AI For Document Intelligence

We train AI models for OCR, layout analysis, PDF to markdown, and more. They're state of the art, easy to use, and open source.

Our Solutions

Here's what our models can do.

PDF -> Markdown

Marker converts PDF to Markdown quickly and accurately, including tables and equations.

OCR

Surya handles OCR in over 90 languages. It benchmarks similarly to Google Cloud OCR on print documents.

Line Detection

Surya does state of the art line detection in any language.

Layout Analysis

Surya can identify layout blocks like titles, images, and equations in a wide range of documents.

Reading Order

Surya can properly order documents, even complex ones like newspapers.

LaTeX OCR

Texify OCRs equations and turns them into LaTeX.

Run them on-prem

Use our state of the art tools securely in your own environment.