OCR

Ocr

post

Extracts text from files using OCR.

Authorizations

AuthorizationstringRequired

Bearer authentication header of the form Bearer <token>.

Body

documentany ofRequired

Document to run OCR on.

or

document_annotation_promptstring · nullableOptional

Optional prompt to guide the model in extracting structured output from the entire document. A document_annotation_format must be provided.

extract_footerbooleanOptional

Whether to extract the footer of the document.

Default: false

extract_headerbooleanOptional

Whether to extract the header of the document.

Default: false

image_limitinteger · nullableOptional

Max images to extract

image_min_sizeinteger · nullableOptional

Minimum height and width of image to extract

include_image_base64boolean · nullableOptional

Include image URLs in response

modelstring · nullableOptional

The model to use for the OCR.

pagesinteger[] · nullableOptional

Specific pages to process. Accepts a list of integers or a string of comma-separated numbers and ranges (e.g. '0,1,2' or '0-5' or '0,2-4'). Page numbers start from 0.

table_formatstring · enum · nullableOptional

Format for table extraction: 'markdown' (default) or 'html'.

Possible values:

Other propertiesanyOptional

Responses

200

Successful Response

application/json

modelstringRequired

document_annotationany of · nullableOptionalDefault: ~?~unset~?~sentinel~?~

stringOptional

or

nullOptional

or

object · UnsetOptional

idstringRequired

The ID of the OCR request.

404

Model not found.

application/json

422

Wrong model type.

application/json

503

Model is too busy, please try again later.

application/json

post/v1/ocr

POST /v1/ocr HTTP/1.1
Host: albert.api.etalab.gouv.fr
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 815

{
  "bbox_annotation_format": {
    "type": "text",
    "json_schema": {
      "name": "text",
      "schema": {
        "ANY_ADDITIONAL_PROPERTY": "anything"
      },
      "strict": false,
      "description": "text",
      "ANY_ADDITIONAL_PROPERTY": "anything"
    },
    "ANY_ADDITIONAL_PROPERTY": "anything"
  },
  "document": {
    "document_name": "text",
    "document_url": "text",
    "type": "document_url",
    "ANY_ADDITIONAL_PROPERTY": "anything"
  },
  "document_annotation_format": {
    "type": "text",
    "json_schema": {
      "name": "text",
      "schema": {
        "ANY_ADDITIONAL_PROPERTY": "anything"
      },
      "strict": false,
      "description": "text",
      "ANY_ADDITIONAL_PROPERTY": "anything"
    },
    "ANY_ADDITIONAL_PROPERTY": "anything"
  },
  "document_annotation_prompt": "text",
  "extract_footer": false,
  "extract_header": false,
  "image_limit": 1,
  "image_min_size": 1,
  "include_image_base64": true,
  "model": "text",
  "pages": [
    1
  ],
  "table_format": "markdown",
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

{
  "pages": [
    {
      "index": 1,
      "markdown": "text",
      "images": [
        {
          "id": "text",
          "top_left_x": 1,
          "top_left_y": 1,
          "bottom_right_x": 1,
          "bottom_right_y": 1,
          "image_base64": "~?~unset~?~sentinel~?~",
          "image_annotation": "~?~unset~?~sentinel~?~"
        }
      ],
      "dimensions": {
        "dpi": 1,
        "height": 1,
        "width": 1
      },
      "tables": [
        {
          "id": "text",
          "content": "text",
          "format": "markdown"
        }
      ],
      "hyperlinks": [
        "text"
      ],
      "header": "~?~unset~?~sentinel~?~",
      "footer": "~?~unset~?~sentinel~?~"
    }
  ],
  "model": "text",
  "usage_info": {
    "pages_processed": 1,
    "doc_size_bytes": "~?~unset~?~sentinel~?~"
  },
  "document_annotation": "~?~unset~?~sentinel~?~",
  "id": "text",
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0,
    "cost": 0,
    "impacts": {
      "kWh": 0,
      "kgCO2eq": 0,
      "ANY_ADDITIONAL_PROPERTY": "anything"
    },
    "requests": 0,
    "ANY_ADDITIONAL_PROPERTY": "anything"
  }
}