yangdx
01288debd1
Ensure splash output flush to system log
2025-01-27 02:45:44 +08:00
yangdx
f045fc3d59
Update API endpoint documentation
2025-01-26 11:36:24 +08:00
yangdx
f8d26cb193
Update default history turns to 3
2025-01-26 05:19:51 +08:00
yangdx
25a58a6545
Fix linting
2025-01-26 05:10:57 +08:00
yangdx
9f80c1904f
Refactoring command line argurements handling logic, add more RAG config to splash screen
2025-01-26 05:09:42 +08:00
yangdx
e4e42a8ec4
Fetch chunk size and chunk overlap size from .env file
2025-01-26 02:31:16 +08:00
yangdx
2719e07107
Convert OllamaMessage to dict in conversation history
2025-01-25 22:33:09 +08:00
yangdx
fb9df50ada
Add conversation history support to chat API
...
- Added HISTORY_TURNS env variable
- Updated chat request data creation
- Modified server to handle history
- Added history to test cases
2025-01-25 22:14:40 +08:00
yangdx
cf2f83377c
fix linting
2025-01-25 16:57:47 +08:00
yangdx
66dcc551ef
Fix LLM binding variable name in create_app function
...
Corrected variable name from llm_binding_host
Updated conditional checks for LLM bindings
2025-01-25 16:29:59 +08:00
Saifeddine ALOUI
06c9e4e454
Fixed missing imports bug and fixed linting
2025-01-25 00:55:07 +01:00
Saifeddine ALOUI
e060fa6abb
Now we can show the files in the health
2025-01-25 00:49:09 +01:00
Saifeddine ALOUI
c81da5a6d7
Fixed startup scan
2025-01-25 00:17:22 +01:00
Saifeddine ALOUI
34018cb1e0
Separated llms from the main llm.py file and fixed some deprication bugs
2025-01-25 00:11:00 +01:00
Saifeddine ALOUI
1776c1afcd
fixed linting
2025-01-24 21:01:34 +01:00
zrguo
91422b0eb6
Merge pull request #644 from danielaskdd/Add-Ollama-generate-API-support
...
Add ollama generate api support
2025-01-25 01:52:59 +08:00
zrguo
13e4fa2e4a
Merge pull request #640 from ParisNeo/main
...
Upgraded docstrings for lightrag-server.py And added a simple front end to interact with the AI
2025-01-25 01:49:18 +08:00
Saifeddine ALOUI
cc3cd0b6dd
Moved splash screen to the end
2025-01-24 17:22:41 +01:00
Saifeddine ALOUI
7b42601ab8
Update lightrag_server.py
2025-01-24 17:14:15 +01:00
Saifeddine ALOUI
f30831dc9d
Update lightrag_server.py
2025-01-24 17:04:02 +01:00
yangdx
f30a69e201
Fix linting, remove redundant commentsr and clean up code for better readability
2025-01-24 23:50:47 +08:00
yangdx
11873625a3
Fix regex pattern for chat history detection
...
- Updated regex to match newline characters
- Added re.MULTILINE flag for multiline matching
- Improved logging for regex match results
- Enhanced query content cleaning process
- Ensured consistent chat history detection
2025-01-24 23:39:33 +08:00
yangdx
930b6cf006
Directly pass the session title or keyword generation request from Open WebUI to the underlying LLM
2025-01-24 23:33:12 +08:00
Saifeddine ALOUI
6e1f9ff00a
Update lightrag_server.py
2025-01-24 13:55:50 +01:00
Saifeddine ALOUI
a0c91d41b9
Fixed serving the webui
2025-01-24 13:54:49 +01:00
Saifeddine ALOUI
d9140a65e9
Merge pull request #1 from ParisNeo/patch-1
...
Patch 1
2025-01-24 13:52:54 +01:00
Saifeddine ALOUI
dfd7f74921
Added serving a web ui
...
Serving webui
2025-01-24 13:50:06 +01:00
Saifeddine ALOUI
c22e35f5d9
Merge branch 'HKUDS:main' into main
2025-01-24 13:38:20 +01:00
Saifeddine ALOUI
8171235f35
Added docstrings to lightrag_server.py
...
