adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
229 Commits 37 Branches 16 Tags
8fc5cc3bb606aa46ddef051355bd9fa70cb5644f
Commit Graph

95 Commits

Author SHA1 Message Date
Ke Sun
667c3393bc refactor(core/models): reorganize imports and add Bedrock connection pooling 
- Introduce BEDROCK_MAX_POOL_CONNECTIONS environment variable (default: 50)
- Introduce BEDROCK_MAX_RETRIES environment variable (default: 2)
 2025-12-29 14:00:03 +08:00
lixiangcheng1
c6d8d6b301 Merge branch 'feature/20251219_lxc' into develop 2025-12-29 11:55:45 +08:00
lixiangcheng1
34fa178f11 [fix]build_graphrag_for_kb 2025-12-29 11:55:17 +08:00
Ke Sun
4d187b9c19 feat(ontology): add learning/education domain predicates 
Add new predicates for learning/education domain to support educational content extraction. Also add field validator to filter empty statements in extraction response to handle malformed LLM outputs.
 2025-12-28 18:05:04 +08:00
lixiangcheng1
cd12844a7c [fix]build knowledge graph 2025-12-27 17:12:04 +08:00
lixiangcheng1
a0c362244e [ADD]Add functions related to knowledge base graph: 
Add functions related to knowledge base graph:
1. Entity type generation,
2. Knowledge base graph acquisition,
3. Hard deletion of knowledge base graph,
4. Knowledge base graph reconstruction (asynchronous)
 2025-12-27 13:53:10 +08:00
谢俊男
9fb7d7d059 feat(tool system): Optimization of the tool system 
1. Optimization of the JSON tool, add insert, replace, delete, parse
2. Optimization of the mcp test_connection
3. tool list desc
4. datetime_tool default timezone set Asia/Shanghai
 2025-12-26 19:11:20 +08:00
朱文辉
05e25c5882 Merge #72 into develop from feature/20251219_myh 
feat(workflow): add parameter extraction node

* feature/20251219_myh: (2 commits)
  feat(workflow): add parameter extraction node
  perf(prompt_opt): improve prompt optimization and model output quality

Signed-off-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Merged-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/72
 2025-12-26 17:48:24 +08:00
mengyonghao
ca89aba548 perf(prompt_opt): improve prompt optimization and model output quality 2025-12-26 17:45:14 +08:00
mengyonghao
fc15a7793a feat(workflow): add parameter extraction node 
- Implemented ParameterExtractorNode to extract structured parameters from input text using LLM.
- Supports dynamic Jinja2 prompt rendering with field descriptions and types.
- Integrates with RedBearLLM and ModelConfigService for model retrieval.
- Handles JSON repair and raises clear BusinessException on parsing errors.
 2025-12-26 14:39:17 +08:00
朱文辉
58a0c619fd Merge #66 into develop from feature/20251219_xjn 
feat(tool system): Tool info add tags variable

* feature/20251219_xjn: (1 commits)
  feat(tool system): Tool info add tags variable

Signed-off-by: 谢俊男 <accounts_6853d0ea6f8174722fb0c8f1@mail.teambition.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Merged-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/66
 2025-12-26 12:28:06 +08:00
Ke Sun
bf1dfd97f0 feat(memory-api): implement memory read/write API service endpoints 
- Add MemoryAPIService with read_memory and write_memory methods for managing user memories
- Create memory_api_schema.py with request/response schemas for read and write operations
- Implement write_memory_api_service endpoint for storing memory content with configurable storage backends
- Implement read_memory_api_service endpoint for querying memories with context-aware responses
- Add memory-specific error codes (MEMORY_WRITE_FAILED, MEMORY_READ_FAILED, MEMORY_CONFIG_NOT_FOUND) to error_codes.py
 2025-12-26 11:43:51 +08:00
谢俊男
4a9d4aa2e3 feat(tool system): Tool info add tags variable 2025-12-26 11:04:16 +08:00
lanceyq
8900fc4dab [fix]Refresh formatted output 2025-12-25 18:56:37 +08:00
mengyonghao
7181d41e51 feat(workflow): add VariableAggregatorNode for aggregating workflow variables 2025-12-25 18:38:53 +08:00
朱文辉
31918d5847 Merge #57 into develop from feature/20251219_myh 
feat(workflow): add Jinja2 template rendering node

