Skip to main content

AI service

PDF/document to structured JSON

We provide PDF/document to structured JSON at any scale, on a private cluster dedicated to you — from a single GPU to a hundred, on premise or in any cloud.

If you need such a service please contact us.

A whole document is parsed into JSON with its hierarchy preserved: sections, headings, paragraphs, lists, tables and footnotes, each with its page and position. Scanned and born-digital files are handled through the same interface and return the same shape. Reading order is reconstructed for multi-column layouts, which is where naive extraction usually fails.

You can use the models we operate or bring your own model and we run it on your cluster. Work arrives as an API call, a batch over a folder or bucket, or a resident on-premise service, and results return as structured output with a per-job audit record.

More services