kreuzberg-dev/langchain-kreuzberg

Langchain document loader for Kreuzberg

37
/ 100
Emerging

# Technical Summary Wraps Kreuzberg's Rust-powered extraction API to handle 88+ file formats with true async processing via tokio, producing LangChain `Document` objects enriched with metadata including quality scores, detected languages, and extracted keywords. Supports configurable OCR backends (Tesseract, EasyOCR, PaddleOCR), per-page splitting for RAG pipelines, multiple output formats (text, Markdown, HTML, structured), and direct bytes input from API responses or cloud storage.

Available on PyPI.

Maintenance 10 / 25
Adoption 9 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

4

Forks

Language

Python

License

MIT

Last pushed

Mar 04, 2026

Monthly downloads

248

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/kreuzberg-dev/langchain-kreuzberg"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.