Data & databases

PyMuPDF is a high-performance Python library for extracting, analyzing, converting and manipulating PDF and other documents, built on the MuPDF engine.

Docling is an MIT-licensed Python library that parses PDF, DOCX, PPTX, HTML and many other documents into structured data ready for generative AI pipelines.

Apache Tika is an open-source Java library and toolkit that detects file types and extracts metadata and text from over a thousand formats, including PDF, PPT and XLS.