* Capture max_token_size before decorator
* Apply wrapper after capturing attribute
* Prevent decorator from stripping dataclass
* Ensure token limit is properly set
- 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
- Add Awaitable and Union type imports
- Update chunking_func type annotation
- Handle coroutine results with await
- Add return type validation
- Update docstring for async support
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
Problem:
In multi-tenant scenarios, different workspaces share a single global
pipeline_status namespace, causing pipelines from different tenants to
block each other, severely impacting concurrent processing performance.
Solution:
- Extended get_namespace_data() to recognize workspace-specific pipeline
namespaces with pattern "{workspace}:pipeline" (following GraphDB pattern)
- Added workspace parameter to initialize_pipeline_status() for per-tenant
isolated pipeline namespaces
- Updated all 7 call sites to use workspace-aware locks:
* lightrag.py: process_document_queue(), aremove_document()
* document_routes.py: background_delete_documents(), clear_documents(),
cancel_pipeline(), get_pipeline_status(), delete_documents()
Impact:
- Different workspaces can process documents concurrently without blocking
- Backward compatible: empty workspace defaults to "pipeline_status"
- Maintains fail-fast: uninitialized pipeline raises clear error
- Expected N× performance improvement for N concurrent tenants
Bug fixes:
- Fixed AttributeError by using self.workspace instead of self.global_config
- Fixed pipeline status endpoint to show workspace-specific status
- Fixed delete endpoint to check workspace-specific busy flag
Code changes: 4 files, 141 insertions(+), 28 deletions(-)
Testing: All syntax checks passed, comprehensive workspace isolation tests completed
- **API:** The `graph/entity/edit` endpoint now returns a detailed `operation_summary` for better client-side handling of update, rename, and merge outcomes.
- **Web UI:** Added an "auto-merge on rename" option. The UI now gracefully handles merge success, partial failures (update OK, merge fail), and other errors with specific user feedback.
- Pass chunk storages to merge function
- Merge relation chunk tracking data
- Merge entity chunk tracking data
- Delete old chunk tracking records
- Persist chunk storage updates
• Add delete_llm_cache parameter to API
• Collect cache IDs from text chunks
• Delete cache after graph operations
• Update UI with new checkbox option
• Add i18n translations for cache option
- Add entity_chunks & relation_chunks storage
- Implement KEEP/FIFO limit strategies
- Update env.example with new settings
- Add migration for chunk tracking data
- Support all KV storage
• Add DocStatus.PREPROCESSED enum value
• Update API routes and response models
• Add preprocessed filter in web UI
• Update localization files
• Handle preprocessed status in deletion
- Store file_path in full_docs storage
- Update PostgreSQL implementation by map file_path to doc_name
- Other storage implementation automatically handles the new field
- Add new aquery_llm/query_llm methods providing structured responses
- Consolidate /query and /query/stream endpoints to use unified aquery_llm
- Optimize cache handling by moving cache checks before LLM calls
• Add include_references param to QueryRequest
• Extend QueryResponse with references field
• Create unified QueryResult data structures
• Refactor kg_query and naive_query functions
• Update streaming to send references first
- Add enable_cot parameter to all LLM APIs
- Implement CoT for OpenAI with <think> tags
- Log warnings for unsupported providers
- Enable CoT in query operations
- Handle streaming and non-streaming CoT
