yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-10-31 09:49:54 +00:00
Code Issues Packages Projects Releases Wiki Activity
767 Commits 5 Branches 71 Tags
Commit Graph

59 Commits

Author SHA1 Message Date
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
chenzihong
9dd51f1f35 fix(lightrag): use is_closed() instead of _closed 2024-12-09 17:10:13 +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
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
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
partoneplay
d8ba7c57f3 Add MongoDB as KV storage 2024-12-05 13:57:43 +08:00
zrguo
6d274019dd Merge pull request #393 from partoneplay/main 
Add Milvus as vector storage
 2024-12-05 12:05:30 +08:00
partoneplay
052322b213 Add Milvus as vector storage 2024-12-05 08:48:41 +08:00
LarFii
44d441a951 update insert custom kg 2024-12-04 19:44:04 +08:00
zrguo
6927b57520 Merge pull request #378 from doosenn/main 
fix neo4jstorage bug
 2024-12-04 11:11:19 +08:00
magicyuan876
607d4f9555 修改日志文件路径 
- 因为LightRAG的几乎都是导入的utils中的全局logger对象，当多个rag实例的时候并无法完全把日志记录到对应的working_dir,并且应用中删除working_dir时会由于logger的句柄无法删除
- 此修改简化了日志文件的路径，不再依赖于 working_dir 属性，日志文件独立于working_dir
 2024-12-04 08:44:13 +08:00
zuoluo
801619084f fix neo4jstorage bug 2024-12-03 16:04:58 +08:00
Tasha Upchurch
eae310cd68 fix for #209 
function was returning a closed event loop.
 2024-11-29 13:27:08 -07:00
jin
9f3c0581ac Merge branch 'HKUDS:main' into main 2024-11-27 15:16:28 +08:00
Larfii
cb492ccb04 Add custom KG insertion 2024-11-25 18:06:19 +08:00
Larfii
8562ecdebc Add a progress bar 2024-11-25 15:04:38 +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
LarFii
ce7f524174 Update 2024-11-19 16:52:26 +08:00
Richard
6bdf693b85 fix neo4j bug 2024-11-15 13:11:43 +08:00
Rick Battle
d4a27c901e Only update storage if there was something to insert 
Before, the `finally` block would always call `_insert_done()`, which writes out the `vdb_*` and `kv_store_*` files ... even if there was nothing to insert (because all docs had already been inserted).  This was causing the speed of skippable inserts to become very slow as the graph grew.
 2024-11-12 09:30:21 -07:00
jin
41599897fb fix pre commit 2024-11-12 13:32:40 +08:00
jin
8bc5d4efff add Oracle support 2024-11-12 09:59:12 +08:00
LarFii
b49f73181c update 2024-11-11 17:54:22 +08:00
LarFii
4c0352ee2b Add delete method 2024-11-11 17:48:40 +08:00
jin
0b6b0064d6 Merge branch 'main' of https://github.com/jin38324/LightRAG 2024-11-11 15:21:37 +08:00
LarFii
d0c1844264 Linting 2024-11-11 10:45:22 +08:00
jin
d68fc3d248 support Oracle DB 2024-11-08 16:20:34 +08:00
jin
5e9d19d5a3 support Oracle Database storage 2024-11-08 16:12:58 +08:00
jin
594470ab56 Oracle Database support 
Add oracle 23ai database as the KV/vector/graph storage
 2024-11-08 14:58:41 +08:00
zrguo
9463d588fa Merge branch 'main' into main 2024-11-07 14:54:15 +08:00
Ken Wiltshire
3d5d083f42 fix event loop conflict 2024-11-06 11:18:14 -05:00
Ken Wiltshire
8420cd1c77 event loop issue 2024-11-06 10:49:14 -05:00
benx13
6f77f54c6d bug fix issue #95 2024-11-05 18:36:59 -08:00
Ken Wiltshire
8bd5d9b5b2 using neo4j async 2024-11-02 18:35:07 -04:00
wiltshirek
f40725feeb Merge branch 'main' into main 2024-11-01 16:50:45 -04:00
Ken Wiltshire
f375620992 cleaning code for pull 2024-11-01 16:11:19 -04:00
Ken Wiltshire
b41d990fd6 securing for production with env vars for creds 2024-11-01 11:01:50 -04:00
Ken Wiltshire
e966a14418 set kg by start param, defaults to networkx 2024-11-01 08:47:52 -04:00
Ken Wiltshire
e4509327dd index to neo4j working and tested. check queires next. 2024-10-30 17:48:14 -04:00
Ken Wiltshire
9ab7312ecc edge degree next almost done 2024-10-29 15:36:07 -04:00
Andrii Lazarchuk
84b60e4aa6 Fix lint issue 2024-10-28 17:05:38 +02:00
Andrii Lazarchuk
0e71a906af Merge branch 'main' into before-sync-28-10-2024 2024-10-28 15:54:43 +02:00
Ken Wiltshire
01b7df7afa inference running locally. use neo4j next 2024-10-27 15:37:41 -04:00
zhenjie.ye
883d6b7cc7 Refactor code formatting in lightrag_api_openai_compatible_demo.py 2024-10-26 16:12:10 +08:00
Yazington
eec29d041a fixing bug 2024-10-26 00:11:21 -04:00
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
LarFii
92c11179fe ollama test 2024-10-16 15:15:10 +08:00