Commit Graph

897 Commits

Author SHA1 Message Date
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
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
zrguo
9c4853d007 Merge pull request #514 from ParisNeo/main
Streamlined API Installation and Documentation Enhancement
2024-12-27 15:39:52 +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
zrguo
fffd00d514 Update graph_visual_with_neo4j.py 2024-12-26 14:55:22 +08:00
zrguo
edfa39d72d Merge pull request #507 from ParisNeo/main
API Installation Options and Documentation Improvements
2024-12-26 09:09:42 +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
Luca Congiu
725d5af215 Refactor code formatting and update requirements for improved clarity and consistency 2024-12-24 09:56:33 +01:00