Skip to content
@datalab-to

Datalab

Developing state of the art document intelligence models.

Pinned Loading

  1. marker marker Public

    Convert PDF to markdown + JSON quickly with high accuracy

    Python 40.4k 2.9k

  2. surya surya Public

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

    Python 21.5k 1.6k

  3. pdftext pdftext Public

    Extract structured text from pdfs quickly

    Python 729 81

  4. chandra chandra Public

    OCR model that handles complex tables, forms, handwriting with full layout.

    Python 12.5k 1.3k

  5. lift lift Public

    Extract structured data from documents quickly and accurately.

    Python 1.2k 112

Repositories

Showing 10 of 13 repositories
  • omni_parse_bench Public
    datalab-to/omni_parse_bench's past year of commit activity
    JavaScript 4 Apache-2.0 0 1 1 Updated Oct 14, 2026
  • omni_extract_bench Public

    A consistent, fair, benchmark for structured extraction.

    datalab-to/omni_extract_bench's past year of commit activity
    Python 34 Apache-2.0 5 2 5 Updated Oct 13, 2026
  • indra Public

    Fast CPU OCR: line detection, CTC recognition, reading order, markdown

    datalab-to/indra's past year of commit activity
    Python 111 Apache-2.0 9 1 0 Updated Oct 13, 2026
  • sdk Public
    datalab-to/sdk's past year of commit activity
    Python 11 MIT 9 4 21 Updated Oct 12, 2026
  • lift Public

    Extract structured data from documents quickly and accurately.

    datalab-to/lift's past year of commit activity
    Python 1,192 Apache-2.0 111 3 2 Updated Oct 5, 2026
  • marker Public

    Convert PDF to markdown + JSON quickly with high accuracy

    datalab-to/marker's past year of commit activity
    Python 40,433 Apache-2.0 2,926 377 101 Updated Oct 2, 2026
  • surya Public

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

    datalab-to/surya's past year of commit activity
    Python 21,492 Apache-2.0 1,562 163 35 Updated Sep 11, 2026
  • datalab-on-prem Public

    Scripts to run Datalab's self-service on-prem container

    datalab-to/datalab-on-prem's past year of commit activity
    Shell 8 3 0 0 Updated Jul 14, 2026
  • pdftext Public

    Extract structured text from pdfs quickly

    datalab-to/pdftext's past year of commit activity
    Python 729 Apache-2.0 81 12 8 Updated Jul 9, 2026
  • chandra Public

    OCR model that handles complex tables, forms, handwriting with full layout.

    datalab-to/chandra's past year of commit activity
    Python 12,498 Apache-2.0 1,257 49 14 Updated Jun 26, 2026
View all repositories

Most used topics

ocr ai pdf