gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
5928 commits 5 branches 72 tags 705 MiB
Commit graph

375 commits

Author SHA1 Message Date
yangdx
8e50eef58b Merge branch 'main' into cohere-rerank 2025-12-02 22:19:37 +08:00
yangdx
ea8d55ab42 Add documentation for embedding provider configuration rules 2025-11-28 17:49:30 +08:00
yangdx
4ab4a7ac94 Allow embedding models to use provider defaults when unspecified 
- Set EMBEDDING_MODEL default to None
- Pass model param only when provided
- Let providers use their own defaults
- Fix lollms embed function params
- Add ollama embed_model default param
 2025-11-28 16:57:33 +08:00
yangdx
56e0365cf0 Add configurable model parameter to jina_embed function 
- Add model parameter to jina_embed
- Pass model from API server
- Default to jina-embeddings-v4
- Update function documentation
- Make model selection flexible
 2025-11-28 15:38:29 +08:00
palanisd
a898f0548d
Merge branch 'HKUDS:main' into cohere-rerank 2025-11-25 14:21:43 -05:00
yangdx
48b67d3077 Handle missing WebUI assets gracefully without blocking server startup 
- Change build check from error to warning
- Redirect to /docs when WebUI unavailable
- Add webui_available to health endpoint
- Only mount /webui if assets exist
- Return status tuple from build check
 2025-11-25 02:51:55 +08:00
netbrah
a05bbf105e Add Cohere reranker config, chunking, and tests 2025-11-22 16:43:13 -05:00
yangdx
e22ac52ebc Auto-initialize pipeline status in LightRAG.initialize_storages() 
• Remove manual initialize_pipeline_status calls
• Auto-init in initialize_storages method
• Update error messages for clarity
• Warn on workspace conflicts
 2025-11-17 12:54:33 +08:00
yangdx
52c812b9a0 Fix workspace isolation for pipeline status across all operations 
- Fix final_namespace error in get_namespace_data()
- Fix get_workspace_from_request return type
- Add workspace param to pipeline status calls
 2025-11-17 12:54:33 +08:00
yangdx
926960e957 Refactor workspace handling to use default workspace and namespace locks 
- Remove DB-specific workspace configs
- Add default workspace auto-setting
- Replace global locks with namespace locks
- Simplify pipeline status management
- Remove redundant graph DB locking
 2025-11-17 12:54:33 +08:00
yangdx
e5addf4d94 Improve embedding config priority and add debug logging 
• Fix embedding_dim priority logic
• Add final config logging
 2025-11-17 12:54:32 +08:00
yangdx
6b2af2b579 Refactor embedding function creation with proper attribute inheritance 
- Extract max_token_size from providers
- Avoid double-wrapping EmbeddingFunc
- Improve configuration priority logic
- Add comprehensive debug logging
- Return complete EmbeddingFunc instance
 2025-11-17 12:54:32 +08:00
yangdx
14a6c24ed7 Add configurable embedding token limit with validation 
- Add EMBEDDING_TOKEN_LIMIT env var
- Set max_token_size on embedding func
- Add token limit property to LightRAG
- Validate summary length vs limit
- Log warning when limit exceeded
 2025-11-17 12:54:32 +08:00
yangdx
7b7f93d77c Implement lazy configuration initialization for API server 
• Add lazy config initialization
• Maintain backward compatibility
• Support programmatic usage
• Add gunicorn dependency
• Explicit config in entry points
 2025-11-17 12:54:32 +08:00
BukeLy
18a4870229 fix: Add default workspace support for backward compatibility 
Fixes two compatibility issues in workspace isolation:

1. Problem: lightrag_server.py calls initialize_pipeline_status()
   without workspace parameter, causing pipeline to initialize in
   global namespace instead of rag's workspace.

   Solution: Add set_default_workspace() mechanism in shared_storage.
   LightRAG.initialize_storages() now sets default workspace, which
   initialize_pipeline_status() uses when called without parameters.

2. Problem: /health endpoint hardcoded to use "pipeline_status",
   cannot return workspace-specific status or support frontend
   workspace selection.

   Solution: Add LIGHTRAG-WORKSPACE header support. Endpoint now
   extracts workspace from header or falls back to server default,
   returning correct workspace-specific pipeline status.