* feature/20251219_myh: (4 commits)
  feat(workflow): support variables wrapped with {{}} in assignment nodes, add input config example
  feat(workflow): add default User-Agent and redirect following for HTTP request ...
  fix(workflow): fix missing re-ranking for hybrid retrieval results in knowledge...
  feat(workflow): add Jinja2 template rendering node

Signed-off-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Merged-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/57
 2025-12-25 17:38:27 +08:00
谢俊男
04be3088a2 feat(tool system): Tool system reengineering 2025-12-25 17:30:20 +08:00
谢俊男
3bcaead413 feat(tool system): tool system development 2025-12-25 17:28:21 +08:00
mengyonghao
eeb7a3a68d feat(workflow): add Jinja2 template rendering node 2025-12-25 16:54:57 +08:00
mengyonghao
0b141fb952 fix(workflow): fix missing re-ranking for hybrid retrieval results in knowledge base node, add config example 2025-12-25 14:47:22 +08:00
mengyonghao
aef7ae2cce feat(workflow): add default User-Agent and redirect following for HTTP request node, add config example 2025-12-25 14:44:47 +08:00
mengyonghao
8accd36f9e feat(workflow): support variables wrapped with {{}} in assignment nodes, add input config example 2025-12-25 14:41:41 +08:00
朱文辉
02204889ea Merge #51 into develop from feature/20251219_myh 
feat(workflow): add HTTP request node

* feature/20251219_myh: (3 commits)
  feat(workflow): add HTTP request node
  refactor(workflow): organize knowledge base code structure and add comments
  fix(workflow): correct property usage in HTTP request node

Signed-off-by: Eternity <1533512157@qq.com>
Commented-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Merged-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/51
 2025-12-25 13:52:35 +08:00
mengyonghao
68901e2642 fix(workflow): correct property usage in HTTP request node 2025-12-24 21:32:38 +08:00
mengyonghao
3993aa55ea refactor(workflow): organize knowledge base code structure and add comments 2025-12-24 21:24:21 +08:00
mengyonghao
31a7727992 feat(workflow): add HTTP request node 
- Introduce a new HttpRequestNode to enable external HTTP API calls in workflows
- Support multiple HTTP methods (GET, POST, PUT, DELETE, PATCH, HEAD)
- Support authentication strategies (None, Basic, Bearer, Custom header)
- Support multiple request body types (JSON, form-data, x-www-form-urlencoded, raw)
- Add configurable timeout, retry, and SSL verification
- Provide flexible error handling strategies (none, default response, branch)
 2025-12-24 21:23:08 +08:00
lixiangcheng1
6338edda11 [ADD]Support parsing of unstructured data MP3, MP4, etc 2025-12-24 17:50:03 +08:00
Ke Sun
292fef0fa7 Merge remote-tracking branch 'origin/develop' into refactor/memory-config-management 2025-12-24 16:07:27 +08:00
李新月
3afe547559 Merge #37 into develop from fix/memory_reflection 
反思输出输入格式统一

* fix/memory_reflection: (60 commits squashed)

  - 新增反思功能（功能配置接口+反思celery后台检测反思的迭代周期）

  - 新增反思功能（功能配置接口+反思celery后台检测反思的迭代周期）

  - 新增反思功能（检测代码/规范化程序）

  - 新增反思功能（检测代码/规范化程序）

  - 新增反思功能（检测代码/规范化程序）

  - 新增反思功能（检测代码/规范化程序）

  - 新增反思功能（检测代码/规范化程序）

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - 反思优化

  - Merge branch develop into fix/memory_reflection (Conflict resolved online)
    
