Office Documents for RAG Format Matrix | Format | Library | Markdown Path | Tables | Images | Comments | |--------|---------|---------------|--------|--------|----------| | DOCX | python-docx | mammoth | Yes | python-docx | python-docx | | PPTX | python-pptx | custom | Limited | | | | XLSX | openpyxl / pandas | custom | Native | Embedded images | openpyxl | | Notion | Notion API + notion-to-md | Native | Yes | Block downloads | Discussion blocks | | Confluence | atlassian-python-api | html2md | Yes | Attachments endpoint | Inline comments API | | Quip | Quip API | html2md | Yes | Blob endpoin…