Datalab

Dépôts appartenant à Datalab, une organisation sur GitHub.

Developing state of the art document intelligence models.

Profil GitHub ↗Site web ↗

2 outils

Convert PDF to markdown + JSON quickly with high accuracy

Langage: Python
Licence: Apache-2.0
Étoiles: 40k
Dernière release: v2.0.0
Dernier push: 2026-10-02

OCR, layout analysis, reading order, table recognition in 90+ languages

Langage: Python
Licence: Apache-2.0
Étoiles: 21k
Dernière release: v0.22.1
Dernier push: 2026-09-11