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
- Optimize JWT Auth module to load configuration via `global_args`.
- Decouple configuration-related code from `utils_api.py`, and add a new `config.py` file for unified configuration management.
- Adjust configuration import in `lightrag_server.py`, `auth.py`, and `document_routes.py` to be introduced through `global_args`.
