unstract

LLM-driven platform turning unstructured documents into structured data: a no-code Prompt Studio to define extractions, then deploy as APIs or ETL pipelines. Self-hosted, AGPL + enterprise.

6,931 661 Python AGPL-3.0updated today

ocr rag

View on GitHubDispute this mapping →

Curator's take

The platform play in document extraction: where parsers hand you markdown, Unstract hands you the FIELDS — Prompt Studio lets a domain expert define and test per-document-type extraction prompts, then ships them as stable APIs or ETL pipelines into warehouses, with the connector surface (S3, databases, DMS) that ops teams actually need. Docker-compose up and it runs. NOT a parsing engine: quality rides on the LLM you wire in and per-page LLM calls at volume cost real money — for clean-layout bulk conversion a deterministic parser is cheaper; and mind the AGPL + enterprise split when embedding.

Mapped by ShipWithAI editors · links verified

README.md

Unstract

Turn Unstructured Documents into Structured Data

Documentation | Enterprise

Python Version from PEP 621 TOML

What is Unstract?

Unstract uses LLMs to extract structured JSON from documents — PDFs, images, scans, you name it. Define what you want to extract using natural language prompts, and deploy as an API or ETL pipeline.

Built for teams in finance, insurance, healthcare, KYC/compliance, and much more.

Current State vs. Unstract

Task	Without Unstract	With Unstract
Schema definition	Write regex, build templates per vendor	Write a prompt once, handles variations
New document type	Days of development	Minutes in Prompt Studio
LLM integration	Build your own pipeline	Plug in any provider (OpenAI, Anthropic, Bedrock, Ollama)
Deployment	Custom infrastructure	`./run-platform.sh` or managed cloud
Output	Unstructured text blobs	Clean JSON, ready for your database

⭐ If Unstract helps you, star this repo!

✨ Key Features

Prompt Studio — Define document extraction schemas with natural language. Docs →

![Prompt Studio](docs/assets/prompt_studi

Continue your stack

What teams reach for next — and why each earns a place beside unstract. Ranked by curator confidence.

Alternative to See all + compare →

chunkr

Document intelligence API in Rust: layout analysis, OCR with bounding boxes, and semantic chunking that turn PDFs, PPTs and Word docs into RAG-ready structured chunks.

Why it fitsBoth are self-hostable document-intelligence services, split by output: Chunkr produces layout-aware RAG-ready chunks; Unstract produces schema-shaped structured fields via prompt-defined extraction, deployable as APIs and ETL.

MinerU

Heavyweight document-to-markdown/JSON parser — PDFs plus Office (docx/pptx/xlsx) through layout analysis and OCR into LLM-ready output for RAG and agentic pipelines. 73k stars, self-hostable.

Why it fitsParser vs platform: MinerU converts documents to LLM-ready markdown/JSON; Unstract sits a level up — prompt-engineered field extraction with deployment, connectors and pipeline management around it. Many stacks front Unstract-style extraction with a MinerU-style parser.