Annotation Models are plug and play packages which perform file extraction, annotation or conversion. Read the docs.

High-performance speech-to-text transcription using CTranslate2-based Whisper models.

Last Updated: 2026-02-26

Fast, deterministic PDF extraction using pdfium.

Last Updated: 2026-02-26

Arxiv PDF inference model. Get structured info about an ArXiv preprint.

Last Updated: 2026-03-03