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

# POST /generate/from-upload

> Upload a PDF or image, auto-detect schema, and generate verified photo variations.

## Endpoint

```
POST /generate/from-upload
```

Upload an existing document (PDF or image), detect its schema using vision AI, and generate verified photo variations.

## Request

This endpoint uses `multipart/form-data`.

<ParamField body="file" type="file" required>
  PDF or image file (PNG, JPG) to upload.
</ParamField>

<ParamField query="presets" type="string" default="full_picture,folded_skewed,blurry">
  Comma-separated list of preset names.
</ParamField>

## Response

<ResponseField name="run_id" type="string">
  Unique identifier for this generation run
</ResponseField>

<ResponseField name="detected_schema" type="object">
  Schema detected from the uploaded document.

  <Expandable>
    <ResponseField name="document_type" type="string">
      Detected type: `dispatch_guide`, `invoice`, `purchase_order`, `bill_of_lading`, `credit_note`, `other`
    </ResponseField>

    <ResponseField name="header" type="object">
      Detected header fields
    </ResponseField>

    <ResponseField name="items" type="array">
      Detected line items
    </ResponseField>

    <ResponseField name="totals" type="object">
      Detected totals (subtotal, tax, total)
    </ResponseField>

    <ResponseField name="confidence" type="number">
      Detection confidence (0.0 - 1.0)
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="ground_truth" type="object">
  Flattened field\_name -> value dict used for verification.
</ResponseField>

<ResponseField name="photos" type="array">
  Array of verified photo results.

  <Expandable>
    <ResponseField name="image_path" type="string">Path to generated photo</ResponseField>
    <ResponseField name="verified" type="boolean">Whether all visible fields match</ResponseField>
    <ResponseField name="attempts" type="integer">Number of generation attempts</ResponseField>
    <ResponseField name="verification" type="object">Per-field verification results</ResponseField>
    <ResponseField name="occlusion_manifest" type="object">Occlusion reasons per field</ResponseField>
  </Expandable>
</ResponseField>

## Example

```bash theme={null}
curl -X POST http://localhost:8000/generate/from-upload \
  -F "file=@/path/to/invoice.pdf" \
  -F "presets=full_picture,blurry"
```

```json Response theme={null}
{
  "run_id": "h8i9j0k1l2",
  "detected_schema": {
    "document_type": "dispatch_guide",
    "header": {
      "doc_number": "00098765",
      "emitter_name": "ACME FOODS S.A."
    },
    "items": [
      {"pos": 1, "description": "HARINA DE TRIGO", "qty": 40, "unit": "UN"}
    ],
    "totals": {"subtotal": 500000, "tax": 95000, "total": 595000},
    "confidence": 0.93
  },
  "ground_truth": {
    "doc_number": "00098765",
    "emitter_name": "ACME FOODS S.A.",
    "item_1_description": "HARINA DE TRIGO",
    "item_1_qty": "40",
    "subtotal": "500000",
    "total": "595000"
  },
  "photos": [
    {
      "image_path": "output/h8i9j0k1l2/photo_full_picture.png",
      "verified": true,
      "attempts": 1
    }
  ]
}
```