MarkItDown
Microsoft's tool for converting Office documents, PDFs, and other files to clean Markdown
Visit MarkItDown →MarkItDown converts Word documents, PowerPoint decks, Excel spreadsheets, PDFs, images, and audio files into Markdown — built specifically with LLM pipelines in mind, since Markdown’s plain structure tokenizes and feeds into a model far more cleanly than raw Office XML or PDF text extraction usually does.
It’s become a common preprocessing step in RAG pipelines and document-ingestion tools for exactly that reason: convert once to a consistent, model-friendly format, then work with that instead of writing separate parsers per file type.