    
    # Conflicts:  
    #      api/app/controllers/memory_reflection_controller.py
    #      api/app/schemas/memory_reflection_schemas.py

  - 反思优化

  - Merge remote-tracking branch &#39;origin/fix/memory_reflection&#39; into fix/memory_reflection

  - 统一输出

  - 统一输出

  - 统一输出

  - Merge branch develop into fix/memory_reflection (Conflict resolved online)
    
    
    # Conflicts:  
    #      api/app/controllers/memory_reflection_controller.py

  - 统一输出

  - Merge remote-tracking branch &#39;origin/fix/memory_reflection&#39; into fix/memory_reflection

  - 统一输出

  - 反思速度提升，从4分钟优化成1分10-40秒

  - 反思速度提升，从4分钟优化成1分10-40秒

  - 反思速度提升，从4分钟优化成1分10-40秒

  - Merge branch develop into fix/memory_reflection (Conflict resolved online)
    
    
    # Conflicts:  
    #      api/app/core/memory/storage_services/reflection_engine/self_reflexion.py

  - 反思速度提升，从4分钟优化成1分10-40秒

  - Merge remote-tracking branch &#39;origin/fix/memory_reflection&#39; into fix/memory_reflection
    
    # Conflicts:
    #&#9;api/app/core/memory/storage_services/reflection_engine/self_reflexion.py

  - 更新 self_reflexion.py

  - 反思图谱添加边的修改

  - Merge remote-tracking branch &#39;origin/fix/memory_reflection&#39; into fix/memory_reflection
    
    # Conflicts:
    #&#9;api/app/core/memory/storage_services/reflection_engine/self_reflexion.py

  - 反思图谱添加边的修改

  - 反思图谱添加边的修改

  - 反思图谱添加边的修改

  - 反思图谱添加边的修改

  - 反思图谱添加边的修改

  - update
    
    
    # Conflicts:  
    #      api/app/core/memory/storage_services/reflection_engine/self_reflexion.py
    #      api/app/core/memory/utils/prompt/prompts/reflexion.jinja2

  - 反思BUG修复

  - Merge remote-tracking branch &#39;origin/fix/memory_reflection&#39; into fix/memory_reflection

  - 反思BUG修复

  - Merge branch develop into fix/memory_reflection (Conflict resolved online)
    
    
    # Conflicts:  
    #      api/app/core/memory/storage_services/reflection_engine/self_reflexion.py

  - 反思BUG修复

  - Merge remote-tracking branch &#39;origin/fix/memory_reflection&#39; into fix/memory_reflection

  - 反思输出输入格式统一

  - Merge branch develop into fix/memory_reflection (Conflict resolved online)
    
    
    # Conflicts:  
    #      api/app/core/memory/utils/prompt/template_render.py

  - 反思优化提示词，提升速度，删除多余LOG日志

  - Merge remote-tracking branch &#39;origin/fix/memory_reflection&#39; into fix/memory_reflection

Signed-off-by: aliyun8644380055 <accounts_68c0f5d519f260d93ee2997e@mail.teambition.com>
Reviewed-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
Merged-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/37
 2025-12-24 06:59:22 +00:00
Mark
63d5047d21 [fix] end stream output 2025-12-24 12:37:50 +08:00
朱文辉
9124a54b0f Merge #42 into develop from feature/20251219_myh 
fix(db): fix database connection handling

* feature/20251219_myh: (3 commits)
  fix(db): fix database connection handling
  fix(db): fix database connection handling
  fix(db): fix database connection handling

Signed-off-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Merged-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/42
 2025-12-24 12:24:37 +08:00
mengyonghao
1253bedcde fix(db): fix database connection handling 2025-12-24 12:23:16 +08:00
mengyonghao
0a8c1be084 fix(db): fix database connection handling 2025-12-24 12:22:59 +08:00
朱文辉
0c3486248f Merge #41 into develop from feature/20251219_myh 
feat(workflow): implement a workflow node for knowledge base retrieval