Added docstrings to lightrag_server.py
2025-01-24 13:37:43 +01:00
yangdx
385661b10e
Removed query mode parsing and related tests
...
- Removed query mode parsing logic
- Removed test_generate_query_modes
- Simplified generate endpoint
- Updated test cases list
- Cleaned up unused code
2025-01-24 19:25:45 +08:00
yangdx
2c8885792c
Refactor /api/generate：use llm_model_func directly
2025-01-24 18:39:43 +08:00
yangdx
b94cae9990
draft implementation of /api/generate endpoint
2025-01-24 18:18:14 +08:00
hyb
7b02fac7b9
feat: New ini file reading database configuration method for production environment convenience, modified Lightrag ainsert method - add.doc_keys retrieval method to only filter existing ones, but this will prevent failed documents from being stored again. Added -- chunk_Size and -- chunkoverlapped size for production environment convenience, and added llm_binding: openai-ollama for easy use of openai while also using ollama embedding
2025-01-24 17:10:19 +08:00
zrguo
afb30fe6c1
Merge branch 'main' into redis_impl
2025-01-24 16:27:40 +08:00
黄渝斌
3ea2ecbcbf
Merge branch 'main' into redis_impl
2025-01-23 23:02:53 +08:00
hyb
ff71952c8c
feat: 新增ini文件读取数据库配置方式，方便生产环境，修改Lightrag ainsert方法_add_doc_keys获取方式，原来只过滤存在的，但这会让失败的文档无法再次存储，新增--chunk_size和--chunk_overlap_size方便生产环境，新增llm_binding：openai-ollama 方便用openai的同时使用ollama embedding
2025-01-23 22:58:57 +08:00
Soichi Sumi
a3306c4633
add "azure_openai" in llm_binding and embedding_binding
2025-01-23 21:30:57 +09:00
yangdx
11b618d434
Fix parameters missing in app creation in case openai is selected
2025-01-23 01:15:48 +08:00
yangdx
8a05ff459f
Add environment variable for Ollama model tag
2025-01-21 03:13:13 +08:00
yangdx
81a0a7cff0
fixed linting
2025-01-21 01:03:37 +08:00
yangdx
2e62cf1c66
Add document indexing during FastAPI startup, Fix docx package name in requirements
...
- Initialize DocumentManager earlier
- Add lifespan context manager
- Scan and index documents on startup
- Fix docx package name in requirements
2025-01-21 00:50:11 +08:00
yangdx
a76abf23f2
Updated OpenAI configuration and documentation.
...
- Added OpenAI alike example in .env.example
- Updated README for OpenAI alike server
- Modified API key handling in lightrag_server.py
2025-01-20 14:50:06 +08:00
Saifeddine ALOUI
70425b0357
fixed linting
2025-01-20 00:26:28 +01:00
Saifeddine ALOUI
9cae05e1ff
Fixed a bug introduced by a modification by someone else in azure_openai_complete (please make sure you test before commiting code)
...
Added api_key to lollms, ollama, openai for both llm and embedding bindings allowing to use api key protected services.
2025-01-19 23:24:37 +01:00
Saifeddine ALOUI
34c051b0b9
Merge branch 'HKUDS:main' into main
2025-01-19 10:40:21 +01:00
yangdx
a78be2ab17
pre-commit run --all-files
2025-01-19 08:07:26 +08:00
yangdx
853a9d2064
Updated API version to 1.0.3
...
- Bumped API version to 1.0.3
- Fixed version reference in server code
2025-01-19 06:06:17 +08:00
yangdx
387be31f09
Refactor embedding function initialization and remove start-server.sh
...
- Simplified RAG initialization logic by deduplicating embedding function
- Removed start-server.sh script which is not needed
- No functional changes to the application
2025-01-19 05:19:02 +08:00
yangdx
8ea179a98b
Migrate Ollama API to lightrag_server.py
2025-01-19 04:44:30 +08:00
Saifeddine ALOUI
35f04b51e6
Update lightrag_server.py
2025-01-17 11:18:45 +01:00
