yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-07-13 20:10:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,250 Commits 4 Branches 40 Tags
Commit Graph

58 Commits

Author SHA1 Message Date
cuikunyu
135a40d696 Optimize: Use python-docx for better parsing. 2025-04-11 03:10:20 +00:00
yangdx
bd2c528dba Merge branch 'optimize-config-management' into clear-doc 2025-04-04 19:46:45 +08:00
yangdx
b0f0f1ff84 refactor: improve document clearing status management 
- Use update() for atomic status updates
- Improve history messages clearing while preserving list object
 2025-04-01 14:03:45 +08:00
yangdx
cd94e84267 Update clear cache endpoint path 2025-04-01 10:36:28 +08:00
yangdx
d54bda8d36 feat(api): Add Pydantic models for all endpoints in document_routes.py 2025-03-31 23:53:14 +08:00
yangdx
8845779ed7 Add clear cache API endpoint 2025-03-31 23:37:03 +08:00
yangdx
95a8ee27ed Fix linting 2025-03-31 23:22:27 +08:00
yangdx
04967b33cc feat(api): Add dedicated ClearDocumentsResponse class for document deletion endpoint 2025-03-31 19:13:27 +08:00
yangdx
bbc770d1ed feat(api): enhance document clearing error handling and status reporting 
- Change pipeline busy status from "error" to "busy"
- Improve error handling documentation
 2025-03-31 13:01:52 +08:00
Milin
4dbd5e3899 Merge branch 'main' into optimize-config-management 
# Conflicts:
#	env.example
#	lightrag/api/utils_api.py
 2025-03-31 11:29:29 +08:00
Milin
088fc19318 feat(config): Refactor configuration management 
- Optimize JWT Auth module to load configuration via `global_args`.
- Decouple configuration-related code from `utils_api.py`, and add a new `config.py` file for unified configuration management.
- Adjust configuration import in `lightrag_server.py`, `auth.py`, and `document_routes.py` to be introduced through `global_args`.
 2025-03-31 11:19:47 +08:00
yangdx
949a3904a9 feat(api): Enhance document clearing functionality 
- Use storage drop methods to properly clean up all data
- Add file deletion from input directory
- Add pipeline status checking and locking mechanism
- Improve error handling with detailed logging and pipeline message tracking
 2025-03-30 16:30:41 +08:00
yangdx
adb4ca9294 Fix linting 2025-03-28 16:49:35 +08:00
yangdx
35d4503677 Feat: add duplicate file check 2025-03-28 16:48:46 +08:00
yangdx
d456269718 feat: Add file name display in WebUI 
Backend:
- Add file_path field to DocStatusResponse
- Update document status response creation

