Commit Graph

457 Commits

Author SHA1 Message Date
lixinyue
a2a69840f7 config_config替换成memory_config 2026-01-22 16:38:24 +08:00
lanceyq
3a4a7590c2 [fix]Fix the memory interface to use end_user_id. 2026-01-22 16:36:12 +08:00
lixinyue
bcc8b7ce3c config_config替换成memory_config 2026-01-22 16:11:48 +08:00
lixinyue
1c7fe6d134 config_config替换成memory_config 2026-01-22 14:59:01 +08:00
lixinyue
c4039f52bd 把group_id替换end_user_id_ 2026-01-22 12:12:41 +08:00
lixinyue
bd851d5e86 Merge branch 'refs/heads/develop' into fix/memory_bug_fix 2026-01-22 12:11:43 +08:00
lixinyue
00e448c5d6 Merge remote-tracking branch 'origin/develop' into develop 2026-01-22 12:11:17 +08:00
Mark
5ff8cdb13a [add] aiofile 2026-01-22 11:50:21 +08:00
Mark
44783574c0 Merge pull request #173 from SuanmoSuanyangTechnology/fix/memory_mcp2_1
Fix/memory mcp2 1
2026-01-22 11:40:33 +08:00
lixinyue
1e7c53d944 (用户摘要) (用户兴趣分布) (记忆洞察) (反思)优化中翻译英,参数放置Headers 2026-01-22 11:29:36 +08:00
lixinyue
655ae796fd (用户摘要) (用户兴趣分布) (记忆洞察) (反思)优化中翻译英,参数放置Headers 2026-01-22 11:25:09 +08:00
lixinyue
93686dbc1e Merge branch 'refs/heads/develop' into fix/memory_mcp2_1 2026-01-22 11:11:50 +08:00
lanceyq
c08b10c20f [fix]Modify the "Implicit and Emotional Caching" prompt message 2026-01-22 10:41:31 +08:00
Mark
16c0d9bb6c [add] migration script 2026-01-22 10:28:40 +08:00
Mark
9f0d1616a8 [modify] flower >= 2.0.1 to requirements.txt 2026-01-22 10:23:28 +08:00
Mark
fafab973ee Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop
# Conflicts:
#	api/pyproject.toml
2026-01-22 10:22:40 +08:00
lixinyue
4648ec04c7 Merge remote-tracking branch 'origin/develop' into develop
# Conflicts:
#	api/app/core/memory/agent/langgraph_graph/nodes/problem_nodes.py
2026-01-22 10:20:37 +08:00
Mark
64e4411048 [add] file storage service 2026-01-22 10:12:23 +08:00
lixinyue
4aeec8afbf 把group_id替换end_user_id_ 2026-01-21 20:37:39 +08:00
lixinyue
f0efed8aa1 把group_id替换end_user_id 2026-01-21 20:33:22 +08:00
lixinyue
4a4931bee2 新增中翻英功能(记忆时间线)(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 2026-01-21 19:37:03 +08:00
lixinyue11
fb25495f1b Fix/memory mcp2 1 (#170)
* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* feat(celery): add comprehensive logging to worker and write task

- Initialize logging system in Celery worker entry point with LoggingConfig
- Add logger instance and startup message to celery_worker.py
- Reorganize imports in tasks.py for better readability and consistency
- Add detailed logging to write_message_task for debugging and monitoring
- Log task start with group_id, config_id, and storage_type parameters
- Log service execution and completion status with results
- Add exception handling with error logging and stack trace capture
- Log task completion time and Celery task ID for performance tracking
- Improves observability and troubleshooting of async task execution

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 快速检索,需要在接口部分添加LLM整合

* 快速检索,需要在接口部分添加LLM整合

---------

Co-authored-by: Ke Sun <kesun5@illinois.edu>
2026-01-21 18:21:51 +08:00
乐力齐
b6e6dbf27f Fix/memory interface (#169)
* [changes]《Modify the interface》
1.Remove the "/search/entity_graph" interface
2.Reconstruct the "/updated_end_user/profile" interface
3.Remove the "Update Username" interface
4.Fix the batch query of user association memory configuration

