unstract

What it does

Pulls structured JSON out of PDFs, images and scans by describing what you want in natural language, so one prompt covers layout variation that would otherwise mean a template per vendor. Deployable as an API or an ETL pipeline, and aimed at finance, insurance, healthcare and KYC workloads. Those are exactly the fields where an extraction error costs money, so validate on your own documents and keep a human check — and note the documents themselves reach whichever model you configure. AGPL-3.0.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

• Setup difficultySome setup needed
• Command lineRequired
• API keyRequired
• Sends data onlineYes

Judged automatically from the project's own metadata. Always confirm on the official page.

unstract FAQ

Is unstract free?

unstract itself is free, but it needs an API key for an external AI service. That service charges separately, though some have a free tier.

Do I need to install anything or write code to use unstract?

It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.

Does unstract work on a phone?

No. It needs a computer.

Can I use unstract commercially?

The licence is AGPL-3.0. Using it commercially is fine, but if you distribute something built on it you may be required to release that under the same licence. Keep it internal, or check before distributing.

How it compares

The conditions that decide whether you can actually use it, side by side.

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other docs & pdf q&a tools