Convert PDF to markdown + JSON quickly with high accuracy
- Language
- Python
- Licence
- Apache-2.0
- Stars
- 40k
- Latest
- v2.0.0
- Last push
- 2026-10-02
Datalab
Repositories owned by Datalab, an organisation on GitHub.
Developing state of the art document intelligence models.
2 tools
OCR, layout analysis, reading order, table recognition in 90+ languages
- Language
- Python
- Licence
- Apache-2.0
- Stars
- 21k
- Latest
- v0.22.1
- Last push
- 2026-09-11