try:
|
||||
# cfg = get_model_config(SELECTED_LLM_ID)
|
||||
# rb_config = RedBearModelConfig(
|
||||
# model_name=cfg["model_name"],
|
||||
# provider=cfg["provider"],
|
||||
# api_key=cfg["api_key"],
|
||||
# base_url=cfg["base_url"],
|
||||
# )
|
||||
# client = OpenAIClient(model_config=rb_config, type_="chat")
|
||||
|
||||
# except Exception as e:
|
||||
# logger.error(f"获取模型配置失败：{e}")
|
||||
# err = f"获取模型配置失败：{str(e)}。请检查!!!"
|
||||
# return err
|
||||
# try:
|
||||
# response = await client.chat(messages)
|
||||
# print(f"model_tool's llm_client_chat response ======>:\n {response}")
|
||||
# return _extract_content(response)
|
||||
# # return _extract_content(result)
|
||||
# except Exception as e:
|
||||
# logger.error(f"LLM调用失败：{str(e)}。请检查 model_name、api_key、api_base 是否正确。")
|
||||
# return f"LLM调用失败：{str(e)}。请检查 model_name、api_key、api_base 是否正确。"
|
||||
|
||||
# async def main(image_url):
|
||||
# await llm_client_chat(image_url)
|
||||
#
|
||||
# # 运行主函数
|
||||
# asyncio.run(main(['https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_male2.wav']))
|
||||
#
|
||||
131
api/app/core/memory/agent/utils/multimodal.py
Normal file
131
api/app/core/memory/agent/utils/multimodal.py
Normal file
@@ -0,0 +1,131 @@
|
||||
"""
|
||||
Multimodal input processor for handling image and audio content.
|
||||
|
||||
This module provides utilities for detecting and processing multimodal inputs
|
||||
(images and audio files) by converting them to text using appropriate models.
|
||||
"""
|
||||
|
||||
import logging
|
||||
from typing import List
|
||||
|
||||
from app.core.memory.agent.multimodal.speech_model import Vico_recognition
|
||||
from app.core.memory.agent.utils.llm_tools import picture_model_requests
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class MultimodalProcessor:
|
||||
"""
|
||||
Processor for handling multimodal inputs (images and audio).
|
||||
|
||||
This class detects image and audio file paths in input content and converts
|
||||
them to text using appropriate recognition models.
|
||||
"""
|
||||
|
||||
# Supported file extensions
|
||||
IMAGE_EXTENSIONS = ['.jpg', '.png']
|
||||
AUDIO_EXTENSIONS = [
|
||||
'aac', 'amr', 'avi', 'flac', 'flv', 'm4a', 'mkv', 'mov',
|
||||
'mp3', 'mp4', 'mpeg', 'ogg', 'opus', 'wav', 'webm', 'wma', 'wmv'
|
||||
]
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the multimodal processor."""
|
||||
pass
|
||||
|
||||
def is_image(self, content: str) -> bool:
|
||||
"""
|
||||
Check if content is an image file path.
|
||||
|
||||
Args:
|
||||
content: Input string to check
|
||||
|
||||
Returns:
|
||||
True if content ends with a supported image extension
|
||||
|
||||
Examples:
|
||||
>>> processor = MultimodalProcessor()
|
||||
>>> processor.is_image("photo.jpg")
|
||||
True
|
||||
>>> processor.is_image("document.pdf")
|
||||
False
|
||||
"""
|
||||
if not isinstance(content, str):
|
||||
return False
|
||||
|
||||
content_lower = content.lower()
|
||||
return any(content_lower.endswith(ext) for ext in self.IMAGE_EXTENSIONS)
|
||||
|
||||
def is_audio(self, content: str) -> bool:
|
||||
"""
|
||||
Check if content is an audio file path.
|
||||
|
||||
Args:
|
||||
content: Input string to check
|
||||
|
||||
Returns:
|
||||
True if content ends with a supported audio extension
|
||||
|
||||
Examples:
|
||||
>>> processor = MultimodalProcessor()
|
||||
>>> processor.is_audio("recording.mp3")
|
||||
True
|
||||
>>> processor.is_audio("video.mp4")
|
||||
True
|
||||
>>> processor.is_audio("document.txt")
|
||||
False
|
||||
"""
|
||||
if not isinstance(content, str):
|
||||
return False
|
||||
|
||||
content_lower = content.lower()
|
||||
return any(content_lower.endswith(f'.{ext}') for ext in self.AUDIO_EXTENSIONS)
|
||||
|
||||
async def process_input(self, content: str) -> str:
|
||||
"""
|
||||
Process input content, converting images/audio to text if needed.
|
||||
|
||||
This method detects if the input is an image or audio file and converts
|
||||
it to text using the appropriate recognition model. If processing fails
|
||||
or the content is not multimodal, it returns the original content.
|
||||
|
||||
Args:
|
||||
content: Input string (may be file path or regular text)
|
||||
|
||||
Returns:
|
||||
Text content (original or converted from image/audio)
|
||||
|
||||
Examples:
|
||||
>>> processor = MultimodalProcessor()
|
||||
>>> await processor.process_input("photo.jpg")
|
||||
"Recognized text from image..."
|
||||
|
||||
>>> await processor.process_input("Hello world")
|
||||
"Hello world"
|
||||
"""
|
||||
if not isinstance(content, str):
|
||||
logger.warning(f"[MultimodalProcessor] Content is not a string: {type(content)}")
|
||||
return str(content)
|
||||
|
||||
try:
|
||||
# Check for image input
|
||||
if self.is_image(content):
|
||||
logger.info(f"[MultimodalProcessor] Detected image input: {content}")
|
||||
result = await picture_model_requests(content)
|
||||
logger.info(f"[MultimodalProcessor] Image recognition result: {result[:100]}...")
|
||||
return result
|
||||
|
||||
# Check for audio input
|
||||
if self.is_audio(content):
|
||||
logger.info(f"[MultimodalProcessor] Detected audio input: {content}")
|
||||
result = await Vico_recognition([content]).run()
|
||||
logger.info(f"[MultimodalProcessor] Audio recognition result: {result[:100]}...")
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[MultimodalProcessor] Error processing multimodal input: {e}", exc_info=True)
|
||||
logger.info("[MultimodalProcessor] Falling back to original content")
|
||||
return content
|
||||
|
||||
# Return original content if not multimodal
|
||||
return content
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user