unstract

Unstract is an open-source document intelligence platform that uses LLMs to extract structured JSON output from unstructured documents including PDFs, scanned images, and other formats. Its core workflow centers on Prompt Studio, a visual interface where users define extraction schemas using plain natural language rather than regex or rigid templates, then deploy those schemas either as REST API endpoints or as ETL pipelines that pull documents from folders and load results into data warehouses. The platform connects to Claude and other AI agents through a built-in MCP server, and also supports an n8n custom node for automation workflow integration. LLM providers including Anthropic, OpenAI, AWS Bedrock, and Ollama are all supported as interchangeable backends. The entire platform deploys locally via a single `./run-platform.sh` script using Docker Compose with an 8 GB RAM minimum. Primary audiences are engineering and operations teams in finance, insurance, healthcare, and compliance who need reliable, schema-consistent data extraction from high-volume document workflows without building custom extraction pipelines from scratch.

Lo que la gente pregunta sobre unstract