Repository · GitHub

NanoNets/docext

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

View on GitHubReport an issue

Owner	NanoNets
License (as declared)	Apache-2.0
Stars	2,083
Forks	158
Main language	Python
Created	25 March 2025
Last updated at source	17 March 2026

pythondocumentdocument-analysisdocument-data-extractiondocument-information-extractionextractionllm-ocrllmsmachine-learningnlpocrocr-benchmarkocr-onpremiseonpremonprem-ocronprem-visiononpremiseragtable-extractionunstructured-datavlms

Embed this entry

<iframe src="https://silytics.si/embed/item/19f91164-f246-4d2d-8c62-385ad511d368" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from NanoNets

docstrangeRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.