- Introduced a new utility for parsing .xlsx files into markdown format, enhancing the ability to process Excel documents natively.
- Updated the Google Drive content extractor to utilize the new Excel parsing functionality, allowing for better handling of spreadsheet files.
- Enhanced file type detection and export logic to support various document formats, improving overall content extraction accuracy.
- Added unit tests to ensure the correctness of the new Excel parsing feature and its integration with existing content extraction workflows.
- Added a reentrant lock to ensure thread-safe access to the tokenizer and embedding model, preventing runtime errors during concurrent operations.
- Updated the `truncate_for_embedding` and `embed_text` functions to utilize the lock, ensuring safe execution in multi-threaded environments.
- Enhanced the `embed_texts` function to maintain thread safety while processing multiple texts for embedding.
- Added endpoint to list agent tools with metadata, excluding hidden tools.
- Updated NewChatRequest and RegenerateRequest schemas to include disabled tools.
- Integrated disabled tools management in the NewChatPage and Composer components.
- Improved tool instructions and visibility in the system prompt.
- Refactored tool registration to support hidden tools and default enabled states.
- Enhanced document chunk creation to handle strict zip behavior.
- Cleaned up imports and formatting across various files for consistency.
- Introduced a shielded async session context manager to ensure safe session closure during cancellations.
- Updated various database operations to utilize the new shielded session, preventing orphaned connections.
- Added environment variables to optimize glibc memory management, improving overall application performance.
- Implemented a function to trim the native heap, allowing for better memory reclamation on Linux systems.
- Increased maximum file upload limit from 10 to 50 to improve user experience.
- Implemented batch processing for document uploads to avoid proxy timeouts, splitting files into manageable chunks.
- Enhanced garbage collection in chat streaming functions to prevent memory leaks and improve performance.
- Added memory delta tracking in system snapshots for better monitoring of resource usage.
- Updated LLM router and service configurations to prevent unbounded internal accumulation and improve efficiency.
- Introduced RequestPerfMiddleware to log request performance metrics, including slow request thresholds.
- Updated various services and retrievers to utilize the new performance logging utility for better tracking of execution times.
- Enhanced existing methods with detailed performance logs for operations such as embedding, searching, and indexing.
- Removed deprecated logging setup in stream_new_chat and replaced it with the new performance logger.
- Replaced direct embedding calls with a utility function across various components to streamline embedding logic.
- Added enable_summary flag to several models and routes to control summary generation behavior.
- Add NotionKBSyncService for immediate KB updates after page changes
- Implement block ID verification to ensure content freshness
- Refactor duplicate block processing logic to shared utils
- Add user-friendly status messages
- Include debug logging for troubleshooting
- Updated the Composio connector naming logic to dynamically generate user-friendly names based on existing connectors.
- Introduced new utility functions for counting connectors and retrieving base names for specific connector types.
- Enhanced the UI components to improve accessibility and focus management, ensuring a better user experience when interacting with connector dialogs.
- Refactored GitHubConnector to utilize gitingest CLI via subprocess, improving performance and avoiding async issues with Celery.
- Updated ingestion method to handle repository digests more efficiently, including error handling for subprocess execution.
- Adjusted GitHub indexer to call the new synchronous ingestion method.
- Clarified documentation regarding the optional nature of the Personal Access Token for public repositories.