* [changes]《Modify the interface》
1.Remove the "/search/entity_graph" interface
2.Reconstruct the "/updated_end_user/profile" interface
3.Remove the "Update Username" interface
4.Fix the batch query of user association memory configuration

* [fix]Fix the error response type
2026-01-21 18:20:28 +08:00
lixinyue
bd5b97e69b 快速检索,需要在接口部分添加LLM整合 2026-01-21 18:16:49 +08:00
lixinyue
6e1f6d886d 快速检索,需要在接口部分添加LLM整合 2026-01-21 18:11:46 +08:00
lixinyue
940af67a87 Merge remote-tracking branch 'origin/develop' into develop 2026-01-21 18:10:46 +08:00
Ke Sun
c24fb73147 Fix/memory celery fix (#168)
* refactor(celery): optimize task routing and worker configuration

- Simplify Celery queue configuration with single default 'io_tasks' queue
- Implement task routing strategy separating IO-bound and CPU-bound tasks
- Add Flower monitoring support with task event tracking enabled
- Add summary node search optimization to only retrieve summary nodes
- Clean up unused imports and reorganize import statements for consistency
- Update docker-compose configuration to support multi-queue worker setup

* chore(celery): simplify flower configuration and add gevent dependency

* chore(dependencies): add gevent dependency to requirements

- Add gevent==24.11.1 to api/requirements.txt
- Gevent is required for async worker support in Celery
- Complements existing flower and celery configuration

* refactor(celery): simplify async event loop handling and reorganize task queues

- Replace complex nest_asyncio and manual event loop management with asyncio.run() in read_message_task, write_message_task, regenerate_memory_cache, and workspace_reflection_task
- Rename task queues from io_tasks/cpu_tasks to memory_tasks/document_tasks for better semantic clarity
- Update task routing configuration to reflect new queue names for memory agent tasks and document processing tasks
- Remove redundant exception handling comments and simplify error handling logic
- Update README with improved community support section including GitHub Issues, Pull Requests, Discussions, and WeChat community links
- Simplifies event loop management by leveraging asyncio.run() which handles loop creation and cleanup automatically, reducing code complexity and potential race conditions
2026-01-21 17:58:46 +08:00
lixinyue
4e96c12634 Merge remote-tracking branch 'origin/develop' into develop 2026-01-21 16:04:56 +08:00
乐力齐
37ef497f4c Feature/distinction role (#167)
* [feature]A set of information for role recognition writing

* [feature]A set of information for role recognition writing

* [fix]Fix the code after rebasing.

* [feature]A set of information for role recognition writing

* [fix]Fix the code after rebasing.

* [fix]Based on the AI review to fix the code

* [changes]Disable the function of batch writing multiple groups of conversations in a cumulative manner

* [fix]Addressing vulnerability risks

* [fix]Fixing short-term memory writing

* [feature]A set of information for role recognition writing

* [fix]Fix the code after rebasing.

* [feature]A set of information for role recognition writing

* [fix]Fix the code after rebasing.

* [fix]Based on the AI review to fix the code

* [fix]Fixing short-term memory writing
2026-01-21 16:04:16 +08:00
乐力齐
2e504f9c48 Feature/distinction role (#165)
* [feature]A set of information for role recognition writing

* [feature]A set of information for role recognition writing

* [fix]Fix the code after rebasing.

* [feature]A set of information for role recognition writing

* [fix]Fix the code after rebasing.

