Convert PDFs and other documents to Markdown, JSON and HTML
Overview
- Purpose
- Convert PDFs and other documents to Markdown, JSON and HTML
- Category
- Office
- Official site
- https://github.com/datalab-to/marker (opens in a new tab)
Main features
- Convert PDFs and other documents to Markdown
- Support outputs including JSON and HTML
- Extract images and process tables and equations
- Optionally use a language model to assist document parsing
Best for
Useful for converting PDF material into editable or machine-processable content.
Things to know
- Installation is required; code and model weights have different license terms, which should be checked separately for commercial use.
- Review generated results before use.
- Before submitting or connecting materials, confirm that you have permission to process them.
FAQ
- Can it output Markdown?
- Yes. The project supports Markdown, JSON and HTML among other formats.
- Do the model weights use the same license as the code?
- No. The project describes different terms for each; check them for your use.