PDF

Read PDFs locally without OCR or an API key — classify text-based versus scanned in tens of milliseconds and name the pages that still need OCR, convert to markdown with headings, lists and tables intact, and pull positioned text or the exact characters inside a box on a page.

iii-hq Updated 114 repo stars

File contents

iii-hq/workers commit bff66caf27

Frequently asked questions

npx get-skill add iii-hq/pdf