- Add --docling CLI flag for easier setup
- Add numpy version constraints
- Exclude docling on macOS (fork-safety)
(cherry picked from commit c246eff725)
- Add --docling CLI flag for easier setup
- Add numpy version constraints
- Exclude docling on macOS (fork-safety)
(cherry picked from commit a24d8181c2)
* feat: Implement multi-tenant architecture with tenant and knowledge base models
- Added data models for tenants, knowledge bases, and related configurations.
- Introduced role and permission management for users in the multi-tenant system.
- Created a service layer for managing tenants and knowledge bases, including CRUD operations.
- Developed a tenant-aware instance manager for LightRAG with caching and isolation features.
- Added a migration script to transition existing workspace-based deployments to the new multi-tenant architecture.
* chore: ignore lightrag/api/webui/assets/ directory
* chore: stop tracking lightrag/api/webui/assets (ignore in .gitignore)
* feat: Initialize LightRAG Multi-Tenant Stack with PostgreSQL
- Added README.md for project overview, setup instructions, and architecture details.
- Created docker-compose.yml to define services: PostgreSQL, Redis, LightRAG API, and Web UI.
- Introduced env.example for environment variable configuration.
- Implemented init-postgres.sql for PostgreSQL schema initialization with multi-tenant support.
- Added reproduce_issue.py for testing default tenant access via API.
* feat: Enhance TenantSelector and update related components for improved multi-tenant support
* feat: Enhance testing capabilities and update documentation
- Updated Makefile to include new test commands for various modes (compatibility, isolation, multi-tenant, security, coverage, and dry-run).
- Modified API health check endpoint in Makefile to reflect new port configuration.
- Updated QUICK_START.md and README.md to reflect changes in service URLs and ports.
- Added environment variables for testing modes in env.example.
- Introduced run_all_tests.sh script to automate testing across different modes.
- Created conftest.py for pytest configuration, including database fixtures and mock services.
- Implemented database helper functions for streamlined database operations in tests.
- Added test collection hooks to skip tests based on the current MULTITENANT_MODE.
* feat: Implement multi-tenant support with demo mode enabled by default
- Added multi-tenant configuration to the environment and Docker setup.
- Created pre-configured demo tenants (acme-corp and techstart) for testing.
- Updated API endpoints to support tenant-specific data access.
- Enhanced Makefile commands for better service management and database operations.
- Introduced user-tenant membership system with role-based access control.
- Added comprehensive documentation for multi-tenant setup and usage.
- Fixed issues with document visibility in multi-tenant environments.
- Implemented necessary database migrations for user memberships and legacy support.
* feat(audit): Add final audit report for multi-tenant implementation
- Documented overall assessment, architecture overview, test results, security findings, and recommendations.
- Included detailed findings on critical security issues and architectural concerns.
fix(security): Implement security fixes based on audit findings
- Removed global RAG fallback and enforced strict tenant context.
- Configured super-admin access and required user authentication for tenant access.
- Cleared localStorage on logout and improved error handling in WebUI.
chore(logs): Create task logs for audit and security fixes implementation
- Documented actions, decisions, and next steps for both audit and security fixes.
- Summarized test results and remaining recommendations.
chore(scripts): Enhance development stack management scripts
- Added scripts for cleaning, starting, and stopping the development stack.
- Improved output messages and ensured graceful shutdown of services.
feat(starter): Initialize PostgreSQL with AGE extension support
- Created initialization scripts for PostgreSQL extensions including uuid-ossp, vector, and AGE.
- Ensured successful installation and verification of extensions.
* feat: Implement auto-select for first tenant and KB on initial load in WebUI
- Removed WEBUI_INITIAL_STATE_FIX.md as the issue is resolved.
- Added useTenantInitialization hook to automatically select the first available tenant and KB on app load.
- Integrated the new hook into the Root component of the WebUI.
- Updated RetrievalTesting component to ensure a KB is selected before allowing user interaction.
- Created end-to-end tests for multi-tenant isolation and real service interactions.
- Added scripts for starting, stopping, and cleaning the development stack.
- Enhanced API and tenant routes to support tenant-specific pipeline status initialization.
- Updated constants for backend URL to reflect the correct port.
- Improved error handling and logging in various components.
* feat: Add multi-tenant support with enhanced E2E testing scripts and client functionality
* update client
* Add integration and unit tests for multi-tenant API, models, security, and storage
- Implement integration tests for tenant and knowledge base management endpoints in `test_tenant_api_routes.py`.
- Create unit tests for tenant isolation, model validation, and role permissions in `test_tenant_models.py`.
- Add security tests to enforce role-based permissions and context validation in `test_tenant_security.py`.
- Develop tests for tenant-aware storage operations and context isolation in `test_tenant_storage_phase3.py`.
* feat(e2e): Implement OpenAI model support and database reset functionality
* Add comprehensive test suite for gpt-5-nano compatibility
- Introduced tests for parameter normalization, embeddings, and entity extraction.
- Implemented direct API testing for gpt-5-nano.
- Validated .env configuration loading and OpenAI API connectivity.
- Analyzed reasoning token overhead with various token limits.
- Documented test procedures and expected outcomes in README files.
- Ensured all tests pass for production readiness.