* feature/20251219_myh: (3 commits)
  feat(workflow): support multi-variable assignment in assigner node
  feat(workflow): implement a workflow node for knowledge base retrieval
  fix(template): remove default initial model in templates

Signed-off-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Merged-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/41
 2025-12-24 12:21:14 +08:00
mengyonghao
38220006a6 fix(db): fix database connection handling 2025-12-24 12:21:12 +08:00
mengyonghao
8c4d31e4d5 feat(workflow): implement a workflow node for knowledge base retrieval 2025-12-24 12:10:52 +08:00
lixiangcheng1
879b3da7ef [fix] mineru parser 2025-12-24 11:13:03 +08:00
Ke Sun
7e28ec0f22 Refactor MCP server initialization and enhance Docker compatibility 
- Simplified FastMCP initialization by removing unnecessary allowed_hosts parameter.
- Added logging for MCP server startup details.
- Implemented DNS rebinding protection configuration to support Docker container hostnames.
 2025-12-24 11:12:45 +08:00
Ke Sun
1f6abb2925 fix(docker-compose): update image names and restore container name usage for MCP server URL 2025-12-24 10:39:13 +08:00
Ke Sun
b515e76efb refactor(memory): reorganize imports and move MemoryClientFactory to utils 
- Move MemoryClientFactory from app.core.memory.client_factory to app.core.memory.utils.llm.llm_utils
- Update all evaluation modules to import MemoryClientFactory from new location (locomo, longmemeval, memsciqa)
- Move GenerateCacheRequest from memory_storage_service to memory_storage_schema
- Update memory_storage_controller imports to reflect schema reorganization
- Add analytics_user_summary import to memory_storage_controller from user_memory_service
- Consolidate utility imports across evaluation test files for consistency
- Improve code organization by centralizing LLM utilities in dedicated utils module
 2025-12-23 18:27:15 +08:00
mengyonghao
d423e80ddb feat(workflow): support multi-variable assignment in assigner node 2025-12-23 17:45:37 +08:00
Ke Sun
48f6fe04a1 Merge remote-tracking branch 'origin/develop' into refactor/memory-config-management 2025-12-23 17:30:09 +08:00
Ke Sun
283c64a358 refactor(memory): restructure memory system and improve configuration management 
- Remove deprecated main.py entry point from memory module
- Reorganize imports across controllers and services for consistency
- Update emotion controller to pass db session instead of config_id to services
- Enhance memory agent controller with db session parameter for status_type and user_profile endpoints
- Refactor memory agent service to accept db parameter in classify_message_type method
- Improve configuration handling in celery_app by removing automatic database reload
- Update all memory-related services to use centralized config management
- Standardize import ordering and remove unused imports across 50+ files
- Add pilot_run_service for new pilot execution workflow
- Refactor extraction engine, reflection engine, and search services for better modularity
- Update LLM utilities and embedder configuration for improved flexibility
- Enhance type classifier and verification tools with better error handling
- Improve memory evaluation modules (LOCOMO, LongMemEval, MemSciQA) with consistent patterns
 2025-12-23 17:17:04 +08:00
mengyonghao
28e88c2d4c fix(workflow): fix incorrect list append logic in assigner node 2025-12-23 16:57:59 +08:00
mengyonghao
0ad5d1b662 fix(workflow): fix incorrect list extend logic in assigner node 2025-12-23 16:57:59 +08:00
mengyonghao
6b2c69ebf4 fix(workflow): fix incorrect list append/pop logic in assigner node 2025-12-23 16:57:59 +08:00
mengyonghao
054a5976f5 feat(workflow): add assigner node and fix circular imports with minor code style cleanup 2025-12-23 16:57:59 +08:00
mengyonghao
75ee591202 style(workflow): remove unnecessary indentation 2025-12-23 16:57:15 +08:00
Mark
714a7d7bcd Merge branch 'develop' of codeup.aliyun.com:redbearai/python/redbear-mem-open into develop 2025-12-23 16:38:32 +08:00
Mark
47c4f93014 [fix] end node bug 2025-12-23 16:38:25 +08:00