gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,071 Commits 2 Branches 0 Tags
b020f5fe2b9a17c9d8896d56620df2aa654d2c64
Commit Graph

1313 Commits

Author SHA1 Message Date
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
Luca Congiu
725d5af215 Refactor code formatting and update requirements for improved clarity and consistency 2024-12-24 09:56:33 +01:00
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
Luca Congiu
58e74d5fb2 Added Azure OpenAI api sample with streaming 2024-12-23 14:34:34 +01:00
Saifeddine ALOUI
469fa9f574 Added lollms integration with lightrag 
Removed a depricated function from ollamaserver
 2024-12-22 00:38:38 +01:00
zrguo
4042783a55 Update __init__.py 2024-12-20 18:26:53 +08:00
Alex Potapenko
016d9f572d GremlinStorage: fix linting error, use asyncio.gather in get_node_edges() 2024-12-20 09:57:35 +01:00
Alex Potapenko
6f71293c83 Add Gremlin graph storage 2024-12-19 17:47:42 +01:00
Weaxs
344d8f277b support TiDBGraphStorage 2024-12-18 10:57:33 +08:00
GG
2d048b5eb0 fix(llm): hashing_kv初始化修复 
-hybrid模式对hashing_kv的依赖不止global_config，干脆复用llm_response_cache的初始化结构
 2024-12-17 16:44:42 +08:00
Alex Potapenko
a44aceab1e AGEStorage: fix has_node() and has_edge() 2024-12-14 13:37:34 +01:00
Alex Potapenko
25d6939ca3 AGEStorage: all queries as multiline strings for consistency 2024-12-14 12:49:39 +01:00
Alex Potapenko
05c73bcfd1 AGEStorage: fix debug logging, and some cosmetics 2024-12-14 12:47:29 +01:00
Alex Potapenko
eb2e6d0d87 AGEStorage: fix has_edge(): AGE always returns field names in lower case 2024-12-14 12:24:45 +01:00
Alex Potapenko
7564841450 Add Apache AGE graph storage 2024-12-13 20:41:38 +01:00
LarFii
b7a2d336e6 Update __version__ 2024-12-13 20:15:49 +08:00
zrguo
9cac3b0ed7 Merge pull request #462 from JasonGuoo/main 
Supporting Zhipu AI API
 2024-12-13 20:09:11 +08:00
Jason Guo
e64cf5068f Fix import 2024-12-13 19:57:25 +08:00
billvsme
a788c78197 keep tqdm_async work 2024-12-13 16:48:22 +08:00
Jason Guo
6a0e9c6c77 Modify the chat_complete method to support keywords extraction. 2024-12-13 16:18:33 +08:00
billvsme
cf0278ca43 The asyncio.as_completed() function does not guarantee that the results are ordered 2024-12-13 15:42:41 +08:00
zrguo
b7552f35aa Merge pull request #461 from tjyiiuan/main 
fix: update operate.py
 2024-12-13 15:10:53 +08:00
Jiyu Tian
aac26b086e fix: update operate.py 
1. 避免变量在赋值之前就被引用
2. 解决未找到entity返回None导致的unpack问题
 2024-12-12 15:47:57 -05:00
chenzihong
e9107a67c3 fix: fix variable name(entitiy->entity) 2024-12-12 23:59:40 +08:00
Weaxs
288985eab4 pre-commit fix tidb 2024-12-12 10:22:31 +08:00
Weaxs
8ef5a6b8cd support TiDB: add TiDBKVStorage, TiDBVectorDBStorage 2024-12-11 16:23:50 +08:00
zrguo
504a3c233b Merge branch 'main' into pkaushal/vectordb-chroma 2024-12-11 14:21:36 +08:00
zrguo
7fbd9aa3e0 Merge pull request #444 from davidleon/fix/lazy_import 
Fix/lazy import
 2024-12-11 14:19:48 +08:00
Magic_yuan
9a2afc9484 style(lightrag): 调整代码格式 2024-12-11 14:06:55 +08:00
Magic_yuan
b89041b5b3 feat(operate): 添加实体类型配置并优化提示生成 
- 在全局配置中添加 entity_types 参数，用于自定义实体类型
- 在生成实体提取和关系提取的提示时，使用配置的实体类型替代默认值
- 优化了提示生成逻辑，提高了代码的可配置性和灵活性
 2024-12-11 13:53:05 +08:00
Magic_yuan
a09e1ba190 refactor(prompt): 优化提示模板以提高相似度评估的准确性- 明确了相似度评分的评判标准，包括不同情况下的评分依据 
- 简化了评分流程，要求直接返回数字
- 期望通过这些改动提高评估的准确性和一致性
 2024-12-11 12:57:58 +08:00
Magic_yuan
0a41cc8a9a feat(llm, prompt):增加日志输出并扩展实体类型 
- 在 llm.py 中添加了日志输出，用于调试和记录 LLM 查询输入
- 在 prompt.py 中增加了 "category" 实体类型，扩展了实体提取的范围
 2024-12-11 12:45:10 +08:00