Commit Graph

252 Commits

Author SHA1 Message Date
yangdx
5c7b2d7c9f Merge from main 2025-01-29 22:13:01 +08:00
yangdx
c8b890547a Add logging for query parameters in NanoVectorDBStorage.query 2025-01-29 21:36:31 +08:00
yangdx
7aedc08caf Add RAG configuration options and enhance parameter configurability
- Add top-k and cosine-threshold parms for api server
- Update .env and cli parms handling with new parameters
- Improve splash screen display
- Update bash and storage classes to read new parameters from .env file.
2025-01-29 21:34:34 +08:00
yangdx
d0052456d4 Fix cosine threshold parameter setting error 2025-01-29 21:09:11 +08:00
ranfysvalle02
4c349c208d +MDB KG 2025-01-29 07:31:34 -05:00
zrguo
80451af839 fix linting errors 2025-01-27 23:21:34 +08:00
Saifeddine ALOUI
56e9c9f4d5 Moved the storages to kg folder 2025-01-27 09:59:26 +01:00
Saifeddine ALOUI
52037205eb Update tidb_impl.py 2025-01-27 09:40:50 +01:00
Saifeddine ALOUI
b2c1144219 Update redis_impl.py 2025-01-27 09:39:58 +01:00
Saifeddine ALOUI
b6068046ff Update postgres_impl.py 2025-01-27 09:39:39 +01:00
Saifeddine ALOUI
57682389e2 Update postgres_impl_test.py 2025-01-27 09:38:32 +01:00
Saifeddine ALOUI
c7c56863b1 Update postgres_impl.py 2025-01-27 09:36:53 +01:00
Saifeddine ALOUI
ecadb71556 Update oracle_impl.py 2025-01-27 09:36:34 +01:00
Saifeddine ALOUI
3fdeeff8ba Update neo4j_impl.py 2025-01-27 09:36:10 +01:00
Saifeddine ALOUI
7a5d058a57 Update mongo_impl.py 2025-01-27 09:35:50 +01:00
Saifeddine ALOUI
9390abb49b Update milvus_impl.py 2025-01-27 09:35:26 +01:00
Saifeddine ALOUI
af245eb73e Update age_impl.py 2025-01-27 09:35:08 +01:00
Saifeddine ALOUI
f307ed43f5 fixed linting 2025-01-27 02:10:24 +01:00
Saifeddine ALOUI
a68aebb124 translated docstrings to english and enhanced the webui 2025-01-27 02:07:06 +01:00
hyb
cd5b1dc98f fix: light_server.py fix 2025-01-26 09:13:11 +08:00
hyb
3dba406644 feat: Added webui management, including file upload, text upload, Q&A query, graph database management (can view tags, view knowledge graph based on tags), system status (whether it is good, data storage status, model status, path),request /webui/index.html 2025-01-25 18:38:46 +08:00
Saifeddine ALOUI
06c9e4e454 Fixed missing imports bug and fixed linting 2025-01-25 00:55:07 +01:00
Saifeddine ALOUI
34018cb1e0 Separated llms from the main llm.py file and fixed some deprication bugs 2025-01-25 00:11:00 +01:00
Lukas Selch
c75ef82b66 Fixed workspace matching in oracle_impl.py
In the query for "node_degree", there was a typo that did not match the workspace of the edges, but only of the nodes.
2025-01-24 15:57:31 +01:00
hyb
e08905b398 feat: 增加redis KV存储,增加openai+neo4j+milvus+redis的demo测试,新增lightrag.py: RedisKVStorage,新增requirements.txt:aioredis依赖 2025-01-22 16:42:13 +08:00
zrguo
b84aab5cd0 Merge pull request #590 from jin38324/main
Enhance Robustness of insert Method with Pipeline Processing and Caching Mechanisms
2025-01-16 14:20:08 +08:00
jin
6ae8647285 support pipeline mode 2025-01-16 12:58:15 +08:00
jin
d5ae6669ea support pipeline mode 2025-01-16 12:52:37 +08:00
jin
17a2ec2bc4 Merge branch 'HKUDS:main' into main 2025-01-16 09:59:27 +08:00
Samuel Chan
2b7d253117 Merge remote-tracking branch 'origin/main' 2025-01-15 12:09:05 +08:00
Samuel Chan
d91a330e9d Enrich README.md for postgres usage, make some change to cater python version<12 2025-01-15 12:02:55 +08:00
zrguo
61349b0fe7 Merge pull request #581 from jiabin2wang20230918/fix_mongo
Fix for mongoDB document 16MB limit and add os env NEO4J_MAX_CONNECTION_POOL_SIZE for neo4j
2025-01-13 18:38:22 +08:00
bingo
1984da0fd6 add logger.debug for mongo_impl get_by_mode_and_id() 2025-01-13 07:27:30 +00:00
bingo
f28b90b2b3 1. add os env NEO4J_MAX_CONNECTION_POOL_SIZE to for neo4j ;
2. fix https://github.com/HKUDS/LightRAG/issues/580 issue for mongoDB document 16MB limit.
2025-01-13 07:06:01 +00:00
Samuel Chan
c016934021 Revise the AGE implementation on get_node_edges, to align with Neo4j behavior. 2025-01-12 21:38:39 +08:00
Samuel Chan
d03d6f5fc5 Revised the postgres implementation, to use attributes(node_id) rather than nodes to identify an entity. Which significantly reduced the table counts. 2025-01-11 09:30:19 +08:00
jin
85331e3fa2 update Oracle support
add cache support, fix bug
2025-01-10 11:36:28 +08:00
Samuel Chan
85d35b16d4 Merge branch 'HKUDS:main' into main 2025-01-06 12:53:06 +08:00
Samuel Chan
6ae27d8f06 Some enhancements:
- Enable the llm_cache storage to support get_by_mode_and_id, to improve the performance for using real KV server
- Provide an option for the developers to cache the LLM response when extracting entities for a document. Solving the paint point that sometimes the process failed, the processed chunks we need to call LLM again, money and time wasted. With the new option (by default not enabled) enabling, we can cache that result, can significantly save the time and money for beginners.
2025-01-06 12:50:05 +08:00
zrguo
6d7a01f29d Merge pull request #542 from xiyihan0/main
添加选取Neo4j指定数据库功能的支持
2025-01-05 12:46:45 +08:00
xiyihan
1e3b25db22 添加选取Neo4j指定数据库功能的支持(fix lint) 2025-01-04 22:33:35 +08:00
xiyihan
bb4c271623 添加选取Neo4j指定数据库功能的支持 2025-01-04 21:47:52 +08:00
Samuel Chan
6c1b669f0f Fix the lint issue 2025-01-04 18:49:32 +08:00
Samuel Chan
e053223ef0 Fix the lint issue 2025-01-04 18:34:35 +08:00
Samuel Chan
f6f62c32a8 Fix the bug of AGE processing 2025-01-03 21:10:06 +08:00
Samuel Chan
b17cb2aa95 With a draft for progres_impl 2025-01-01 22:43:59 +08:00
Magic_yuan
650b8e38b7 feat(lightrag): Add document status tracking and checkpoint support
功能(lightrag): 添加文档状态跟踪和断点续传支持