Changes:
- lightrag/kg/shared_storage.py: Add set/get_default_workspace()
- lightrag/lightrag.py: Call set_default_workspace() in initialize_storages()
- lightrag/api/lightrag_server.py: Add get_workspace_from_request() helper,
  update /health endpoint to support LIGHTRAG-WORKSPACE header

Testing:
- Backward compatibility: Old code works without modification
- Multi-instance safety: Explicit workspace passing preserved
- /health endpoint: Supports both default and header-specified workspaces

Related: #2353
 2025-11-17 12:54:20 +08:00
yangdx
a624a9508a Add Gemini to APIs requiring embedding dimension parameter 2025-11-08 03:54:50 +08:00
yangdx
de4ed73652 Add Gemini embedding support 
- Implement gemini_embed function
- Add gemini to embedding binding choices
- Add L2 normalization for dims < 3072
 2025-11-08 03:34:30 +08:00
yangdx
0b2a15c452 Centralize embedding_send_dim config through args instead of env var 2025-11-08 01:52:23 +08:00
yangdx
03cc6262c4 Prohibit direct access to internal functions of EmbeddingFunc. 
• Fix similarity search error in query stage
• Remove redundant null checks
• Improve log readability
 2025-11-08 01:43:36 +08:00
yangdx
d95efcb9ad Fix linting 2025-11-07 21:27:54 +08:00
yangdx
ce28f30ca6 Add embedding_dim parameter support to embedding functions 
• Pass embedding_dim to jina_embed call
• Pass embedding_dim to openai_embed call
 2025-11-07 21:23:59 +08:00
yangdx
c14f25b7f8 Add mandatory dimension parameter handling for Jina API compliance 2025-11-07 21:08:34 +08:00
yangdx
d8a6355e41 Merge branch 'main' into apply-dim-to-embedding-call 2025-11-07 20:48:22 +08:00
yangdx
33a1482f7f Add optional embedding dimension parameter control via env var 
* Add EMBEDDING_SEND_DIM environment variable
* Update Jina/OpenAI embed functions
* Add send_dimensions to EmbeddingFunc
* Auto-inject embedding_dim when enabled
* Add parameter validation warnings
 2025-11-07 20:46:40 +08:00
yangdx
fc40a36968 Add timeout support to Gemini LLM and improve parameter handling 
• Add timeout parameter to Gemini client
• Convert timeout seconds to milliseconds
• Update function signatures consistently
• Add Gemini thinking config example
• Clean up parameter documentation
 2025-11-07 15:50:14 +08:00
yangdx
6e36ff41e1 Fix linting 2025-11-06 16:01:24 +08:00
yangdx
5f49cee20f Merge branch 'main' into VOXWAVE-FOUNDRY/main 2025-11-06 15:37:35 +08:00
yangdx
7ccc1fdd27 Add frontend rebuild warning indicator to version display 
- Return bool from check_frontend_build()
- Add ⚠️ symbol to outdated versions
- Show tooltip with rebuild message
- Add translations for warning text
- Fix tailwind config filename typo
 2025-10-31 06:09:46 +08:00
yangdx
d5bcd14c6f Refactor service deployment to use direct process execution 
- Remove bash wrapper script
- Update systemd service configuration
- Improve process management for gunicorn
- Simplify shared storage cleanup logic
- Update documentation for deployment
 2025-10-29 18:55:47 +08:00
yangdx
6489aaa7f0 Remove worker_exit hook and improve cleanup logging 
• Remove unreliable worker_exit function
• Add debug logs for cleanup modes
• Move DEBUG_LOCKS to top of file
 2025-10-29 15:15:13 +08:00
yangdx
4a46d39c93 Replace GUNICORN_CMD_ARGS with custom LIGHTRAG_GUNICORN_MODE flag 
• Use custom env var for mode detection
• Improve Gunicorn mode reliability
 2025-10-29 14:06:03 +08:00
yangdx
816feefd84 Fix cleanup coordination between Gunicorn and UvicornWorker lifecycles 
• Document UvicornWorker hook limitations
• Add GUNICORN_CMD_ARGS cleanup guard
• Prevent double cleanup in workers
 2025-10-29 13:53:46 +08:00
yangdx
72b29659c9 Fix worker process cleanup to prevent shared resource conflicts 
• Add worker_exit hook in gunicorn config
