datalab-to/indra
New · under observationOverview
High-precision document intelligence. Transform unstructured content into precise, production-ready data.
Not yet sourced · 8 fields
Customers / users · Business model · Industry · Legal name · Location · Founded · Employee count · Latest valuation found
Developments · past 30 days
Indra OCR 1.1: handwriting, 80+ languages and pages at any angle
Published 2026-10-19
News & announcements · 18
API submits and result checks, 2x faster
2026-11-06 · datalab.to
Which document-parsing benchmarks can you trust?
2026-11-04 · datalab.to
Data extraction vs parsing: Which to use?
2026-11-02 · datalab.to
Surya 2.5: 1.7x faster, best open OCR under 1B
2026-10-29 · datalab.to
Chandra 2.6: more accurate than the frontier, 2.5x faster, same price
2026-10-27 · datalab.to
Lite vs Azure, AWS and Google: 2x faster, 10x cheaper, as accurate
2026-10-26 · datalab.to
Open-source OCR models on OmniParseBench
2026-10-23 · datalab.to
Lite mode: document parsing for $0.50 per 1,000 pages
2026-10-22 · datalab.to
Improved document segmentation
2026-10-21 · datalab.to
Word boxes that hold up on handwriting
2026-10-20 · datalab.to
Find the fillable fields on any form
2026-10-19 · datalab.to
Indra OCR 1.1: handwriting, 80+ languages and pages at any angle
2026-10-19 · datalab.to
Script confusions: when an OCR model writes the right word in the wrong alphabet
2026-10-16 · datalab.to
Managing Model Uncertainty to Catch OCR Hallucinations
2026-10-15 · datalab.to
Chandra 2.5: Structured Image Descriptions and Faster OCR
2026-10-14 · datalab.to
Indra OCR: a 1M-parameter OCR model that reads 49 pages per second on CPU
2026-10-13 · datalab.to
How KIQP's technical team processed 30,000 pages of historical Arabic archives ~65% faster
2026-10-13 · datalab.to
Why we built OmniParseBench
2026-10-12 · datalab.to
Private notes & workspace
Private to this browser. Export your workspace to move notes between devices.