CreateEntityRecognizerRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/amazon-comprehend/json-schema/amazon-comprehend-create-entity-recognizer-request-schema.json",
  "title": "CreateEntityRecognizerRequest",
  "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/CreateEntityRecognizerRequest",
  "type": "object",
  "properties": {
    "RecognizerName": {
      "type": "string",
      "description": "The name given to the newly created recognizer. Recognizer names can be a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The name must be unique in the account/Region."
    },
    "VersionName": {
      "type": "string",
      "description": "The version name given to the newly created recognizer. Version names can be a maximum of 256 characters. Alphanumeric characters, hyphens (-) and underscores (_) are allowed. The version name must be unique among all models with the same recognizer name in the account/Region."
    },
    "DataAccessRoleArn": {
      "type": "string",
      "description": "The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data."
    },
    "Tags": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/Tag"
      },
      "description": "Tags to associate with the entity recognizer. A tag is a key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with \"Sales\" as the key might be added to a resource to indicate its use by the sales department."
    },
    "InputDataConfig": {
      "$ref": "#/$defs/EntityRecognizerInputDataConfig"
    },
    "ClientRequestToken": {
      "type": "string",
      "description": "A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one."
    },
    "LanguageCode": {
      "type": "string",
      "enum": [
        "en",
        "es",
        "fr",
        "de",
        "it",
        "pt",
        "ar",
        "hi",
        "ja",
        "ko",
        "zh",
        "zh-TW"
      ],
      "description": "You can specify any of the following languages: English (\"en\"), Spanish (\"es\"), French (\"fr\"), Italian (\"it\"), German (\"de\"), or Portuguese (\"pt\"). If you plan to use this entity recognizer with PDF, Word, or image input files, you must specify English as the language. All training documents must be in the same language."
    },
    "VolumeKmsKeyId": {
      "type": "string",
      "description": "ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt data on the storage volume attached to the ML compute instance(s) that process the analysis job. The VolumeKmsKeyId can be either of the following formats: KMS Key ID: \"1234abcd-12ab-34cd-56ef-1234567890ab\" Amazon Resource Name (ARN) of a KMS Key: \"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\""
    },
    "VpcConfig": {
      "$ref": "#/$defs/VpcConfig"
    },
    "ModelKmsKeyId": {
      "type": "string",
      "description": "ID for the KMS key that Amazon Comprehend uses to encrypt trained custom models. The ModelKmsKeyId can be either of the following formats: KMS Key ID: \"1234abcd-12ab-34cd-56ef-1234567890ab\" Amazon Resource Name (ARN) of a KMS Key: \"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab\""
    },
    "ModelPolicy": {
      "type": "string",
      "description": "The JSON resource-based policy to attach to your custom entity recognizer model. You can use this policy to allow another Amazon Web Services account to import your custom model. Provide your JSON as a UTF-8 encoded string without line breaks. To provide valid JSON for your policy, enclose the attribute names and values in double quotes. If the JSON body is also enclosed in double quotes, then you must escape the double quotes that are inside the policy: \"{\\\"attribute\\\": \\\"value\\\", \\\"attribute\\\": [\\\"value\\\"]}\" To avoid escaping quotes, you can use single quotes to enclose the policy and double"
    }
  },
  "required": [
    "RecognizerName",
    "DataAccessRoleArn",
    "InputDataConfig",
    "LanguageCode"
  ],
  "$defs": {
    "AugmentedManifestsListItem": {
      "type": "object",
      "properties": {
        "S3Uri": {
          "type": "string",
          "description": "The Amazon S3 location of the augmented manifest file."
        },
        "Split": {
          "type": "string",
          "enum": [
            "TRAIN",
            "TEST"
          ],
          "description": "The purpose of the data you've provided in the augmented manifest. You can either train or test this data. If you don't specify, the default is train. TRAIN - all of the documents in the manifest will be used for training. If no test documents are provided, Amazon Comprehend will automatically reserve a portion of the training documents for testing. TEST - all of the documents in the manifest will be used for testing."
        },
        "AttributeNames": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "The JSON attribute that contains the annotations for your training documents. The number of attribute names that you specify depends on whether your augmented manifest file is the output of a single labeling job or a chained labeling job. If your file is the output of a single labeling job, specify the LabelAttributeName key that was used when the job was created in Ground Truth. If your file is the output of a chained labeling job, specify the LabelAttributeName key for one or more jobs in the chain. Each LabelAttributeName key provides the annotations from an individual job."
        },
        "AnnotationDataS3Uri": {
          "type": "string",
          "description": "The S3 prefix to the annotation files that are referred in the augmented manifest file."
        },
        "SourceDocumentsS3Uri": {
          "type": "string",
          "description": "The S3 prefix to the source files (PDFs) that are referred to in the augmented manifest file."
        },
        "DocumentType": {
          "type": "string",
          "enum": [
            "PLAIN_TEXT_DOCUMENT",
            "SEMI_STRUCTURED_DOCUMENT"
          ],
          "description": "The type of augmented manifest. PlainTextDocument or SemiStructuredDocument. If you don't specify, the default is PlainTextDocument. PLAIN_TEXT_DOCUMENT A document type that represents any unicode text that is encoded in UTF-8. SEMI_STRUCTURED_DOCUMENT A document type with positional and structural context, like a PDF. For training with Amazon Comprehend, only PDFs are supported. For inference, Amazon Comprehend support PDFs, DOCX and TXT."
