- Enhance delete implementation in JsonKVStorage by removing immediate persistence in delete operation
- Update documentation for drop method to clarify persistence behavior
- Add abstract delete method to BaseKVStorage
- 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`.
- Use storage drop methods to properly clean up all data
- Add file deletion from input directory
- Add pipeline status checking and locking mechanism
- Improve error handling with detailed logging and pipeline message tracking
- Remove unused check_storage_env_vars method
- Add TODO to check if has_edge works on reverse relation
- Add TODO about entities_vdb.client_storage local storage limitation
- Use .env from current folder for each lightrag instance
- Allow different .env files for different instances
- Make OS env vars take precedence over .env file
Add support for custom client configurations in the OpenAI integration,
allowing for more flexible configuration of the AsyncOpenAI client.
This includes:
- Create a reusable helper function `create_openai_async_client`
- Add proper documentation for client configuration options
- Ensure consistent parameter precedence across the codebase
- Update the embedding function to support client configurations
- Add example script demonstrating custom client configuration usage
The changes maintain backward compatibility while providing a cleaner
and more maintainable approach to configuring OpenAI clients.
