yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-07-18 14:31:53 +00:00
Code Issues Packages Projects Releases Wiki Activity
375 Commits 3 Branches 43 Tags
Commit Graph

60 Commits

Author SHA1 Message Date
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
magicyuan876
4da7dd1865 移除kwargs中的hashing_kv参数取为变量 2024-12-06 15:35:09 +08:00
magicyuan876
efdd4b8b8e 移除kwargs中的hashing_kv参数取为变量 2024-12-06 15:23:18 +08:00
magicyuan876
8d9fc01b4c 解决冲突 2024-12-06 15:09:50 +08:00
magicyuan876
8924d2b8fc Merge remote-tracking branch 'origin/main' 
# Conflicts:
#	lightrag/llm.py
#	lightrag/operate.py
 2024-12-06 15:06:00 +08:00
magicyuan876
e619b09c8a 重构缓存处理逻辑 
- 提取通用缓存处理逻辑到新函数 handle_cache 和 save_to_cache
- 使用 CacheData 类统一缓存数据结构
- 优化嵌入式缓存和常规缓存的处理流程
- 添加模式参数以支持不同查询模式的缓存策略
- 重构 get_best_cached_response 函数，提高缓存查询效率
 2024-12-06 14:29:16 +08:00
zrguo
f2a208c343 Merge branch 'main' into main 2024-12-06 11:38:27 +08:00
magicyuan876
5dfb74ef2d 修复 args_hash在使用常规缓存时候才计算导致embedding缓存时没有计算的bug 2024-12-06 10:40:48 +08:00
magicyuan876
6c29a37f20 修复 args_hash在使用常规缓存时候才计算导致embedding缓存时没有计算的bug 2024-12-06 10:28:35 +08:00
magicyuan876
6540d11096 修复 args_hash在使用常规缓存时候才计算导致embedding缓存时没有计算的bug 2024-12-06 10:21:53 +08:00
partoneplay
e82d13e182 Add support for Ollama streaming output and integrate Open-WebUI as the chat UI demo 2024-12-06 10:13:16 +08:00
magicyuan876
d48c6e4588 feat(lightrag): 添加 查询时使用embedding缓存功能 
- 在 LightRAG 类中添加 embedding_cache_config配置项
- 实现基于 embedding 相似度的缓存查询和存储
- 添加量化和反量化函数，用于压缩 embedding 数据
- 新增示例演示 embedding 缓存的使用
 2024-12-06 08:17:20 +08:00
Larfii
a2072a055a fix: unexpected keyword argument error 2024-12-05 11:47:56 +08:00
LarFii
44d441a951 update insert custom kg 2024-12-04 19:44:04 +08:00
zrguo
3e69b326ec Merge pull request #383 from MRX760/main 
added nvidia text-embedding API and example of using nvidia API llm a…
 2024-12-04 11:21:46 +08:00
MRX760
5f13ce1ce9 added nvidia text-embedding API and example of using nvidia API llm and text-embedding 2024-12-03 17:15:10 +07:00
partoneplay
bc2b8c592e embedding deprecated in favor of embed 2024-12-03 08:42:36 +08:00
zrguo
e8b5498699 Merge pull request #360 from ahmadhatahet/azure_openai_embedding 
Azure OpenAI Embedding
 2024-12-02 16:02:13 +08:00
Ahmad Hatahet
f281414308 add api_version to azure_openai_complete_if_cache 2024-11-30 17:47:33 +01:00
Ahmad Hatahet
23cabbe7a3 update max_token_size according to openai doc 2024-11-30 17:16:07 +01:00
Ahmad Hatahet
7fea7d7b5e add api_version to args 2024-11-30 17:11:38 +01:00
b10902118
0ab55da47a fix error and tested 2024-11-30 00:00:51 +08:00
b10902118
753c1e6714 support JSON output for ollama and openai 2024-11-29 21:41:37 +08:00
jin
7cd06159e0 add LightRAG init parameters in readme 
also fix some error
 2024-11-26 10:19:28 +08:00
jin
26ae240c65 Logic Optimization 2024-11-25 13:40:38 +08:00
jin
1dbe803521 Merge branch 'main' of https://github.com/jin38324/LightRAG 2024-11-25 13:32:33 +08:00
jin
89c2de54a2 Optimization logic 2024-11-25 13:29:55 +08:00
david
3ac8010c3f fix hf embedding to support loading to different device 2024-11-13 14:20:36 +08:00
Ken Wiltshire
3d5d083f42 fix event loop conflict 2024-11-06 11:18:14 -05:00
Ken Wiltshire
8bd5d9b5b2 using neo4j async 2024-11-02 18:35:07 -04:00
Andrii Lazarchuk
0e71a906af Merge branch 'main' into before-sync-28-10-2024 2024-10-28 15:54:43 +02:00
tackhwa
2cf3a85a0f update do_preprocess 2024-10-26 16:24:35 +08:00
tackhwa
8deb30aa20 support lmdeploy backend 2024-10-26 16:11:15 +08:00
zrguo
a7811ad18c Merge pull request #138 from tackhwa/main 
[FIX] fix hf output bug (current output contain user prompt which cause logical error in entity extraction phase)
 2024-10-26 14:10:14 +08:00
tackhwa
87f8b7dba1 Update token length 2024-10-26 02:42:40 +08:00
tackhwa
226f6f3d87 fix hf output bug 2024-10-26 02:20:23 +08:00
Sanketh Kumar
a157e8e0a2 Manually reformatted files 2024-10-25 13:32:25 +05:30
tackhwa
f96ffad62f move_code 2024-10-23 15:25:46 +08:00
tackhwa
dfec83de1d fix hf bug 2024-10-23 15:02:28 +08:00
zrguo
5822e7012f Merge pull request #87 from Soumil32/main 
Added a class to use multiple models
 2024-10-23 11:12:44 +08:00
zrguo
28dc8cf1d8 Merge branch 'main' into main 2024-10-23 11:08:40 +08:00
tpoisonooo
1ef973c7fc feat(examples): support siliconcloud free API 2024-10-22 15:16:57 +08:00
Abyl Ikhsanov
1dd927eb9d Update llm.py 2024-10-21 20:40:49 +02:00
Soumil
e5ab24bad4 added a class to use multiple models 2024-10-21 18:34:43 +01:00
Andrii Lazarchuk
25a2dd41c1 Add ability to passadditional parameters to ollama library like host and timeout 2024-10-21 11:55:46 +00:00
Sanketh Kumar
32464fab4e chore: added pre-commit-hooks and ruff formatting for commit-hooks 2024-10-19 09:43:17 +05:30
João Galego
37d713a5c8 Fixed retry strategy, message history and inference params; Cleaned up Bedrock example 2024-10-18 16:50:02 +01:00
João Galego
1fc55b18d5 Added support for Amazon Bedrock models 2024-10-18 14:17:14 +01:00
LarFii
92c11179fe ollama test 2024-10-16 15:15:10 +08:00
Sung Kim
eeded24b42 Added OpenAI compatible options and examples 2024-10-15 12:55:05 -07:00