kreuzberg 1.0.0 copy "kreuzberg: ^1.0.0" to clipboard
kreuzberg: ^1.0.0 copied to clipboard

High-performance document intelligence library — extract text, metadata, tables from 97+ formats including PDF, DOCX, images, and email.

1.0.0 #

  • Initial release candidate
  • Document extraction (text, metadata, tables) from 97+ formats
  • OCR via Tesseract, PaddleOCR, VLM backends
  • HTML-to-Markdown conversion
  • PDF rendering
  • Code intelligence via tree-sitter (248 languages)
  • MIME type detection (118+ extensions)
  • LLM-powered structured extraction
  • Batch document processing
  • Embeddings generation via ONNX Runtime
2
likes
45
points
182
downloads

Documentation

API reference

Publisher

verified publisherkreuzberg.dev

Weekly Downloads

High-performance document intelligence library — extract text, metadata, tables from 97+ formats including PDF, DOCX, images, and email.

Homepage
Repository (GitHub)
View/report issues
Contributing

License

Elastic-2.0 (license)

Dependencies

flutter_rust_bridge, freezed_annotation, json_annotation

More

Packages that depend on kreuzberg