Parse PDF, Office documents, and images into LLM-ready markdown or JSON with four quality tiers and nine output formats.
Unstructured
Open source alternative to Google Document AI, LlamaParse and Reducto
Parse PDFs, scans, spreadsheets, and 65+ file types into clean structured data for RAG pipelines, AI agents, and LLM workflows.
About Unstructured
Unstructured is an open source tool in Data & Analytics. Use it as a free, self-hostable alternative to LlamaParse, Reducto and Google Document AI.
Parse PDFs, scans, spreadsheets, and 65+ file types into clean structured data for RAG pipelines, AI agents, and LLM workflows.
Licensed under Apache-2.0 with 15,600 stars on GitHub.
More open source data & analytics tools
See all →
Build no-code database apps on any Postgres, MySQL, or SQLite with a spreadsheet interface. Grid, kanban, gallery, form, and calendar views included.
Visualize live aircraft, ships, satellites, earthquakes, and public cameras on a photorealistic 3D globe with no account or subscription required.
Free open-source database management tool for SQL databases.