BREAKING CHANGE: The `content` field in query response references is now
an array of strings instead of a concatenated string. This preserves
individual chunk boundaries when a single file has multiple chunks.
Changes:
- Update QueryResponse Pydantic model to accept List[str] for content
- Modify query_text endpoint to return content as list (query_routes.py:425)
- Modify query_text_stream endpoint to support chunk content enrichment
- Update OpenAPI schema and examples to reflect array structure
- Update API README with breaking change notice and migration guide
- Fix RAGAS evaluation to flatten chunk content lists
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
• Uses exact versions from `bun.lock` without updating
• Skips devDependencies, saving time and bandwidth
• The --emptyOutDir already configured in vite.config.ts
Added three new REST API endpoints for direct knowledge graph manipulation:
- POST /graph/entity/create: Create new entities in the knowledge graph
- POST /graph/relation/create: Create relationships between entities
- POST /graph/entities/merge: Merge duplicate/misspelled entities while preserving relationships
The merge endpoint is particularly useful for consolidating entities discovered after document processing, fixing spelling errors, and cleaning up the knowledge graph. All relationships from source entities are transferred to the target entity, with intelligent handling of duplicate relationships.
Updated API documentation in lightrag/api/README.md with usage examples for all three endpoints.
- 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
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.
- 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.
