- Add KaTeX extensions (mhchem for chemistry, copy-tex for copying)
- Add CASCADE to AGE extension for PostgreSQL
- Remove future dependency, replace passlib with bcrypt
- Fix Jina embedding configuration and provider defaults
- Update gunicorn help text and bump API version to 0258
- Documentation and README updates
Graph Connectivity Awareness:
- Add db_degree property to all KG implementations (NetworkX, Postgres, Neo4j, Mongo, Memgraph)
- Show database degree vs visual degree in node panel with amber badge
- Add visual indicator (amber border) for nodes with hidden connections
- Add "Load X hidden connection(s)" button to expand hidden neighbors
- Add configurable "Expand Depth" setting (1-5) in graph settings
- Use global maxNodes setting for node expansion consistency
Orphan Connection UI:
- Add OrphanConnectionDialog component for manual orphan entity connection
- Add OrphanConnectionControl button in graph sidebar
- Expose /graph/orphans/connect API endpoint for frontend use
Backend Improvements:
- Add get_orphan_entities() and connect_orphan_entities() to base storage
- Add orphan connection configuration parameters
- Improve entity extraction with relationship density requirements
Frontend:
- Add graphExpandDepth and graphIncludeOrphans to settings store
- Add min_degree and include_orphans graph filtering parameters
- Update translations (en.json, zh.json)
- 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
- 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
