TLDR Tech / DevOps
MarkItDown (GitHub Repo)
Microsoft has released MarkItDown, an open-source Python utility that converts various file formats (including PDF, Word, PowerPoint, and Excel) into Markdown for use with large language models and text analysis. The tool requires Python 3.10 or higher and focuses on preserving document structure like headings, lists, and tables while being token-efficient, with optional features including OCR support through plugins and integration with Azure's Content Understanding service for higher-quality conversions.
Read the full story