Fix/language unification (#283)

* [changes]add user_summary language unification

* [add]Entity extraction, user memory, emotion suggestions, unified language type for writing

* [add]Complete the switch between Chinese and English for the emotion labels and emotion suggestions fields.

* [changes]add user_summary language unification

* [add]Entity extraction, user memory, emotion suggestions, unified language type for writing

* [add]Complete the switch between Chinese and English for the emotion labels and emotion suggestions fields.

* [changes]Modify the code based on the AI review
This commit is contained in:
乐力齐
2026-02-03 16:03:08 +08:00
committed by GitHub
parent 63fa4dc8ec
commit 8670aaba1e
30 changed files with 1033 additions and 810 deletions

View File

@@ -25,12 +25,12 @@ from fastapi import APIRouter, Depends, HTTPException, Header
from sqlalchemy.orm import Session
from app.core.error_codes import BizCode
from app.core.language_utils import get_language_from_header
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.services.memory_base_service import Translation_English
from app.core.memory.models.ontology_models import OntologyClass
from typing import List
from app.schemas.ontology_schemas import (
@@ -63,72 +63,6 @@ router = APIRouter(
)
async def translate_ontology_classes(
classes: List[OntologyClass],
model_id: str
) -> List[OntologyClass]:
"""翻译本体类列表
将本体类的中文字段翻译为英文,包括:
- name_chinese: 中文名称
- description: 描述
- examples: 示例列表
Args:
classes: 本体类列表
model_id: LLM模型ID用于翻译
Returns:
List[OntologyClass]: 翻译后的本体类列表
"""
translated_classes = []
for ontology_class in classes:
# 创建类的副本,避免修改原对象
translated_class = ontology_class.model_copy(deep=True)
# 翻译 name_chinese 字段
if translated_class.name_chinese:
try:
translated_class.name_chinese = await Translation_English(
model_id,
translated_class.name_chinese
)
except Exception as e:
logger.warning(f"Failed to translate name_chinese: {e}")
# 保留原文
# 翻译 description 字段
if translated_class.description:
try:
translated_class.description = await Translation_English(
model_id,
translated_class.description
)
except Exception as e:
logger.warning(f"Failed to translate description: {e}")
# 保留原文
# 翻译 examples 列表
if translated_class.examples:
translated_examples = []
for example in translated_class.examples:
try:
translated_example = await Translation_English(
model_id,
example
)
translated_examples.append(translated_example)
except Exception as e:
logger.warning(f"Failed to translate example: {e}")
translated_examples.append(example) # 保留原文
translated_class.examples = translated_examples
translated_classes.append(translated_class)
return translated_classes
def _get_ontology_service(
db: Session = Depends(get_db),
current_user: User = Depends(get_current_user),
@@ -243,7 +177,7 @@ def _get_ontology_service(
@router.post("/extract", response_model=ApiResponse)
async def extract_ontology(
request: ExtractionRequest,
language_type: str = Header(default="zh", alias="X-Language-Type"),
language_type: str = Header(default=None, alias="X-Language-Type"),
db: Session = Depends(get_db),
current_user: User = Depends(get_current_user)
):
@@ -260,31 +194,6 @@ async def extract_ontology(
db: 数据库会话
current_user: 当前用户
Returns:
ApiResponse: 包含提取结果的响应
Response format:
{
"code": 200,
"msg": "本体提取成功",
"data": {
"classes": [
{
"id": "147d9db50b524a9e909e01a753d3acdd",
"name": "Patient",
"name_chinese": "患者",
"description": "在医疗机构中接受诊疗、护理或健康管理的个体",
"examples": ["糖尿病患者", "术后康复患者", "门诊初诊患者"],
"parent_class": null,
"entity_type": "Person",
"domain": "Healthcare"
},
...
],
"domain": "Healthcare",
"extracted_count": 7
}
}
"""
api_logger.info(
f"Ontology extraction requested by user {current_user.id}, "
@@ -296,6 +205,9 @@ async def extract_ontology(
)
try:
# 使用集中化的语言校验
language = get_language_from_header(language_type)
# 获取当前工作空间ID
workspace_id = current_user.current_workspace_id
if not workspace_id:
@@ -314,33 +226,11 @@ async def extract_ontology(
scenario=request.scenario,
domain=request.domain,
scene_id=request.scene_id,
workspace_id=workspace_id
workspace_id=workspace_id,
language=language
)
# ===== 新增:翻译逻辑 =====
# 如果需要英文,则翻译数据
if language_type != 'zh':
api_logger.info(f"Translating extraction result to English")
# 翻译 classes 列表
result.classes = await translate_ontology_classes(
result.classes,
request.llm_id
)
# 翻译 domain 字段
if result.domain:
try:
result.domain = await Translation_English(
request.llm_id,
result.domain
)
except Exception as e:
logger.warning(f"Failed to translate domain: {e}")
# 保留原文
# ===== 翻译逻辑结束 =====
# 构建响应
# 构建响应(语言已在提取时通过模板控制,无需二次翻译)
response = ExtractionResponse(
classes=result.classes,
domain=result.domain,