gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
886 Commits 2 Branches 0 Tags
648645ef455d3bbccb36a1e6ecb12dd3d779b3fe
Commit Graph

886 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
zrguo
65e0e675cc Merge pull request #443 from magicyuan876/main 
fix(lightrag): 修复只有实体没有关系的chunk处理逻辑
 2024-12-11 14:14:59 +08:00
Magic_yuan
b63c6155ee style(lightrag): 调整ReadMe,加入自定义实体类型参数配置示例 2024-12-11 14:10:27 +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
Pankaj Kaushal
ca788463cc feat: Add ChromaDB integration for vector storage 
- Implemented `ChromaVectorDBStorage` class in `lightrag/kg/chroma_impl.py` to support ChromaDB as a vector storage backend.
- Updated `lightrag.py` to include `ChromaVectorDBStorage` in the storage class mapping.
- Added a test script `test_chromadb.py` to demonstrate the usage of ChromaDB with LightRAG, including configuration for embedding functions and ChromaDB connection settings.
- fix lazy import function to support package context for dynamic class loading.
  288d4b8355
 2024-12-10 16:23:05 +01:00
david
288d4b8355 fix lazy import 2024-12-10 17:16:21 +08:00
Magic_yuan
316c4df949 更新日志描述 2024-12-10 14:15:43 +08:00
Magic_yuan
58c0f94346 fix(lightrag): 修复只有实体没有关系的chunk处理逻辑 
- 只有实体没有关系时，继续处理，而不是直接return
- 当只有实体而没有关系的图片在高阶查询关系时会返回空，这里优化返回，当没有关系时降级为local查询
 2024-12-10 14:13:11 +08:00
david
21a3992e39 fix extra keyword_extraction. 2024-12-10 09:52:27 +08:00
david
f6eeedb050 add concurrent embedding limit 2024-12-10 09:01:21 +08:00
david
d0a4ef252e fix: rare embedding issue. 2024-12-10 09:00:22 +08:00
zrguo
11d8440393 Merge pull request #436 from eltociear/patch-1 
chore: update llm.py
 2024-12-09 22:24:13 +08:00
Ikko Eltociear Ashimine
b8cddb6c72 chore: update llm.py 
intialize -> initialize
 2024-12-09 22:08:06 +09:00
zrguo
e5cc43ad3c Merge pull request #434 from magicyuan876/main 
提取关键词的prompt优化
 2024-12-09 20:55:27 +08:00
zrguo
6282abcb42 Merge pull request #435 from davidleon/fix/unicode_escape 
fix unicode escape. for the case of "/utils" in the response.
 2024-12-09 20:54:58 +08:00
david
3210c8f5bd fix unicode_escape. 2024-12-09 19:14:27 +08:00
Magic_yuan
e7ac7daee8 Merge branch 'HKUDS:main' into main 2024-12-09 18:17:01 +08:00
Magic_yuan
9724b59e19 提取关键词时LLM输出的关键词跟随用户提问的语言，可以避免一些指定英文而偶发的一些LLM输出的JSON不规范导致JSON解析失败的问题 2024-12-09 18:15:09 +08:00
zrguo
725284e8ba Update __version__ 2024-12-09 18:12:08 +08:00
zrguo
3e112c0d05 Merge pull request #432 from ChenZiHong-Gavin/main 
fix(lightrag): use is_closed() instead of _closed
 2024-12-09 18:08:43 +08:00
zrguo
4c89a1a620 Merge pull request #429 from davidleon/improvement/lazy_external_load 
fix extra kwargs error: keyword_extraction.
