yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-08-04 23:01:56 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,498 Commits 4 Branches 47 Tags
Commit Graph

1644 Commits

Author SHA1 Message Date
童石渊
6b19401dc6 chunk split retry 2025-01-07 16:26:12 +08:00
童石渊
536d6f2283 添加字符分割功能，在“insert”函数中如果增加参数split_by_character，则会按照split_by_character进行字符分割，此时如果每个分割后的chunk的tokens大于max_token_size，则会继续按token_size分割（todo：考虑字符分割后过短的chunk处理） 2025-01-07 00:28:15 +08:00
xYLiuuuuuu
79646fced8
Fix:Optimized logic for automatic switching modes when keywords do not exist 2025-01-06 16:54:53 +08:00
zrguo
39a366a3dc
Update __init__.py 2025-01-06 15:43:05 +08:00
zrguo
990b684a85 Update lightrag.py 2025-01-06 15:27:31 +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
11f889a9df Merge remote-tracking branch 'origin/main' 2025-01-04 18:35:39 +08:00
Samuel Chan
e053223ef0 Fix the lint issue 2025-01-04 18:34:35 +08:00
Samuel Chan
733d329aba
Merge branch 'HKUDS:main' into main 2025-01-04 18:34:24 +08:00
Saifeddine ALOUI
b15c398889 applyed linting 2025-01-04 02:23:39 +01:00
Saifeddine ALOUI
518a8a726a Added servers protection using an API key to restrict access to only authenticated entities. 2025-01-04 02:21:37 +01:00
Samuel Chan
60e8a355f0
Merge branch 'HKUDS:main' into main 2025-01-03 21:18:17 +08:00
Samuel Chan
ebe5fe1676 Merge remote-tracking branch 'origin/main' 2025-01-03 21:14:22 +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
zrguo
d489d9dec0 fix linting errors 2024-12-31 17:32:04 +08:00
zrguo
71e9267f4b Update README.md 2024-12-31 17:25:57 +08:00
zrguo
cee5b2fbb0 add delete by doc id 2024-12-31 17:15:57 +08:00
chenzihong
648645ef45 fix: fix formatting issues 2024-12-31 01:33:14 +08:00
chenzihong
97bc42d896 Merge branch 'main' of https://github.com/ChenZiHong-Gavin/LightRAG into retry-config 2024-12-31 01:22:55 +08:00
Magic_yuan
7271ac69b7 修复断点续传bug，过滤已经存在的文档是只过滤状态是已经处理完成的 2024-12-30 20:32:10 +08:00
chenzihong
eb1fc0dae7 fix: change exception type 2024-12-30 01:46:15 +08:00
Magic_yuan
7b91dc7fd8 feat: 增强知识图谱关系的时序性支持 
- 为关系和向量数据增加时间戳支持,记录知识获取的时间
- 优化混合查询策略,同时考虑语义相关性和时间顺序
- 增强提示词模板,指导LLM在处理冲突信息时考虑时间因素
 2024-12-29 15:37:34 +08:00
Magic_yuan
4c950cf4ce feat: 增强知识图谱关系的时序性支持 
- 为关系和向量数据增加时间戳支持,记录知识获取的时间
- 优化混合查询策略,同时考虑语义相关性和时间顺序
- 增强提示词模板,指导LLM在处理冲突信息时考虑时间因素
 2024-12-29 15:25:57 +08:00
Magic_yuan
6325e290bb 优化mix模式的查询提示词，使用简洁的回答，并提供参考来源 2024-12-29 00:32:09 +08:00
Magic_yuan
aaaf617451 feat(lightrag): Implement mix search mode combining knowledge graph and vector retrieval 
- Add 'mix' mode to QueryParam for hybrid search functionality
- Implement mix_kg_vector_query to combine knowledge graph and vector search results
- Update LightRAG class to handle 'mix' mode queries
- Enhance README with examples and explanations for the new mix search mode
- Introduce new prompt structure for generating responses based on combined search results
 2024-12-28 11:56:28 +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
zrguo
c022db4355
Merge pull request #516 from ShanGor/main 
Fix the async issue while running on Windows
 2024-12-27 15:44:01 +08:00
zrguo
35e8c76f92
Merge pull request #515 from zhangch-ss/main 
fix keywords_extraction_examples format error
 2024-12-27 15:41:15 +08:00
Samuel Chan
42b3690e71 Fix the async issue while running on Windows 2024-12-27 12:01:50 +08:00
ai_user
376603826b fix keywords_extraction_examples format error 2024-12-27 03:12:55 +00:00
Saifeddine ALOUI
27a52ddf37 fixed linting 2024-12-26 23:39:10 +01:00
Saifeddine ALOUI
4d0184189f Added the option to only return context without doing a query to the AI (useful for automated systems like lollms) 2024-12-26 23:32:02 +01:00
Saifeddine ALOUI
5fcfb05e62 fixed file uploading 2024-12-26 22:48:52 +01:00
Saifeddine ALOUI
f2b52a2a38 Added azure openai lightrag server to the api install and fused documentation. 2024-12-26 21:32:56 +01:00
zrguo
457e683acd
Update lightrag.py 2024-12-26 22:14:04 +08:00
zrguo
a1493f56d6
Update utils.py 2024-12-26 22:09:46 +08:00
zrguo
1d3d4c092d
Merge pull request #513 from theClassLight/GG/pr 
fix(utils): 修复缓存未正确启用的问题
 2024-12-26 22:07:28 +08:00
GG
04293466ad fix(utils): 修复缓存未正确启用的问题 
- 在 handle_cache 函数中添加了对 global_config 中 enable_l`lm_cache 设置的检查
- 如果配置禁用了缓存，则直接返回 None
-这个修改确保了在不需要缓存的情况下，函数能够正确地跳过缓存处理
 2024-12-26 22:03:45 +08:00
zrguo
1ca3f64e7d
Update __init__.py 2024-12-26 15:13:24 +08:00
Saifeddine ALOUI
9921223281 Merge remote-tracking branch 'upstream/main' 2024-12-25 18:04:02 +01:00
zrguo
dc0d60ea58
Merge pull request #504 from congiuluc/feature-azureopenai-api 
Added Azure OpenAI api sample with streaming
 2024-12-24 19:01:46 +08:00
Saifeddine ALOUI
69b3f0b37b fixed the default lollms server port number 2024-12-24 11:33:28 +01:00
Saifeddine ALOUI
848465d5d7 precommit tested 2024-12-24 10:35:00 +01:00
Saifeddine ALOUI
9951f8584a Added API as an option to the installation, reorganized the API and fused all documentations in README.md 2024-12-24 10:31:12 +01:00