ParseHawk

ParseHawk

ParseHawk is a self-hostable document AI preview from Austria that converts PDFs, scans and images into schema-validated JSON.

AustriaOpen Source

About ParseHawk

ParseHawk is a developer preview for document AI from Austria that you operate yourself. The software turns PDFs, scans, images, text and Markdown into JSON that is checked against a given schema. It can be operated through a REST API, the command line or a web interface. The bundled local model environment runs on macOS with Apple silicon chips and on Linux with NVIDIA graphics cards, but not on Windows or Intel Macs. The project is open source and free. As an alternative to Google Document AI it processes documents without them leaving your own system.

Frequently Asked Questions

Reviews

Sign in to write a review.

Sign In

More alternatives in Development, AI Chatbots & LLMs