* kg(postgres_impl): ensure AGE extension is loaded in session and configure graph initialization
* dev: add hybrid dev helper scripts, Makefile, docker-compose.dev-db and local development docs
* feat(dev): add dev helper scripts and local development documentation for hybrid setup
* feat(multi-tenant): add detailed specifications and logs for multi-tenant improvements, including UX, backend handling, and ingestion pipeline
* feat(migration): add generated tenant/kb columns, indexes, triggers; drop unused tables; update schema and docs
* test(backward-compat): adapt tests to new StorageNameSpace/TenantService APIs (use concrete dummy storages)
* chore: multi-tenant and UX updates — docs, webui, storage, tenant service adjustments
* tests: stabilize integration tests + skip external services; fix multi-tenant API behavior and idempotency
- gpt5_nano_compatibility: add pytest-asyncio markers, skip when OPENAI key missing, prevent module-level asyncio.run collection, add conftest
- Ollama tests: add server availability check and skip markers; avoid pytest collection warnings by renaming helper classes
- Graph storage tests: rename interactive test functions to avoid pytest collection
- Document & Tenant routes: support external_ids for idempotency; ensure HTTPExceptions are re-raised
- LightRAG core: support external_ids in apipeline_enqueue_documents and idempotent logic
- Tests updated to match API changes (tenant routes & document routes)
- Add logs and scripts for inspection and audit
- Remove separate ENABLE_RERANK flag in favor of rerank_binding="null"
- Change default rerank binding from "cohere" to "null" (disabled)
- Update UI to display both rerank binding and model information
- Read config from selected_rerank_func when env var missing
- Make api_key optional for rerank function
- Add response format validation with proper error handling
- Update Cohere rerank default to official API endpoint
- Add --enable-rerank CLI argument and ENABLE_RERANK env var
- Simplify rerank configuration logic to only check enable flag and binding
- Update health endpoint to show enable_rerank and rerank_configured status
- Improve logging messages for rerank enable/disable states
- Maintain backward compatibility with default value True
• Remove global temperature parameter
• Add provider-specific temp configs
• Update env example with new settings
• Fix Bedrock temperature handling
• Clean up splash screen display
- Add global --temperature command line argument with env fallback
- Implement temperature priority for Ollama LLM binding:
1. --ollama-llm-temperature (highest)
2. OLLAMA_LLM_TEMPERATURE env var
3. --temperature command arg
4. TEMPERATURE env var (lowest)
- Implement same priority logic for OpenAI/Azure OpenAI LLM binding
- Ensure command line args always override environment variables
- Maintain backward compatibility with existing configurations
- Add OpenAILLMOptions dataclass with full OpenAI API parameter support
- Integrate OpenAI options in config.py for automatic binding detection
- Update server functions to inject OpenAI options for openai/azure_openai bindings
- Implement OLLAMA_LLM_TEMPERATURE env var
- Fallback to global TEMPERATURE if unset
- Remove redundant OllamaLLMOptions logic
- Update env.example with new setting
This parameter is no longer used. Its removal simplifies the API and clarifies that token length management is handled by upstream text chunking logic rather than the embedding wrapper.
Fix line length
Create binding_options.py
Remove test property
Add dynamic binding options to CLI and environment config
Automatically generate command-line arguments and environment variable
support for all LLM provider bindings using BindingOptions. Add sample
.env generation and extensible framework for new providers.
Add example option definitions and fix test arg check in OllamaOptions
Add options_dict method to BindingOptions for argument parsing
Add comprehensive Ollama binding configuration options
ruff formatting Apply ruff formatting to binding_options.py
Add Ollama separate options for embedding and LLM
Refactor Ollama binding options and fix class var handling
The changes improve how class variables are handled in binding options
and better organize the Ollama-specific options into LLM and embedding
subclasses.
Fix typo in arg test.
Rename cls parameter to klass to avoid keyword shadowing
Fix Ollama embedding binding name typo
Fix ollama embedder context param name
Split Ollama options into LLM and embedding configs with mixin base
Add Ollama option configuration to LLM and embeddings in lightrag_server
Update sample .env generation and environment handling
Conditionally add env vars and cmdline options only when ollama bindings
are used. Add example env file for Ollama binding options.
- Add ollama_server_infos attribute to LightRAG class with default initialization
- Move default values to constants.py for centralized configuration
- Refactor OllamaServerInfos class with property accessors and CLI support
- Update OllamaAPI to get configuration through rag object instead of direct import
- Add command line arguments for simulated model name and tag
- Fix type imports to avoid circular dependencies
This commit renames the parameter 'llm_model_max_token_size' to 'summary_max_tokens' for better clarity, as it specifically controls the token limit for entity relation summaries.
- Add 9 environment variables to /health endpoint configuration section
- Centralize default constants in lightrag/constants.py for consistency
- Update config.py to use centralized defaults for better maintainability
This commit refactors query parameter management by consolidating settings like `top_k`, token limits, and thresholds into the `LightRAG` class, and consistently sourcing parameters from a single location.
- Refactor the trigger condition for LLM-based summarization of entities and relations. Instead of relying on character length, the summary is now triggered when the number of merged description fragments exceeds a configured threshold. This provides a more robust and logical condition for consolidation.
- Introduce the `OLLAMA_NUM_CTX` environment variable to explicitly configure the context window size (`num_ctx`) for Ollama models. This decouples the model's context length from the `MAX_TOKENS` parameter, which is now specifically used to limit input for summary generation, making the configuration clearer and more flexible.
- Updated `README` files, `env.example`, and default values to reflect these changes.
This commit introduces `lightrag/constants.py` to centralize default values for various configurations across the API and core components.
Key changes:
- Added `constants.py` to centralize default values
- Improved the `get_env_value` function in `api/config.py` to correctly handle string "None" as a None value and to catch `TypeError` during value conversion.
- Updated the default `SUMMARY_LANGUAGE` to "English"
- Set default `WORKERS` to 2