* [fix]Based on the AI review to fix the code

* [changes]Disable the function of batch writing multiple groups of conversations in a cumulative manner

* [fix]Addressing vulnerability risks
2026-01-21 13:55:32 +08:00
lixinyue
3be3604125 Merge branch 'refs/heads/fix/memory_mcp2_1' into develop
# Conflicts:
#	api/app/core/memory/agent/langgraph_graph/nodes/problem_nodes.py
#	api/app/core/memory/agent/langgraph_graph/nodes/summary_nodes.py
#	api/app/core/memory/agent/langgraph_graph/nodes/verification_nodes.py
#	api/app/core/memory/agent/langgraph_graph/read_graph.py
#	api/app/core/memory/agent/langgraph_graph/routing/routers.py
#	api/app/core/memory/agent/models/verification_models.py
#	api/app/core/memory/agent/services/optimized_llm_service.py
2026-01-21 11:45:17 +08:00
lixinyue11
6920deef63 Fix/memory bug fix (#162)
* 图谱数据量限制数量去掉

* 图谱数据量限制数量去掉

* 图谱数据量限制数量去掉

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 读取的接口,去掉全局锁

* 输出数组

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化测试接口

* 反思优化测试接口

* 读取接口内层嵌套BUG修复

* 读取接口内层嵌套BUG修复

* 读取接口内层嵌套BUG修复

* 读取接口内层嵌套BUG修复

* 读取接口内层嵌套BUG修复

* 新增中翻英功能(记忆时间线)(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)

* 新增中翻英功能(记忆时间线)(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段

* 新增中翻英功能(记忆时间线)(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段

* 新增中翻英功能(记忆时间线)(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段

* 新增中翻英功能(记忆时间线)(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段

* 新增中翻英功能(记忆时间线)(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段
2026-01-21 11:33:52 +08:00
Mark
6c30347219 Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop 2026-01-21 11:28:38 +08:00
Mark
d6b08b3c5c [modify] uv.lock 2026-01-21 11:28:29 +08:00
Mark
21ec923f24 Merge pull request #164 from SuanmoSuanyangTechnology/fix/workflow-parallelization
fix(workflow): fix improper merge of execution flows caused by multi-branch routing
2026-01-21 11:26:40 +08:00
Eternity
3a0eab068c perf(workflow): optimize logging output for workflow nodes 2026-01-21 11:18:29 +08:00
Eternity
8aa496f588 fix(workflow): fix improper merge of execution flows caused by multi-branch routing 2026-01-21 11:09:48 +08:00
lixinyue11
af7b9ee41c Fix/memory bug fix (#161)
* 图谱数据量限制数量去掉

* 图谱数据量限制数量去掉

* 图谱数据量限制数量去掉

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 读取的接口,去掉全局锁

* 输出数组

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化测试接口

* 反思优化测试接口

* 读取接口内层嵌套BUG修复

* 读取接口内层嵌套BUG修复

* 读取接口内层嵌套BUG修复

* 读取接口内层嵌套BUG修复

* 读取接口内层嵌套BUG修复
2026-01-20 19:14:59 +08:00
Ke Sun
83fe793e72 refactor(memory): clean up deprecated config and self-reflexion utilities
- Remove deprecated self_reflexion endpoint from memory_storage_controller
- Delete obsolete config modules (config_optimization, definitions, get_example_data, litellm_config)
- Remove self_reflexion_utils package and related evaluation/reflexion modules
- Refactor hot_memory_tags to use Neo4jConnector instead of direct GraphDatabase connection
- Simplify LLM client initialization by removing DEFAULT_LLM_ID fallback logic
- Remove unnecessary sys.path manipulation and project root resolution code
- Update filter_tags_with_llm to properly handle missing config with clear error messages
- Migrate get_raw_tags_from_db to async function using Neo4jConnector
- Consolidate imports and remove unused dependencies (uuid, sys)
- Improve error handling with explicit ValueError messages for missing configuration
2026-01-20 15:03:29 +08:00
lixinyue11
9d36ec70bc Fix/memory bug fix (#157)
* 图谱数据量限制数量去掉

* 图谱数据量限制数量去掉

* 图谱数据量限制数量去掉

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 读取的接口,去掉全局锁

* 输出数组

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化测试接口

* 反思优化测试接口
2026-01-20 11:24:33 +08:00
lixinyue11
e518b57dea Fix/memory bug fix (#150)
* 图谱数据量限制数量去掉