• Add shutdown_manager parameter in finalize_share_data of share_storage
• Prevent Manager shutdown in workers
• Remove custom signal handlers
 2025-10-29 13:33:21 +08:00
yangdx
88d12beae2 Add offline Swagger UI support with custom static file serving 
- Disable default docs URL
- Add custom /docs endpoint
- Mount static Swagger UI files
- Include OAuth2 redirect handler
- Support offline documentation access
 2025-10-28 02:23:08 +08:00
Humphry
0b3d31507e extended to use gemini, sswitched to use gemini-flash-latest 2025-10-20 13:17:16 +03:00
yangdx
012aaada22 Update Swagger API key status description text 2025-10-18 09:40:44 +08:00
yangdx
46ac5dac53 Improve API description formatting and add ReDoc link 2025-10-17 16:24:01 +08:00
yangdx
f45dce347a Fix cache control error of index.html 
• Retrun no-cache for all HTML responses not just .html files
• Prevent force browser refresh action after front-end rebuild
 2025-10-17 12:43:04 +08:00
yangdx
64900b5457 Add frontend source code update warning 
- Add frontend freshness check logic
- Warn when rebuild needed
- Remove --production from install docs
 2025-10-14 10:59:21 +08:00
yangdx
a8bbce3ae7 Use frozen lockfile for consistent frontend builds 2025-10-14 03:34:55 +08:00
yangdx
ee45ab5104 Move frontend build check from setup.py to runtime server startup 
• Remove complex setup.py build checks
• Add runtime frontend validation
• Update install docs with uv/bun steps
• Simplify setup.py to minimal form
• Check webui before server starts
 2025-10-14 02:21:26 +08:00
yangdx
5eb4a4b799 feat: simplify citations, add reference merging, and restructure API response format 2025-09-24 14:30:10 +08:00
yangdx
6b953fa53d Remove auto-scan-at-startup feature and related documentation 
• Remove --auto-scan-at-startup arg
• Delete auto scan docs sections
• Remove startup scanning logic
 2025-09-23 16:24:53 +08:00
yangdx
a1df76a4ea Optimize LLM/embedding config caching to reduce repeated parsing overhead 
• Add LLMConfigCache class for smart caching
• Pre-process OpenAI/Ollama configurations
• Create optimized function factories
• Reduce redundant option parsing calls
 2025-09-05 16:36:08 +08:00
yangdx
ae09b5c656 refactor: eliminate conditional imports and simplify LightRAG initialization 
- Remove conditional import block, replace with lazy loading factory functions
- Add create_llm_model_func() and create_llm_model_kwargs() for clean configuration
- Update wrapper functions with lazy imports for better performance
- Unify LightRAG initialization, eliminating duplicate conditional branches
- Reduce code complexity by 33% while maintaining full backward compatibility
 2025-08-31 00:18:29 +08:00
yangdx
332202c111 Fix lambda closure bug in embedding function configuration 
• Replace lambda with proper async function
• Capture config values at creation time
• Avoid closure variable reference issues
• Add factory function for embeddings
• Remove test file for closure bug
 2025-08-30 23:43:34 +08:00
avchauzov
414d47d12a fix(server): Resolve lambda closure bug in embedding_func 
Fixes #2023. Resolves an issue where the embedding function would incorrectly fall back to the OpenAI provider if the server's configuration arguments were mutated after initialization. This was caused by a lambda function capturing a reference to the mutable 'args' object instead of capturing the configuration values at creation time.
 2025-08-30 14:43:33 +02:00
yangdx
925e631a9a refac: Add robust time out handling for LLM request 2025-08-29 13:50:35 +08:00
yangdx
ff0a18e08c Unify SUMMARY_LANGUANGE and ENTITY_TYPES implementation method 2025-08-27 12:23:22 +08:00
Thibo Rosemplatt
c3aabfc251 Merge branch 'main' into entityTypesServerSupport 2025-08-26 21:48:20 +02:00