put_external_model

put_external_model(**kwargs)

Creates or updates an Amazon SageMaker model endpoint. You can also use this action to update the configuration of the model endpoint, including the IAM role and/or the mapped variables.

See also: AWS API Documentation

Request Syntax

response = client.put_external_model(
    modelEndpoint='string',
    modelSource='SAGEMAKER',
    invokeModelEndpointRoleArn='string',
    inputConfiguration={
        'eventTypeName': 'string',
        'format': 'TEXT_CSV'|'APPLICATION_JSON',
        'useEventVariables': True|False,
        'jsonInputTemplate': 'string',
        'csvInputTemplate': 'string'
    },
    outputConfiguration={
        'format': 'TEXT_CSV'|'APPLICATION_JSONLINES',
        'jsonKeyToVariableMap': {
            'string': 'string'
        },
        'csvIndexToVariableMap': {
            'string': 'string'
        }
    },
    modelEndpointStatus='ASSOCIATED'|'DISSOCIATED',
    tags=[
        {
            'key': 'string',
            'value': 'string'
        },
    ]
)
Parameters
  • modelEndpoint (string) --

    [REQUIRED]

    The model endpoints name.

  • modelSource (string) --

    [REQUIRED]

    The source of the model.

  • invokeModelEndpointRoleArn (string) --

    [REQUIRED]

    The IAM role used to invoke the model endpoint.

  • inputConfiguration (dict) --

    [REQUIRED]

    The model endpoint input configuration.

    • eventTypeName (string) --

      The event type name.

    • format (string) --

      The format of the model input configuration. The format differs depending on if it is passed through to SageMaker or constructed by Amazon Fraud Detector.

    • useEventVariables (boolean) -- [REQUIRED]

      The event variables.

    • jsonInputTemplate (string) --

      Template for constructing the JSON input-data sent to SageMaker. At event-evaluation, the placeholders for variable names in the template will be replaced with the variable values before being sent to SageMaker.

    • csvInputTemplate (string) --

      Template for constructing the CSV input-data sent to SageMaker. At event-evaluation, the placeholders for variable-names in the template will be replaced with the variable values before being sent to SageMaker.

  • outputConfiguration (dict) --

    [REQUIRED]

    The model endpoint output configuration.

    • format (string) -- [REQUIRED]

      The format of the model output configuration.

    • jsonKeyToVariableMap (dict) --

      A map of JSON keys in response from SageMaker to the Amazon Fraud Detector variables.

      • (string) --
        • (string) --
    • csvIndexToVariableMap (dict) --

      A map of CSV index values in the SageMaker response to the Amazon Fraud Detector variables.

      • (string) --
        • (string) --
  • modelEndpointStatus (string) --

    [REQUIRED]

    The model endpoint’s status in Amazon Fraud Detector.

  • tags (list) --

    A collection of key and value pairs.

    • (dict) --

      A key and value pair.

      • key (string) -- [REQUIRED]

        A tag key.

      • value (string) -- [REQUIRED]

        A value assigned to a tag key.

Return type

dict

Returns

Response Syntax

{}

Response Structure

  • (dict) --

Exceptions

  • FraudDetector.Client.exceptions.ValidationException
  • FraudDetector.Client.exceptions.InternalServerException
  • FraudDetector.Client.exceptions.ThrottlingException
  • FraudDetector.Client.exceptions.AccessDeniedException
  • FraudDetector.Client.exceptions.ConflictException