Goldziher/kreuzberg

The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.

197 best points · 75 comments · 1 Hacker News post · 9,558 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Kreuzberg – Modern async Python library for document text extraction (197 points, 75 comments, by nhirschfeld, 2025-02-15)