gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
919 Commits 2 Branches 0 Tags
22e9f1cd8919b18c528dff9977eee7c6bd9f4fe7
Commit Graph

919 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
✨Data Intelligence Lab@HKU✨
22e9f1cd89 Update README.md 2025-01-06 23:21:02 +08:00
✨Data Intelligence Lab@HKU✨
e415f88bd4 Update README.md 2025-01-06 23:20:26 +08:00
zrguo
39a366a3dc Update __init__.py 2025-01-06 15:43:05 +08:00
zrguo
916380e511 Update README.md 2025-01-06 15:39:44 +08:00
zrguo
e2a4819af9 Update README.md 2025-01-06 15:37:37 +08:00
zrguo
c88bb4fd53 Update LICENSE 2025-01-06 15:34:50 +08:00
zrguo
990b684a85 Update lightrag.py 2025-01-06 15:27:31 +08:00
zrguo
12f4a45440 Merge pull request #545 from ShanGor/main 
Enhance the llm_cache_kv_store, enable the llm_cache for entity extraction and revise readme
 2025-01-06 15:24:34 +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
zrguo
6b5f4755e7 Merge pull request #539 from ShanGor/main 
Added PostgreSQL implementation
 2025-01-04 22:13:06 +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
zrguo
fb414582c7 Merge pull request #541 from ParisNeo/main 
Add Optional API Key Authentication to FastAPI Services
 2025-01-04 13:58:43 +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
db663114a9 Remove unused import 2025-01-03 21:20:47 +08:00
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
zrguo
f52982d5cf Merge pull request #533 from JasonnnW3000/main 
Update LICENSE, fix copyright license year
 2025-01-01 22:53:45 +08:00
Samuel Chan
b17cb2aa95 With a draft for progres_impl 2025-01-01 22:43:59 +08:00
JasonnnW3000
7e7230a6e3 Update LICENSE, fix license year 
Signed-off-by: JasonnnW3000 <sufssl04@gmail.com>
 2025-01-01 00:20:46 -05:00
zrguo
bb2ea3db6a Merge pull request #532 from HKUDS/dev 
Dev
 2024-12-31 17:34:00 +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
zrguo
c0eef702ee Merge pull request #527 from ChenZiHong-Gavin/retry-config 
fix: change exception type
 2024-12-31 02:46:12 +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
zrguo
af893a1951 Merge pull request #529 from magicyuan876/main 
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
 2024-12-31 00:46:27 +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
zrguo
889d056a6f Merge pull request #525 from magicyuan876/main 
feat: 增强知识图谱关系的时序性支持
 2024-12-29 20:13:26 +08:00
Magic_yuan
b84c4d1fca Merge branch 'HKUDS:main' into main 2024-12-29 15:45:34 +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
zrguo
4ddf87ffd4 Merge pull request #524 from magicyuan876/main 
优化mix查询模式的提示词
 2024-12-29 10:00:31 +08:00
Magic_yuan
b8b371f65a Merge branch 'HKUDS:main' into main 2024-12-29 00:35:19 +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
zrguo
aad3b6fdc3 Merge pull request #523 from magicyuan876/main 
feat(lightrag): Implement mix search mode combining knowledge graph a…
 2024-12-28 20:08:39 +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
zrguo
8a0b59ca56 Merge pull request #521 from magicyuan876/main 
功能(lightrag): 添加文档状态跟踪和断点续传支持
 2024-12-28 00:40:34 +08:00
Magic_yuan
e6b2f68e7c docs(readme): Add batch size configuration documentation 
文档(readme): 添加批处理大小配置说明

- Add documentation for insert_batch_size parameter in addon_params
- 在 addon_params 中添加 insert_batch_size 参数的文档说明

- Explain default batch size value and its usage
- 说明默认批处理大小值及其用途

- Add example configuration for batch processing
- 添加批处理配置的示例
 2024-12-28 00:16:53 +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