Open-source document parser that extracts content from PDFs and other files into structured formats
Overview
- Purpose
- Open-source document parser that extracts content from PDFs and other files into structured formats
- Category
- Office
- Official site
- https://docling-project.github.io/docling/ (opens in a new tab)
Main features
- Parses text, layout and tables in PDFs and other documents
- OCR for scanned PDFs or images
- Outputs Markdown, HTML, JSON and other formats
- Runs locally, from the command line or in code
Best for
Suited to technical users organizing documents in bulk, building knowledge bases or converting PDFs into editable structures.
Things to know
- Installation and local use require setting up an environment; some models need separate downloads
- Check recognition of complex layouts, tables and formulas against the original
FAQ
- Can it process documents locally?
- Yes. The official documentation lists local execution.
- Can it export Markdown?
- Yes. The official documentation lists Markdown, HTML, JSON and other output formats.