Skip to content

kreuzberg

Extract text from documents with a local Python library

Visit official site

What kreuzberg is

kreuzberg is described as a modern Python library for extracting text from many document formats through a compact local API.

What you can do with it

  • Extract text from PDFs, images and office files
  • Run OCR on scanned documents
  • Detect text encoding automatically

Getting started

  • Install the library with pip
  • Add Pandoc and Tesseract OCR
  • Use extract_file or extract_bytes
  • Pass a file path or byte content

Pros & cons

✓ What we like

  • No external API or cloud dependency is described
  • Light resource use is listed

! What to watch out for

  • Processing is described as local only
  • System dependencies such as Pandoc and Tesseract are needed

FAQ

Which formats are named?

The feature list names PDF, images and office documents.

How is it installed?

The material describes pip installation plus Pandoc and Tesseract OCR.

Last reviewed: 2026-11-15

More AI coding tools tools

View all →

How we review