- Introduced BACKEND_URL in the configuration to allow overriding the HTTP to HTTPS in the OAuth redirect URI.
- Updated the Google OAuth router to conditionally use the BACKEND_URL for the redirect URI when specified.
- Introduced a fixed parameter order for AzureOpenAIEmbeddings to resolve compatibility issues.
- Updated the voice selection logic to include Azure voices in the podcaster utility.
- Modified the page limit service to use a more efficient method for retrieving users.
- Added RERANKERS_ENABLED option to control reranking functionality.
- Updated rerank_documents function to handle cases when reranking is disabled.
- Enhanced documentation for environment variables related to rerankers in installation guides.
- Simplify STT_SERVICE config to local/MODEL_SIZE format
- Remove separate STT routes, integrate with document upload
- Add local STT support to audio file processing pipeline
- Remove React component, use existing upload interface
- Support both local Faster-Whisper and external STT services
- Tested with real speech: 99% accuracy, 2.87s processing
- Remove .env file (should not be committed to version control)
- Revert docker-compose.override.yml to use ghcr images instead of local builds
- Remove unnecessary DOCLING config section from __init__.py
- Remove model context window additions (litellm already provides this)
- Keep litellm<1.70.0 constraint due to Ollama vector_stores 404 errors
Addresses all feedback from PR #211 review
- Added DOCLING as third ETL_SERVICE option (alongside UNSTRUCTURED/LLAMACLOUD)
- Implemented add_received_file_document_using_docling function
- Added Docling processing logic in documents_routes.py
- Enhanced chunking with configurable overlap support
- Added comprehensive document processing service
- Supports both CPU and GPU processing with user selection
Addresses #161 - Add Docling Support as an ETL_SERVICE
Follows same pattern as LlamaCloud integration (PR #123)
