yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-08-01 21:31:54 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,166 Commits 5 Branches 46 Tags
Commit Graph

705 Commits

Author SHA1 Message Date
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
fd76e00c6a Refactor storage initialization to separate object creation from data loading 
• Split __post_init__ and initialize()
• Move data loading to initialize()
• Add FastAPI lifespan integration
 2025-03-01 03:48:19 +08:00
yangdx
b3328542c7 refactor: migrate synchronous locks to async locks for improved concurrency 
• Add UnifiedLock wrapper class
• Convert with blocks to async with
 2025-03-01 02:22:35 +08:00
yangdx
aac1bdd9e6 feat: add configurable log rotation settings via environment variables 
• Add LOG_DIR env var for log file location
• Add LOG_MAX_BYTES for max log file size
• Add LOG_BACKUP_COUNT for backup count
 2025-02-28 23:21:14 +08:00
yangdx
c973498c34 Fix linting 2025-02-28 21:35:04 +08:00
yangdx
c37b1e8aa7 Align Gunicorn configuration with Uvicorn 
- centralize config in gunicorn_config.py
- fix log level handling in Gunicorn
 2025-02-28 20:41:11 +08:00
yangdx
f588cdc5df Optimize logging config & worker handling for different server modes 
• Separate logging config for uvicorn/gunicorn
• Force workers=1 in uvicorn mode
• Add warning for worker count in uvicorn
 2025-02-28 16:50:54 +08:00
yangdx
81f6f6e343 Fix lightrag logger initailization problem, fix gunicorn acccess log missing 2025-02-28 16:07:33 +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
b090a22be7 Add concurrency check for auto scan task to prevent duplicate scans 
• Add pipeline status check before scan
• Add storage lock protection
• Add latest_message to status tracking
• Add helpful log message at startup
 2025-02-28 12:22:20 +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
64f22966a3 Fix linting 2025-02-27 19:05:51 +08:00
yangdx
92ecb0da97 Refactor document scanning progress share variable initialization 2025-02-27 16:07:00 +08:00
yangdx
03d05b094d Improve Gunicorn support and cleanup shared storage initialization 
• Move Gunicorn check before other startup
• Improve startup flow organization
 2025-02-27 14:13:42 +08:00
yangdx
7aec78833c Implement Gunicorn+Uvicorn integration for shared data preloading 
- Create run_with_gunicorn.py script to properly initialize shared data in the
  main process before forking worker processes
- Revert unvicorn to single process mode only, and let gunicorn do all the multi-process jobs
 2025-02-27 13:25:22 +08:00
yangdx
7c237920b1 Refactor shared storage to support both single and multi-process modes 
• Initialize storage based on worker count
• Remove redundant global variable checks
• Add explicit mutex initialization
• Centralize shared storage initialization
• Fix process/thread lock selection logic
 2025-02-27 08:48:33 +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
41f5d208a9 fix: shared data intitialization failed for multi-worker 2025-02-26 13:32:15 +08:00
yangdx
15a6a9cf7c fix: log filtering void when uvicorn wokers is greater than 1 
- Centralize logging setup
- Fix logger propagation issues
 2025-02-26 12:23:35 +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
ArnoChen
798c37d4fa build webui 2025-02-25 18:36:34 +08:00
ArnoChen
40a1a94a31 add graph depth and layout iteration settings 2025-02-25 18:32:53 +08:00
yangdx
7262f61b0e add redis configuration and update workers default value 2025-02-25 10:47:27 +08:00
yangdx
04fc5ce604 Remove unspported endpoint from splash mesages 2025-02-25 09:45:14 +08:00
yangdx
ddc366b672 Optimize display_splash_screen function 
- Merge System Configuration into Server Configuration section
- Add Workers parameter display after Port parameter
 2025-02-25 09:44:17 +08:00
yangdx
d74a23d2cc Add multiple workers support for API Server 2025-02-25 09:37:00 +08:00
ArnoChen
e54aa276c8 Merge remote-tracking branch 'origin/main' into dev-webui 2025-02-24 19:00:06 +08:00
ArnoChen
69b36d855b build webui 2025-02-24 18:59:31 +08:00
yangdx
2e13def95c Remove unused global_top_k variable and related configurations. 2025-02-24 18:20:39 +08:00
yangdx
facf7c11fe Reduce knowledge graph max_depth from 100 to 3 2025-02-24 03:34:44 +08:00
yangdx
f29628125b Fix typo in parameter name from 'nodel_label' to 'node_label' 2025-02-24 02:36:36 +08:00
yangdx
f5efe5977b Merge branch 'clear-text-before-insert' into simplify-cli-arguments 2025-02-23 17:06:39 +08:00
yangdx
78e0ca7835 Change defautl timeout for LLM to 150s 2025-02-23 17:03:35 +08:00
yangdx
57884f2fb8 Refine LLM settings in env sample file 2025-02-23 16:52:41 +08:00
yangdx
df95f251dc Move server ready message to lifespan 2025-02-23 16:42:31 +08:00
yangdx
dbeda8a9ff Change scanning logs from INFO to DEBUG level 2025-02-23 16:12:08 +08:00
yangdx
460bc3a6aa update README.md and .env.example 2025-02-23 13:26:38 +08:00
yangdx
637d6756b8 Optimize RAG initialization for openai-ollama 2025-02-23 11:54:36 +08:00
yangdx
d84b90bcd4 Handle special case of CLI argument openai-ollama 2025-02-22 15:27:19 +08:00
yangdx
f9780830ad Revert: get llm-binding and embedding-binding from cli 2025-02-22 10:46:54 +08:00
yangdx
2fd997ca4f Merge branch 'clear-text-before-insert' into simplify-cmdline-arguments 2025-02-22 10:07:46 +08:00
yangdx
3c866eec16 Merge branch 'refactor-api-server' into clear-text-before-insert 2025-02-22 10:04:56 +08:00
yangdx
dff07e50a4 Merge branch 'main' into refactor-api-server 2025-02-21 21:12:02 +08:00
yangdx
b144e0c3b0 Sync modifications from main branch 2025-02-21 21:07:37 +08:00
yangdx
2fdbbc2062 Reorder and improve command line argument definitions for better organization 
- Change verbose to store_true action
- Move verbose flag to logging section
- Move auto-scan flag to end of options
 2025-02-21 20:01:43 +08:00
yangdx
a848884a7b Remove unnesessary CLI arguments, reduce CLI arguments complexity 
• Move storage config from CLI
• Move LLM and embedding binding config from CLI
• Remove chunk config from CLI
 2025-02-21 19:34:17 +08:00