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

# Data Extraction

> AI-powered extraction of structured data from invoices

VATextract uses advanced OCR technology to extract structured data from any invoice format—PDF, scanned documents, or images.

## Supported File Formats

| Format     | Description                       |
| ---------- | --------------------------------- |
| PDF        | Native PDFs and scanned documents |
| JPEG/PNG   | High-resolution images            |
| Multi-page | Documents up to 100 pages         |

## Extracted Fields

### Header Information

| Field           | Description                  |
| --------------- | ---------------------------- |
| `invoiceNumber` | Unique invoice identifier    |
| `invoiceDate`   | Date the invoice was issued  |
| `dueDate`       | Payment due date             |
| `deliveryDate`  | Goods/services delivery date |
| `purchaseOrder` | Purchase order reference     |

### Financial Data

| Field           | Description                             |
| --------------- | --------------------------------------- |
| `netAmount`     | Pre-tax amount                          |
| `vatAmount`     | VAT/tax amount                          |
| `vatRate`       | VAT percentage                          |
| `totalAmount`   | Total including tax                     |
| `currency`      | ISO currency code (EUR, GBP, USD, etc.) |
| `freightAmount` | Shipping/freight charges                |

### Supplier Details

| Field             | Description                   |
| ----------------- | ----------------------------- |
| `supplierName`    | Company name                  |
| `supplierTaxId`   | VAT/Tax identification number |
| `supplierAddress` | Full address                  |
| `supplierContact` | Email, phone, IBAN, etc.      |

### Line Items

Each line item contains:

```json theme={null}
{
  "description": "Product or service name",
  "quantity": 10,
  "unitPrice": 25.00,
  "amount": 250.00,
  "productCode": "SKU-12345",
  "vatCode": "T1"
}
```

<Info>
  VAT codes are automatically assigned based on the line item's VAT rate and your accounting software. See [VAT Codes](/docs/features/vat-codes) for details.
</Info>

## OCR Providers

VATextract supports multiple OCR engines:

<Tabs>
  <Tab title="Google Document AI">
    **Default provider.** Best for European invoices and complex layouts.

    * Excellent multi-language support
    * Strong table extraction
    * High accuracy on scanned documents
  </Tab>

  <Tab title="AWS Textract">
    **Alternative provider.** Expense Analysis API optimized for invoices.

    * Native invoice field detection
    * Strong for English documents
    * Good line item extraction
  </Tab>
</Tabs>

<Info>
  Configure your preferred OCR provider in Settings → Preferences, or set the `OCR_PROVIDER` environment variable for self-hosted deployments.
</Info>

## Extraction Confidence

Each extracted field includes a confidence score (0-100%). Low-confidence extractions are highlighted in the review interface for manual verification.

## Geometry Data

For advanced integrations, VATextractprovides bounding box coordinates for each extracted field:

```json theme={null}
{
  "fieldName": "TOTAL",
  "text": "$1,250.00",
  "confidence": 98.5,
  "geometry": {
    "boundingBox": {
      "left": 0.72,
      "top": 0.85,
      "width": 0.15,
      "height": 0.02
    },
    "pageNumber": 1
  }
}
```

This enables document overlay highlighting and programmatic field location.