MarkItDown: Microsoft’s Python tool to convert files to Markdown for AI/LLM workflows
Summary
MarkItDown is a lightweight Python utility from Microsoft for converting a wide range of file formats into Markdown designed for AI and large language model workflows. It supports PDFs, Office documents, images, audio, HTML, YouTube, and more, with optional dependencies and plugins, plus an MCP server integration for LLM context. The README also covers Azure Document Intelligence usage, installation, and contribution guidance, making it a practical tool for automating AI-ready content pipelines in SMBs.