- Enhanced graph_routes.py and query_routes.py to support multi-tenant architecture by introducing tenant-specific RAG instances.
- Updated create_graph_routes and create_query_routes functions to accept rag_manager for tenant management.
- Added get_tenant_rag dependency to all relevant endpoints to ensure tenant context is utilized for operations.
- Modified Vite configuration to include comprehensive API proxy rules for seamless interaction with backend services.
- Implemented cascade delete functionality in tenant_service.py for tenant and knowledge base deletions.
- Added detailed logging and error handling for tenant operations.
- Created audit logs documenting the multi-tenant implementation process and decisions made.
• Check content hash before insertion
• Return duplicated status if exists
• Use sanitized text for hash computation
• Apply to both single and batch inserts
• Prevent duplicate content processing
(cherry picked from commit 19c16bc464)
Added comprehensive documentation for the new include_chunk_content parameter
that enables retrieval of actual chunk text content in API responses.
Documentation Updates:
- Added "Include Chunk Content in References" section to API README
- Explained use cases: RAG evaluation, debugging, citations, transparency
- Provided JSON request/response examples
- Clarified parameter interaction with include_references
OpenAPI/Swagger Examples:
- Added "Response with chunk content" example to /query endpoint
- Shows complete reference structure with content field
- Demonstrates realistic chunk text content
This makes the feature discoverable through:
1. API documentation (README.md)
2. Interactive Swagger UI (http://localhost:9621/docs)
3. Code examples for developers
(cherry picked from commit 963ad4c637)
- Fix final_namespace error in get_namespace_data()
- Fix get_workspace_from_request return type
- Add workspace param to pipeline status calls
(cherry picked from commit 52c812b9a0)
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
(cherry picked from commit eb52ec94d7)
- Add --docling CLI flag for easier setup
- Add numpy version constraints
- Exclude docling on macOS (fork-safety)
(cherry picked from commit a24d8181c2)
