POST /generate/from-upload

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.

file

required

PDF or image file (PNG, JPG) to upload.

string

default:"full_picture,folded_skewed,blurry"

Comma-separated list of preset names.

Response

string

Unique identifier for this generation run

object

Schema detected from the uploaded document.

Show child attributes

string

Detected type: dispatch_guide, invoice, purchase_order, bill_of_lading, credit_note, other

object

Detected header fields

array

Detected line items

object

Detected totals (subtotal, tax, total)

number

Detection confidence (0.0 - 1.0)

object

Flattened field_name -> value dict used for verification.

array

Array of verified photo results.

Show child attributes

string

Path to generated photo

boolean

Whether all visible fields match

integer

Number of generation attempts

object

Per-field verification results

object

Occlusion reasons per field

Example

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

Response

{
  "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
    }
  ]
}

​Endpoint

​Request

​Response

​Example

Endpoint

Request

Response

Example