* 图谱数据量限制数量去掉

* 图谱数据量限制数量去掉

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 用户详情优化

* 读取的接口,去掉全局锁

* 输出数组

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化1.0(优化隐私输出、时间检索)

* 反思优化1.0(优化隐私输出、时间检索)
2026-01-20 10:39:12 +08:00
lixinyue11
642587fc97 Fix/memory mcp2 1 (#145)
* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* 去掉MCP框架,重构

* feat(celery): add comprehensive logging to worker and write task

- Initialize logging system in Celery worker entry point with LoggingConfig
- Add logger instance and startup message to celery_worker.py
- Reorganize imports in tasks.py for better readability and consistency
- Add detailed logging to write_message_task for debugging and monitoring
- Log task start with group_id, config_id, and storage_type parameters
- Log service execution and completion status with results
- Add exception handling with error logging and stack trace capture
- Log task completion time and Celery task ID for performance tracking
- Improves observability and troubleshooting of async task execution

* 去掉MCP框架,重构

* 去掉MCP框架,重构

---------

Co-authored-by: Ke Sun <kesun5@illinois.edu>
2026-01-20 10:36:30 +08:00
lixinyue
8881daf592 去掉MCP框架,重构 2026-01-20 10:16:22 +08:00
lixinyue
4976fccf7d 去掉MCP框架,重构 2026-01-19 19:06:56 +08:00
lixinyue
ee2d3fd53a Merge branch 'refs/heads/develop' into fix/memory_mcp2_1 2026-01-19 19:05:36 +08:00
Ke Sun
63baf3bd40 feat(celery): add comprehensive logging to worker and write task
- Initialize logging system in Celery worker entry point with LoggingConfig
- Add logger instance and startup message to celery_worker.py
- Reorganize imports in tasks.py for better readability and consistency
- Add detailed logging to write_message_task for debugging and monitoring
- Log task start with group_id, config_id, and storage_type parameters
- Log service execution and completion status with results
- Add exception handling with error logging and stack trace capture
- Log task completion time and Celery task ID for performance tracking
- Improves observability and troubleshooting of async task execution
2026-01-19 19:01:51 +08:00
乐力齐
12a27dbcf7 Feature/memory redis (#152)
* [feature]Emotional memory cache

* [feature]Implicit memory cache

* [changes]Modify the expiration time of implicit memory to 24 hours.

* [feature]Emotional memory cache

* [feature]Implicit memory cache

* [changes]Modify the expiration time of implicit memory to 24 hours.

* [changes]Modify the code based on the AI review

* [feature]Emotional memory cache

* [feature]Implicit memory cache

* [changes]Modify the expiration time of implicit memory to 24 hours.

* [feature]Implicit memory cache

* [changes]Modify the code based on the AI review

* [changes]Modify the generated emotion cache to be "end_user_id"

* [feature]Emotional memory cache

* [feature]Implicit memory cache

* [changes]Modify the code based on the AI review

* [feature]Emotional memory cache

* [changes]Modify the code based on the AI review

* [changes]Modify the generated emotion cache to be "end_user_id"
2026-01-19 17:56:52 +08:00
lixinyue
547ce858e7 去掉MCP框架,重构 2026-01-19 17:52:04 +08:00
lixinyue
995b896b9d 去掉MCP框架,重构 2026-01-19 17:15:19 +08:00
乐力齐
9d25b08641 Feature/memory redis (#151)
* [feature]Emotional memory cache

* [feature]Implicit memory cache

* [changes]Modify the expiration time of implicit memory to 24 hours.

* [feature]Emotional memory cache

* [feature]Implicit memory cache

* [changes]Modify the expiration time of implicit memory to 24 hours.

* [changes]Modify the code based on the AI review

* [feature]Emotional memory cache

* [feature]Implicit memory cache

* [changes]Modify the expiration time of implicit memory to 24 hours.

* [feature]Implicit memory cache

* [changes]Modify the code based on the AI review
2026-01-19 16:41:11 +08:00