Documents & data
microsoft/markitdown
Converts PDFs and office documents to clean Markdown for LLMs
- 174k
- MIT
- Python
What it is and why it matters
markitdown is a Microsoft Python tool that converts files and office documents (PDF, Word, Excel and others) to clean Markdown. The goal is to help an LLM understand and work with the data without parsing heavy formats, which also cuts token usage by not delegating conversion to the model. It fits well in RAG and context-preparation workflows.
Key points
- Converts PDF, Word, Excel and other formats to clean Markdown in Python
- Cuts token usage by doing the conversion outside the model
- Aimed at context preparation and RAG workflows, feeding the LLM more readable data
Where we saw it
Same category