        }
      },
      "required": [
        "S3Uri",
        "AttributeNames"
      ]
    },
    "EntityRecognizerAnnotations": {
      "type": "object",
      "properties": {
        "S3Uri": {
          "type": "string",
          "description": "Specifies the Amazon S3 location where the annotations for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling."
        },
        "TestS3Uri": {
          "type": "string",
          "description": "Specifies the Amazon S3 location where the test annotations for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling."
        }
      },
      "required": [
        "S3Uri"
      ]
    },
    "EntityRecognizerDocuments": {
      "type": "object",
      "properties": {
        "S3Uri": {
          "type": "string",
          "description": "Specifies the Amazon S3 location where the training documents for an entity recognizer are located. The URI must be in the same Region as the API endpoint that you are calling."
        },
        "TestS3Uri": {
          "type": "string",
          "description": "Specifies the Amazon S3 location where the test documents for an entity recognizer are located. The URI must be in the same Amazon Web Services Region as the API endpoint that you are calling."
        },
        "InputFormat": {
          "type": "string",
          "enum": [
            "ONE_DOC_PER_FILE",
            "ONE_DOC_PER_LINE"
          ],
          "description": "Specifies how the text in an input file should be processed. This is optional, and the default is ONE_DOC_PER_LINE. ONE_DOC_PER_FILE - Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers. ONE_DOC_PER_LINE - Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages."
        }
      },
      "required": [
        "S3Uri"
      ]
    },
    "EntityRecognizerEntityList": {
      "type": "object",
      "properties": {
        "S3Uri": {
          "type": "string",
          "description": "Specifies the Amazon S3 location where the entity list is located. The URI must be in the same Region as the API endpoint that you are calling."
        }
      },
      "required": [
        "S3Uri"
      ]
    },
    "EntityRecognizerInputDataConfig": {
      "type": "object",
      "properties": {
        "DataFormat": {
          "type": "string",
          "enum": [
            "COMPREHEND_CSV",
            "AUGMENTED_MANIFEST"
          ],
          "description": "The format of your training data: COMPREHEND_CSV: A CSV file that supplements your training documents. The CSV file contains information about the custom entities that your trained model will detect. The required format of the file depends on whether you are providing annotations or an entity list. If you use this value, you must provide your CSV file by using either the Annotations or EntityList parameters. You must provide your training documents by using the Documents parameter. AUGMENTED_MANIFEST: A labeled dataset that is produced by Amazon SageMaker Ground Truth. This file is in JSON lin"
        },
        "EntityTypes": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/EntityTypesListItem"
          },
          "description": "The entity types in the labeled training data that Amazon Comprehend uses to train the custom entity recognizer. Any entity types that you don't specify are ignored. A maximum of 25 entity types can be used at one time to train an entity recognizer. Entity types must not contain the following invalid characters: \\n (line break), \\\\n (escaped line break), \\r (carriage return), \\\\r (escaped carriage return), \\t (tab), \\\\t (escaped tab), space, and , (comma)."
        },
        "Documents": {
          "$ref": "#/$defs/EntityRecognizerDocuments"
        },
        "Annotations": {
          "$ref": "#/$defs/EntityRecognizerAnnotations"
        },
        "EntityList": {
          "$ref": "#/$defs/EntityRecognizerEntityList"
        },
        "AugmentedManifests": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/AugmentedManifestsListItem"
          },
          "description": "A list of augmented manifest files that provide training data for your custom model. An augmented manifest file is a labeled dataset that is produced by Amazon SageMaker Ground Truth. This parameter is required if you set DataFormat to AUGMENTED_MANIFEST."
        }
      },
      "required": [
        "EntityTypes"
      ]
    },
    "EntityTypesListItem": {
      "type": "object",
      "properties": {
        "Type": {
          "type": "string",
          "description": "An entity type within a labeled training dataset that Amazon Comprehend uses to train a custom entity recognizer. Entity types must not contain the following invalid characters: \\n (line break), \\\\n (escaped line break, \\r (carriage return), \\\\r (escaped carriage return), \\t (tab), \\\\t (escaped tab), and , (comma)."
        }
      },
      "required": [
        "Type"
      ]
    },
    "Tag": {
      "type": "object",
      "properties": {
        "Key": {
          "type": "string",
          "description": "The initial part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the key portion of the pair, with multiple possible values such as “sales,” “legal,” and “administration.”"
        },
        "Value": {
          "type": "string",
          "description": "The second part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the initial (key) portion of the pair, with a value of “sales” to indicate the sales department."
        }
      },
      "required": [
        "Key"
      ]
    },
    "VpcConfig": {
      "type": "object",
      "properties": {
        "SecurityGroupIds": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "The ID number for a security group on an instance of your private VPC. Security groups on your VPC function serve as a virtual firewall to control inbound and outbound traffic and provides security for the resources that you’ll be accessing on the VPC. This ID number is preceded by \"sg-\", for instance: \"sg-03b388029b0a285ea\". For more information, see Security Groups for your VPC."
        },
        "Subnets": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "The ID for each subnet being used in your private VPC. This subnet is a subset of the a range of IPv4 addresses used by the VPC and is specific to a given availability zone in the VPC’s Region. This ID number is preceded by \"subnet-\", for instance: \"subnet-04ccf456919e69055\". For more information, see VPCs and Subnets."
        }
      },
      "required": [
        "SecurityGroupIds",
        "Subnets"
      ]
    }
  }
}