The definition of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
AWS Step Functions integrates with services directly in the Amazon States Language.
You can control these AWS services using service integration patterns.
Depending on the AWS Service, the Service Integration Pattern availability will vary.
Default: - `IntegrationPattern.REQUEST_RESPONSE` for most tasks.
`IntegrationPattern.RUN_JOB` for the following exceptions:
`BatchSubmitJob`, `EmrAddStep`, `EmrCreateCluster`, `EmrTerminationCluster`, and `EmrContainersStartJobRun`.
Parameters:
integrationPattern - AWS Step Functions integrates with services directly in the Amazon States Language. This parameter is required.
The JSON that will replace the state's raw result and become the effective result before ResultPath is applied.
You can use ResultSelector to create a payload with values that are static
or selected from the state's raw result.
Default: - None
Parameters:
resultSelector - The JSON that will replace the state's raw result and become the effective result before ResultPath is applied. This parameter is required.
The definition of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
Parameters:
primaryContainer - The definition of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions. This parameter is required.
The subnets of the VPC to which the hosted model is connected (Note this parameter is only used when VPC is provided).
Default: - Private Subnets are selected
Parameters:
subnetSelection - The subnets of the VPC to which the hosted model is connected (Note this parameter is only used when VPC is provided). This parameter is required.
heartbeatTimeout