zerox

![Hero Image](./assets/heroImage.png)

## Zerox OCR

<a href="https://discord.gg/smg2QfwtJ6">
  <img src="https://github.com/user-attachments/assets/cccc0e9a-e3b2-425e-9b54-e5024681b129" alt="Join us on Discord" width="200px">
</a>

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!

The general logic:

- Pass in a file (PDF, DOCX, image, etc.)
- Convert that file into a series of images
- Pass each image to GPT and ask nicely for Markdown
- Aggregate the responses and return Markdown

Try out the hosted version here: <https://getomni.ai/ocr-demo>
Or visit our full documentation at: <https://docs.getomni.ai/zerox>

## Getting Started

Zerox is available as both a Node and Python package.

- [Node README](#node-zerox) - [npm package](https://www.npmjs.com/package/zerox)
- [Python README](#python-zerox) - [pip package](https://pypi.org/project/py-zerox/)

| Feature                   | Node.js                      | Python                     |
| ------------------------- | ---------------------------- | -------------------------- |
| PDF Processing            | ✓ (requires graphicsmagick)  | ✓ (requires poppler)       |
| Image Processing          | ✓                            | ✓                          |
| OpenAI Support            | ✓                            | ✓                          |
| Azure OpenAI Support      | ✓                            | ✓                          |
| AWS Bedrock Support       | ✓                            | ✓                          |
| Google Gemini Support     | ✓                            | ✓                          |
| Vertex AI Support         | ✗                            | ✓                          |
| Data Extraction           | ✓ (`schema`)                 | ✗                          |
| Per-page Extraction       | ✓ (`extractPerPage`)         | ✗                          |
| Custom System Prompts     | ✗                            | ✓ (`custom_system_prompt`) |
| Maintain Format Option    | ✓ (`maintainFormat`)         | ✓ (`maintain_format`)      |
| Async API                 | ✓                            | ✓                          |
| Error Handling Modes      | ✓ (`errorMode`)              | ✗                          |
| Concurrent Processing     | ✓ (`concurrency`)            | ✓ (`concurrency`)          |
| Temp Directory Management | ✓ (`tempDir`)                | ✓ (`temp_dir`)             |
| Page Selection            | ✓ (`pagesToConvertAsImages`) | ✓ (`select_pages`)         |
| Orientation Correction    | ✓ (`correctOrientation`)     | ✗                          |
| Edge Trimming             | ✓ (`trimEdges`)              | ✗                          |

## Node Zerox

(Node.js SDK - supports vision models from different providers like OpenAI, Azure OpenAI, Anthropic, AWS Bedrock, Google Gemini, etc.)

### Installation

```sh
npm install ze