Open-source document parsing tool that converts PDFs, images and Office documents into structured Markdown / JSON output.
MinerU is an open-source tool for intelligent document parsing, suited to turning PDFs, images, papers, reports and office documents into machine-readable Markdown, JSON and similar formats. It can be used for structuring research materials, extracting PDF content, converting documents to Markdown and building knowledge bases.
Use cases: PDF parsing, converting papers to Markdown, document structuring, table extraction, organising research materials
Note: Recognition of complex layouts, formulas and tables needs to be tested on your specific documents.