 2024-12-09 18:07:30 +08:00
zrguo
616ab39997 Merge pull request #425 from guyuecode/patch-1 
Fix: syntaxError
 2024-12-09 17:59:14 +08:00
zrguo
2dd231d8b3 Merge pull request #417 from partoneplay/main 
Add support for OpenAI Compatible Streaming output and delete unreachable code
 2024-12-09 17:56:10 +08:00
zrguo
7b0f3ffcda Merge branch 'main' into main 2024-12-09 17:55:56 +08:00
zrguo
113a7f4a71 Merge pull request #430 from zhenya-zhu/ollama-api-service-demo 
Add a ollama API service demo
 2024-12-09 17:47:37 +08:00
Larfii
2ba20910bb fix naive_query 2024-12-09 17:45:01 +08:00
zrguo
e083854d47 Merge pull request #415 from SaujanyaV/fix-entity-name-string 
Fix: Ensure entity_or_relation_name is a string in _handle_entity_relation_summary
 2024-12-09 17:36:06 +08:00
zrguo
71af34196f Merge branch 'main' into fix-entity-name-string 2024-12-09 17:30:40 +08:00
chenzihong
25d8430a60 Merge branch 'HKUDS:main' into main 2024-12-09 17:10:42 +08:00
chenzihong
9dd51f1f35 fix(lightrag): use is_closed() instead of _closed 2024-12-09 17:10:13 +08:00
I561043
a2f3de25f8 fix format 2024-12-09 17:06:52 +08:00
Larfii
ffa95e0461 Fix jina embedding 2024-12-09 17:05:17 +08:00
zrguo
91843267e9 Merge pull request #428 from magicyuan876/main 
修复bug https://github.com/HKUDS/LightRAG/issues/306
 2024-12-09 16:52:36 +08:00
I561043
9fef519caf add demo for ollama api service 2024-12-09 15:39:34 +08:00
zrguo
5d724d8197 Update README.md 2024-12-09 15:39:34 +08:00
david
9717ad87fc fix extra kwargs error: keyword_extraction. 
add lazy_external_load to reduce external lib deps whenever it's not necessary for user.
 2024-12-09 15:35:35 +08:00
Magic_yuan
865e76a083 修复bug 
https://github.com/HKUDS/LightRAG/issues/306
主要修改包括：
在存储文本块数据时增加了验证，确保只存储有效的数据
在处理文本块之前增加了空列表检查
在截断文本块之前过滤掉无效的数据
增加了更多的日志警告信息
查询的修改：
添加了对 chunks 的有效性检查,过滤掉无效的 chunks:
 2024-12-09 15:08:30 +08:00
guyue
f223527e24 Fix syntaxError 
Double quote error
 2024-12-09 14:07:36 +08:00
partoneplay
a7fcb653e3 Merge remote-tracking branch 'origin/main' and fix syntax 2024-12-09 12:36:55 +08:00
Larfii
d8edc915e7 Move jina demo 2024-12-09 11:19:57 +08:00
zrguo
77bcf1bea4 Merge pull request #424 from kaushikacharya/interactive_graph 
Interactive Graph: Mouse hover nodes and edges displays description in pop-up window
 2024-12-09 10:21:45 +08:00
zrguo
0a8d88212a Merge pull request #423 from davidleon/feature/jina_embedding 
add jina embedding
 2024-12-09 10:18:50 +08:00
zrguo
2644a295aa Merge pull request #421 from magicyuan876/main 
优化embedding相似度缓存机制，增加 LLM 相似性检查功能并优化缓存机制
 2024-12-09 10:18:12 +08:00
Kaushik Acharya
aca80fe981 Interactive Graph: Mouse hover nodes and edges displays description in pop-up window 2024-12-08 21:46:33 +05:30
david
97d1894077 add jina embedding 2024-12-08 22:20:41 +08:00
Magic_yuan
779ed604d8 清理多余注释 2024-12-08 17:38:49 +08:00
Magic_yuan
39c2cb11f3 清理多余注释 2024-12-08 17:37:58 +08:00
Magic_yuan
ccf44dc334 feat(cache): 增加 LLM 相似性检查功能并优化缓存机制 
- 在 embedding 缓存配置中添加 use_llm_check 参数
- 实现 LLM 相似性检查逻辑，作为缓存命中的二次验证- 优化 naive 模式的缓存处理流程
- 调整缓存数据结构，移除不必要的 model 字段
 2024-12-08 17:35:52 +08:00