Unstract

Active

GitHub Python AGPL-3.0

Description

LLM-driven extraction of unstructured data, built for API deployments and ETL pipeline workflows. Automates document parsing, PDF extraction, and intelligent data processing with LLM-powered intelligence.

Key Features

Prompt Studio defines document extraction schemas with natural language
Supports REST API deployment and ETL pipeline workflows
MCP Server integration connecting to Claude and other AI agents
Compatible with OpenAI, Anthropic, Bedrock, Ollama, and more
Handles PDFs, images, scans, and many other document formats
n8n node integration to embed into existing automation workflows

Use Cases

💡 Extract structured data from unstructured documents for database storage

💡 Automate document processing in finance and insurance workflows

💡 Build intelligent extraction systems for KYC and compliance scenarios

💡 Convert unstructured PDF reports into analyzable JSON data

Strengths & Limitations

✅ Strengths

• Actively maintained, recent updates
• High community interest (7.2k stars)
• Established track record (2 years in production)

⚠️ Limitations

• Restrictive license (AGPL-3.0)

Quick Start

1. Clone the repository and navigate to the project directory
2. Run `./run-platform.sh` to start everything
3. Visit `http://frontend.unstract.localhost`
4. Login with username `unstract` password `unstract`
5. Define extraction schemas in Prompt Studio and start extracting

Visit GitHub

Related Projects

Instill Core

2.3k · Python

Stale C

A full-stack AI infrastructure tool for data, model, and pipeline orchestration. Streamlines building versatile AI-first applications with a visual pipeline editor for end-to-end workflows from data ingestion to model inference.

workflowpythonautomation +3

· End-to-end AI platform for data, pipeline, and model orchestration
· Visual pipeline editor for building versatile AI-first APIs and automated workflows
· Unstructured data processing turning documents, images, audio, and video into AI-ready formats

View on GitHub

DocETL

4.1k · Python

Active A

An agentic LLM-powered data processing and ETL system. Enables complex data transformations using natural language-defined pipelines, turning unstructured data into structured, analyzable outputs with LLM intelligence.

data-processingragpython +3

· LLM-powered data processing pipeline engine with operators like map, reduce, resolve, gleaning, and filter for complex document transformations
· DocWrangler interactive UI playground for iterative prompt engineering — experiment with prompts and see results in real-time
· Python package for production pipelines runnable from command line or Python code with full programmatic control

View on GitHub

OpenLLM

12.5k · Python

Active A+

Run any open-source LLMs such as DeepSeek and Llama as OpenAI-compatible API endpoints in the cloud. Supports fine-tuning, quantization, and distributed inference for production-grade LLM deployment.

llmpythonapi +3

· Any Open-Source LLM Support: Run DeepSeek, Llama, Qwen and any open-source models
· OpenAI-Compatible APIs: Provides endpoints compatible with OpenAI API for seamless integration
· Built-in Chat UI: Ready-to-use chat interface

View full details → View on GitHub

Haystack

26.4k · Python