- Add DocStatus enum and DocProcessingStatus class for document processing state management
- 添加 DocStatus 枚举和 DocProcessingStatus 类用于文档处理状态管理

- Implement JsonDocStatusStorage for persistent status storage
- 实现 JsonDocStatusStorage 用于持久化状态存储

- Add document-level deduplication in batch processing
- 在批处理中添加文档级别的去重功能

- Add checkpoint support in ainsert method for resumable document processing
- 在 ainsert 方法中添加断点续传支持,实现可恢复的文档处理

- Add status query methods for monitoring processing progress
- 添加状态查询方法用于监控处理进度

- Update LightRAG initialization to support document status tracking
- 更新 LightRAG 初始化以支持文档状态跟踪
2024-12-28 00:11:25 +08:00
Samuel Chan
42b3690e71 Fix the async issue while running on Windows 2024-12-27 12:01:50 +08:00
Alex Potapenko
848b3f6e33 GremlinStorage: fixes and patch to support other Gremlin compatible BD. Tested on ArcadeDB with Gremlin plugin. The main change is using "entity_name" vertex property instead of the label as a node_id since different implementations have different restrictions on label names. 2024-12-23 16:16:17 +01:00
Alex Potapenko
016d9f572d GremlinStorage: fix linting error, use asyncio.gather in get_node_edges() 2024-12-20 09:57:35 +01:00