Frontend:
- Remove metadata column
- Improve filename display with truncation and tooltips
- Add show/hide filename toggle with proper styling
- Update translations for all supported languages"
 2025-03-25 22:42:46 +08:00
yangdx
35df22cf08 Update pipeline_enqueue_file to include file_paths parameter 2025-03-25 20:47:25 +08:00
yangdx
d05cf286f4 Fix linting 2025-03-24 14:30:17 +08:00
yangdx
9e3994419e Refactor authentication logic and Swagger UI config 
- Consolidate authentication dependencies
- Improve Swagger UI security parameters
 2025-03-24 14:29:36 +08:00
yangdx
79bf26dfeb Process update flags status for proper boolean conversion 
- Convert MutableBoolean to regular boolean values
- Handle both multiprocess and single process cases
 2025-03-24 12:49:39 +08:00
yangdx
77ab26e5bf Fix linting 2025-03-24 05:39:50 +08:00
yangdx
071302d10f Moved update status logic to document routes. 
- Removed update status from health check endpoint
- Added update_status field to PipelineStatusResponse
 2025-03-24 05:37:03 +08:00
yangdx
90ef55960d Refactor authentication and whitelist handling 
- Combined auth and API key dependencies
- Optimized whitelist path matching
- Added optional API key to OllamaAPI
 2025-03-24 05:23:40 +08:00
yangdx
7e8a2c0e9b Added temperature parameter for LLM 2025-03-24 02:02:34 +08:00
yangdx
53396e4d82 Fixlinting 2025-03-21 16:56:47 +08:00
yangdx
0761af19c6 Files are now processed in batches in auto scan 2025-03-21 13:41:37 +08:00
yangdx
168232803b Optimized the document processing pipeline 
- Enqueue all files to pipeline before starting process when scanning input folder
- Changed parallel enqueue to sequential to prevent CPU overload by heavy file extraction jobs
 2025-03-21 13:08:57 +08:00
yangdx
73440e3a96 Fix linting 2025-03-12 16:28:55 +08:00
yangdx
16e06100e7 Add PipelineStatusResponse model for API endpoint 2025-03-12 16:16:39 +08:00
Saifeddine ALOUI
53cfb72db4 linted 2025-03-08 23:07:51 +01:00
zrguo
c67e6aceca
Merge branch 'main' into main 2025-03-09 00:23:06 +08:00
Milin
c015296081 refactor(api): Fix issues reported by pre-commit 
- Modified code layout and formatting in multiple files, improving code readability.
  - Updated import statements, removing unused libraries.
  - Simplified the writing of some functions and exception handling.
 2025-03-06 14:23:52 +08:00
Saifeddine ALOUI
00f3c6c6dd Upgraded document loading engine 2025-03-06 01:11:48 +01:00
Saifeddine ALOUI
6e4daea056
Linting 2025-03-05 15:36:47 +01:00
Saifeddine ALOUI
aaa8194423
Update document_routes.py 2025-03-05 15:32:39 +01:00
Milin
852634e20e
Merge branch 'main' into feat_login-jwt 2025-03-05 12:42:40 +08:00
Milin
63aa4f9dfc feat(api): Add user authentication functionality 
- Implement JWT-based user authentication logic
- Add login endpoint and token validation middleware
- Update API routes with authentication dependencies
- Add authentication-related environment variables
- Optimize requirements.txt with necessary dependencies
 2025-03-05 11:09:31 +08:00
zrguo
9d56b1c8a4
Merge pull request #976 from danielaskdd/validate-content-before-enqueue 
Improved file handling and validation for document processing
 2025-03-04 13:26:54 +08:00
yangdx
61839f311a Fix package name checks for docx and pptx modules. 
- Added type ignore for package checks
- Corrected docx pptx package name for new version
 2025-03-04 10:00:07 +08:00
yangdx
aa5888042e Improved file handling and validation for document processing 
• Enhanced UTF-8 validation for text files
• Added content validation checks
• Better handling of binary data
• Added logging for ignored document IDs
• Improved document ID filtering
 2025-03-02 23:57:57 +08:00
yangdx
d704512139 Refactor shared storage module to improve async handling and naming consistency 
• Add async support for get_namespace_data
• Rename get_update_flags to get_update_flag
• Rename set_update_flag to set_all_update_flags
• Update docstrings for clarity
• Fix typos in log messages
 2025-03-01 05:01:26 +08:00
yangdx
c973498c34 Fix linting 2025-02-28 21:35:04 +08:00
yangdx
157ec862ae Enhance logging system with file rotation and unified configuration 
• Unify logging across Gunicorn and Uvicorn
• Add rotating file handlers
 2025-02-28 14:57:25 +08:00
yangdx
8cd45161f2 feat: add history_messages to track pipeline processing progress 
• Add shared history_messages list
• Track pipeline progress with messages
 2025-02-28 13:53:40 +08:00
yangdx
04bd5413c9 Add API endpoint to retrieve document indexing pipeline status 
• GET /pipeline_status endpoint added
• Returns current pipeline processing state
 2025-02-28 12:21:50 +08:00
yangdx
b4bcd76599 Remove useless scan progress tracking functionality and related code 2025-02-28 10:53:36 +08:00
yangdx
db2a902fcb Rename get_scan_lock to get_storage_lock 2025-02-28 00:34:33 +08:00
yangdx
92ecb0da97 Refactor document scanning progress share variable initialization 2025-02-27 16:07:00 +08:00
yangdx
7436c06f6c Fix linting 2025-02-26 18:11:16 +08:00
yangdx
4eb069d1d6 Initialize scan_progress with default values if not already set 2025-02-26 17:42:49 +08:00
yangdx
2752a764ae Refactor storage implementations to support both single and multi-process modes 
• Add shared storage management module
• Support process/thread lock based on mode
 2025-02-26 05:38:38 +08:00