> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lyzr.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OCR Agent

## 📄 POST `/extract`

Endpoint: [https://lyzr-ocr.lyzr.app/extract](https://lyzr-ocr.lyzr.app/extract)

### Summary

This API provides endpoints for a scalable and production-ready document processing service. It supports a PDF extraction endpoint that takes a PDF file, processes its content, and returns extracted data. Designed with multi-tenant architecture in mind via `organization_id`.

### Description

Upload a PDF file and extract relevant data. Requires `organization_id` as a query parameter and a file upload via `multipart/form-data`.

### Query Parameters

| Name             | Type   | Required | Description            |
| ---------------- | ------ | -------- | ---------------------- |
| organization\_id | string | ✅        | ID of the organization |

### Request Body

Content type: `multipart/form-data`

| Name | Type   | Format | Required | Description                   |
| ---- | ------ | ------ | -------- | ----------------------------- |
| file | string | binary | ✅        | PDF file to extract data from |

### Responses

| Status Code | Description         |
| ----------- | ------------------- |
| 200         | Successful Response |
| 422         | Validation Error    |

### **Response:**

```json theme={null}
{
  "status": "success",
  "data": {
    "1": {
      "page": 1,
      "content": ""
    },
    "2"{
      "page": 1,
      "content": ""
    },...
  },
  "total_actions": 2
}
```

#### Validation Error Schema

```json theme={null}
{
  "detail": [
    {
      "loc": ["string", 0],
      "msg": "string",
      "type": "string"
    }
  ]
}
```