DetectEntitiesRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/amazon-comprehend/refs/heads/main/json-schema/openapi.yml-detect-entities-request-schema.json",
  "title": "DetectEntitiesRequest",
  "description": "DetectEntitiesRequest schema",
  "type": "object",
  "properties": {
    "Text": {
      "allOf": [
        {
          "$ref": "#/components/schemas/CustomerInputString"
        },
        {
          "description": "A UTF-8 text string. The maximum string size is 100 KB. If you enter text using this parameter, do not use the <code>Bytes</code> parameter."
        }
      ]
    },
    "LanguageCode": {
      "allOf": [
        {
          "$ref": "#/components/schemas/LanguageCode"
        },
        {
          "description": "<p>The language of the input documents. You can specify any of the primary languages supported by Amazon Comprehend. If your request includes the endpoint for a custom entity recognition model, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you specify here.</p> <p>All input documents must be in the same language.</p>"
        }
      ]
    },
    "EndpointArn": {
      "allOf": [
        {
          "$ref": "#/components/schemas/EntityRecognizerEndpointArn"
        },
        {
          "description": "<p>The Amazon Resource Name of an endpoint that is associated with a custom entity recognition model. Provide an endpoint if you want to detect entities by using your own custom model instead of the default model that is used by Amazon Comprehend.</p> <p>If you specify an endpoint, Amazon Comprehend uses the language of your custom model, and it ignores any language code that you provide in your request.</p> <p>For information about endpoints, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html\">Managing endpoints</a>.</p>"
        }
      ]
    },
    "Bytes": {
      "allOf": [
        {
          "$ref": "#/components/schemas/SemiStructuredDocumentBlob"
        },
        {
          "description": "<p>This field applies only when you use a custom entity recognition model that was trained with PDF annotations. For other cases, enter your text input in the <code>Text</code> field.</p> <p> Use the <code>Bytes</code> parameter to input a text, PDF, Word or image file. Using a plain-text file in the <code>Bytes</code> parameter is equivelent to using the <code>Text</code> parameter (the <code>Entities</code> field in the response is identical).</p> <p>You can also use the <code>Bytes</code> parameter to input an Amazon Textract <code>DetectDocumentText</code> or <code>AnalyzeDocument</code> output file.</p> <p>Provide the input document as a sequence of base64-encoded bytes. If your code uses an Amazon Web Services SDK to detect entities, the SDK may encode the document file bytes for you. </p> <p>The maximum length of this field depends on the input document type. For details, see <a href=\"https://docs.aws.amazon.com/comprehend/latest/dg/idp-inputs-sync.html\"> Inputs for real-time custom analysis</a> in the Comprehend Developer Guide. </p> <p>If you use the <code>Bytes</code> parameter, do not use the <code>Text</code> parameter.</p>"
        }
      ]
    },
    "DocumentReaderConfig": {
      "allOf": [
        {
          "$ref": "#/components/schemas/DocumentReaderConfig"
        },
        {
          "description": "Provides configuration parameters to override the default actions for extracting text from PDF documents and image files."
        }
      ]
    }
  }
}