微软 MarkItDown
Microsoft's open-source Python tool — convert PDF/Word/PPT/audio/YouTube to clean Markdown
Microsoft's open-source Python tool that converts PDF/Word/PPT/audio/YouTube into clean Markdown with one command — a RAG data-preprocessing essential.
Translate documents, parse PDFs, and extract text with OCR.
Key features
- Lightweight Python utility converting files to Markdown for LLMs
- Supports PDF, Word, PowerPoint, Excel, images, audio, HTML, YouTube
- Preserves document structure: headings, lists, tables, links
- Plugin system and LLM-vision OCR plugin for embedded images
Good for
- Developers feeding documents into LLM text analysis pipelines
- RAG pipelines needing Markdown conversion of office files
Stack & tags
Pythonmarkdowndocument-conversionllm-preprocessingpdfocrclipython-library
Quick start
pip install 'markitdown[all]'
markitdown path-to-file.pdf > document.mdFrom the project README on GitHub.
Similar open-source projects
DeepSeek-OCR
★ 23,926DeepSeek's novel OCR document model — "contextual optical compression"
olmOCR
★ 19,683AI2's open-source OCR — high-quality PDF-to-text at 1/32 the cost of GPT-4o API