github.com
Zerox
A document extraction tool that uses vision models to read page images.
https://github.com/getomni-ai/zeroxAbout This Resource
A document extraction tool that uses vision models to read page images. It converts the resulting content into Markdown for downstream processing and AI applications.
Saved Notes
Original notes saved with this link. They may describe an earlier version.
GitHub - getomni-ai/zerox: PDF to Markdown with vision models
Zerox OCR
A dead simple way of OCR-ing a document for AI ingestion. Documents are meant to be a visual representation after all. With weird layouts, tables, charts, etc. The vision models just make sense!