mirror of
https://github.com/coleam00/Archon.git
synced 2025-12-24 02:39:17 -05:00
bc97f5dbf5
- Add Docling dependency to pyproject.toml for multi-format document support - Create docling_processing.py with DocumentConverter and HybridChunker - Implement intelligent semantic-aware chunking for better RAG performance - Add enhanced document upload method with Docling integration - Update knowledge API to use enhanced processing with legacy fallback - Support PDF, DOCX, PPTX, XLSX, HTML formats with structure preservation - Include enhanced metadata tracking for processing methods - Maintain backward compatibility with existing document processors Resolves #756 🤖 Generated with [Claude Code](https://claude.ai/code) Co-authored-by: Cole Medin <coleam00@users.noreply.github.com>