DetectEntitiesRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/amazon-comprehend/json-schema/amazon-comprehend-detect-entities-request-schema.json",
  "title": "DetectEntitiesRequest",
  "x-generated": "2026-11-11",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/amazon-comprehend-amazon-comprehend-api-openapi.yml#/components/schemas/DetectEntitiesRequest",
  "type": "object",
  "properties": {
    "Text": {
      "type": "string",
      "description": "A UTF-8 text string. The maximum string size is 100 KB. If you enter text using this parameter, do not use the Bytes parameter."
    },
    "LanguageCode": {
      "type": "string",
      "enum": [
        "en",
        "es",
        "fr",
        "de",
        "it",
        "pt",
        "ar",
        "hi",
        "ja",
        "ko",
        "zh",
        "zh-TW"
      ],
      "description": "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. All input documents must be in the same language."
    },
    "EndpointArn": {
      "type": "string",
      "description": "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. 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. For information about endpoints, see Managing endpoints."
    },
    "Bytes": {
      "type": "string",
      "format": "byte",
      "description": "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 Text field. Use the Bytes parameter to input a text, PDF, Word or image file. Using a plain-text file in the Bytes parameter is equivelent to using the Text parameter (the Entities field in the response is identical). You can also use the Bytes parameter to input an Amazon Textract DetectDocumentText or AnalyzeDocument output file. Provide the input document as a sequence of base64-encoded bytes. If your code uses an Amazon Web Services SDK"
    },
    "DocumentReaderConfig": {
      "$ref": "#/$defs/DocumentReaderConfig"
    }
  },
  "$defs": {
    "DocumentReaderConfig": {
      "type": "object",
      "properties": {
        "DocumentReadAction": {
          "type": "string",
          "enum": [
            "TEXTRACT_DETECT_DOCUMENT_TEXT",
            "TEXTRACT_ANALYZE_DOCUMENT"
          ],
          "description": "This field defines the Amazon Textract API operation that Amazon Comprehend uses to extract text from PDF files and image files. Enter one of the following values: TEXTRACT_DETECT_DOCUMENT_TEXT - The Amazon Comprehend service uses the DetectDocumentText API operation. TEXTRACT_ANALYZE_DOCUMENT - The Amazon Comprehend service uses the AnalyzeDocument API operation."
        },
        "DocumentReadMode": {
          "type": "string",
          "enum": [
            "SERVICE_DEFAULT",
            "FORCE_DOCUMENT_READ_ACTION"
          ],
          "description": "Determines the text extraction actions for PDF files. Enter one of the following values: SERVICE_DEFAULT - use the Amazon Comprehend service defaults for PDF files. FORCE_DOCUMENT_READ_ACTION - Amazon Comprehend uses the Textract API specified by DocumentReadAction for all PDF files, including digital PDF files."
        },
        "FeatureTypes": {
          "type": "array",
          "items": {
            "type": "string",
            "enum": [
              "TABLES",
              "FORMS"
            ]
          },
          "description": "Specifies the type of Amazon Textract features to apply. If you chose TEXTRACT_ANALYZE_DOCUMENT as the read action, you must specify one or both of the following values: TABLES - Returns additional information about any tables that are detected in the input document. FORMS - Returns additional information about any forms that are detected in the input document."
        }
      },
      "required": [
        "DocumentReadAction"
      ]
    }
  }
}