Rocket - Think it. Type it. Launch it.
Mini toolsChandra OCR 2
By Datalab
Chandra is an open-source OCR-oriented document AI project built for high-complexity document parsing rather than simple flat text recognition. The repository positions it around structured extraction from tables, forms, handwriting, and other layout-heavy pages, with an emphasis on retaining document structure. That makes it useful for workflows where spatial organization matters, such as forms processing, scanned business documents, and tabular records, instead of just line-by-line transcription.
New
Multimodal
Gen 3
Overview
Chandra is an OCR model for difficult document extraction tasks. Its GitHub description says it handles complex tables, forms, and handwriting while preserving full layout structure, making it more document-understanding focused than plain text O
About Datalab
Datalab builds specialized, small AI foundation models (100-500M parameters) for document intelligence. Its open-source tools Surya (OCR, layout analysis in 90+ languages) and Marker (PDF-to-Markdown conversion) have 48K+ GitHub stars. The platform turns unstructured documents into structured, production-ready data for AI systems.
Industry:
Artificial Intelligence
Company Size:
1-10
Location:
New York, New York, US
Website:
datalab.to
Tools using Chandra OCR 2
No tools found for this model yet.
Last updated: March 27, 2026
