Pduut

Pduut

From textbooks to structured knowledge — PDFs, untangled

3 followers

Pduut is an open-source PDF extractor built for students & researchers. It splits books page-by-page, capturing text, equations, and diagrams into structured JSON—perfect for RAG datasets. Join us, contribute, and make learning accessible!

Pduut makers

Here are the founders, developers, designers and product people who worked on Pduut