Enable a single LightRAG server instance to serve multiple isolated workspaces
via HTTP header-based routing. This allows multi-tenant SaaS deployments where
each tenant's data is completely isolated.
Key features:
- Header-based workspace routing (LIGHTRAG-WORKSPACE, X-Workspace-ID fallback)
- Process-local pool of LightRAG instances with LRU eviction
- FastAPI dependency (get_rag) for workspace resolution per request
- Full backward compatibility - existing deployments work unchanged
- Strict multi-tenant mode option (LIGHTRAG_ALLOW_DEFAULT_WORKSPACE=false)
- Configurable pool size (LIGHTRAG_MAX_WORKSPACES_IN_POOL)
- Graceful shutdown with workspace finalization
Configuration:
- LIGHTRAG_DEFAULT_WORKSPACE: Default workspace (falls back to WORKSPACE)
- LIGHTRAG_ALLOW_DEFAULT_WORKSPACE: Require explicit header when false
- LIGHTRAG_MAX_WORKSPACES_IN_POOL: Max concurrent workspace instances (default: 50)
Files:
- New: lightrag/api/workspace_manager.py (core multi-workspace module)
- New: tests/test_multi_workspace_server.py (17 unit tests)
- New: render.yaml (Render deployment blueprint)
- Modified: All route files to use get_rag dependency
- Updated: README.md, env.example with documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- 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
- Add model parameter to jina_embed
- Pass model from API server
- Default to jina-embeddings-v4
- Update function documentation
- Make model selection flexible
- 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
- 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
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
- 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
• 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
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.
