What it does
Unstract reads documents such as PDFs, images and scans and pulls out the information you ask for. You describe what you want in plain language, and it returns tidy data in JSON, a common format for structured data.
You can set it up as an API (a doorway other programs call) or as a pipeline that takes files from a folder and loads results into a database. It also connects to AI agents and to the n8n automation tool.
It works with many AI providers, including OpenAI, Anthropic and local models through Ollama. There is also a paid enterprise version.
Who it's for
Teams in finance, insurance, healthcare and compliance that process lots of documents.
Can I use it without coding?
With some setup. You run it with Docker using one setup script. New to this? Start here.
Can I run it?
- Cost
- Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
- Runs on
- Linux, Mac, Server
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Install Docker on a Linux or Mac computer with at least 8 GB of memory.
- Download the project and run its platform script.
- Open the local web page, log in and describe the data you want to extract.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (AGPL-3.0): Free to use; if you run a changed version as an online service, you must share your source code.
- More on staying safe
Where people are talking about it
- Show HN: Unstract(AGPL) – Launch LLM-powered APIs to structure unstructured docsHacker News · Mar 2024