github.com
MarkItDown
A Microsoft utility for converting documents and other files into Markdown.
https://github.com/microsoft/markitdownAbout This Resource
A Microsoft utility for converting documents and other files into Markdown. It extracts content into a text format that can be used for indexing, analysis, or language model workflows.
Saved Notes
Original notes saved with this link. They may describe an earlier version.
GitHub - microsoft/markitdown: Python tool for converting files and office documents to Markdown.
<img src="https://app.notion.com/icons/info-alternate_yellow.svg" alt="https://app.notion.com/icons/info-alternate_yellow.svg" width="40px" />
Word on the street out there (as of December 15, 2024) is that this project mainly uses existing libraries that handle document processing, but has yet to add substantial contributions to the topic, especially when it comes to dealing with Microsoft-specific OOXML shenanigans which we actually expect this package to fix.
But it does not. So for now, this gets the HOLD treatment.
The MarkItDown library is a utility tool for converting various files to Markdown (e.g., for indexing, text analysis, etc.)
The MarkItDown library is a utility tool for converting various files to Markdown (e.g., for indexing, text analysis, etc.)
It presently supports:
- PDF (.pdf)
- PowerPoint (.pptx)
- Word (.docx)
- Excel (.xlsx)
- Images (EXIF metadata, and OCR)
- Audio (EXIF metadata, and speech transcription)
- HTML (special handling of Wikipedia, etc.)
- Various other text-based formats (csv, json, xml, etc.)