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 |
|
Luca Congiu
|
b0c98531b0
|
Refactor keyword extraction handling in async wrapper for OpenAI completion
|
2024-12-23 17:11:30 +01:00 |
|
zrguo
|
45cea6e9ff
|
Merge pull request #505 from alllexx88/arcadedb_gremlin_graph
GremlinStorage: support more Gremlin compatible DBs
|
2024-12-24 00:03:34 +08:00 |
|
Luca Congiu
|
de190603c3
|
Update Azure OpenAI deployment instructions in README_AZURE_OPENAI.md for improved clarity and variable usage
|
2024-12-23 16:19:24 +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
|
07d20f4520
|
Add deployment instructions for Azure OpenAI setup in README
|
2024-12-23 16:12:31 +01:00 |
|
Luca Congiu
|
58e74d5fb2
|
Added Azure OpenAI api sample with streaming
|
2024-12-23 14:34:34 +01:00 |
|
zrguo
|
bfacfb975e
|
Merge pull request #502 from ParisNeo/main
Add LoLLMs Integration to LightRAG
|
2024-12-22 23:07:39 +08:00 |
|
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 |
|
zrguo
|
4e6f3bb91c
|
Merge pull request #494 from alllexx88/gremlin_graph
Add Gremlin graph storage
|
2024-12-20 18:25:47 +08:00 |
|
Alex Potapenko
|
016d9f572d
|
GremlinStorage: fix linting error, use asyncio.gather in get_node_edges()
|
2024-12-20 09:57:35 +01:00 |
|
zrguo
|
e5dc186e2f
|
Merge pull request #482 from ParisNeo/main
Added ollama and openai Fastapi api services
|
2024-12-20 10:37:39 +08:00 |
|
Alex Potapenko
|
6f71293c83
|
Add Gremlin graph storage
|
2024-12-19 17:47:42 +01:00 |
|
Saifeddine ALOUI
|
bbba07e1b9
|
Merge branch 'main' of https://github.com/ParisNeo/LightRAG
|
2024-12-19 11:44:03 +01:00 |
|
Saifeddine ALOUI
|
fe6ebfa995
|
Fixed linting
|
2024-12-19 11:44:01 +01:00 |
|
zrguo
|
a19ffbaea7
|
Merge pull request #483 from Weaxs/main
support TiDBGraphStorage
|
2024-12-19 16:42:50 +08:00 |
|
Saifeddine ALOUI
|
5df5754c92
|
Merge branch 'HKUDS:main' into main
|
2024-12-18 10:34:30 +01:00 |
|
Weaxs
|
344d8f277b
|
support TiDBGraphStorage
|
2024-12-18 10:57:33 +08:00 |
|
Saifeddine ALOUI
|
81ba55df7b
|
Added openai api
|
2024-12-18 01:58:19 +01:00 |
|
Saifeddine ALOUI
|
2266399da6
|
working server
|
2024-12-18 01:37:16 +01:00 |
|
Saifeddine ALOUI
|
59edc324af
|
upgraded
|
2024-12-18 00:46:47 +01:00 |
|
Saifeddine ALOUI
|
8a85b30aed
|
upgraded
|
2024-12-18 00:40:33 +01:00 |
|
Saifeddine ALOUI
|
a6ae0f5d44
|
updated requirements
|
2024-12-18 00:04:52 +01:00 |
|
Saifeddine ALOUI
|
ce3d7df6eb
|
fix
|
2024-12-17 23:51:49 +01:00 |
|
Saifeddine ALOUI
|
3d721e3db8
|
updated
|
2024-12-17 23:36:30 +01:00 |
|
zrguo
|
874f3b392b
|
Merge pull request #479 from theClassLight/GG/pr
fix(llm): hashing_kv初始化修复
|
2024-12-17 17:38:19 +08:00 |
|
zrguo
|
86ef375fad
|
Merge branch 'main' into GG/pr
|
2024-12-17 17:38:11 +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 |
|
zrguo
|
c840a053ac
|
Merge pull request #477 from theClassLight/GG/pr
refactor(lightrag): 优化hashing_kv初始化逻辑
|
2024-12-17 15:09:26 +08:00 |
|
GG
|
9893e93dd1
|
refactor(lightrag): 优化hashing_kv初始化逻辑
- 修改了 llm_model_func 和 query 方法中的hashing_kv初始化逻辑
- 当 self.llm_response_cache 不存在或没有 global_config 属性时,会创建一个新的hashing_kv实例
- 所有基于hashing_kv获取global_config属性的对象可以正常运行
|
2024-12-17 13:45:39 +08:00 |
|
Saifeddine ALOUI
|
b9c75dc2cd
|
Merge branch 'main' of https://github.com/ParisNeo/LightRAG
|
2024-12-16 21:49:51 +01:00 |
|
Saifeddine ALOUI
|
c67ec3a740
|
updazted
|
2024-12-16 21:49:50 +01:00 |
|
Saifeddine ALOUI
|
c0f4d13240
|
Update README.md
|
2024-12-16 20:59:55 +01:00 |
|
Saifeddine ALOUI
|
9a41912b88
|
Update README.md
|
2024-12-16 20:54:24 +01:00 |
|