# Available OCR systems

Most of these systems use a combination of classical OCR + AI for best results.

## olmOCR

olmOCR is an open-source tool designed for high-throughput conversion of
PDFs and other documents into plain text while preserving natural
reading order. It supports tables, equations, handwriting, and more.

Links:
  - [Demo](https://olmocr.allenai.org/).
  - [Github](https://github.com/allenai/olmocr).
  - [HackerNews discussion](https://news.ycombinator.com/item?id=43174298).


## Mistral OCR

OCR engine for Le Chat / Mistral AI.

Links:
  - [LeChat](https://chat.mistral.ai/chat)
  - [HackerNews discussion](https://news.ycombinator.com/item?id=43282905).


## 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!

Links:
  - [Github](https://github.com/getomni-ai/zerox).
  - [Hosted version](https://getomni.ai/ocr-demo).