Request Syntax Request Parameters Response Syntax Response Elements Errors See Also

StopInferenceExperiment

Stops an inference experiment.

Request Syntax


{
   "DesiredModelVariants": [ 
      { 
         "InfrastructureConfig": { 
            "InfrastructureType": "string",
            "RealTimeInferenceConfig": { 
               "InstanceCount": number,
               "InstanceType": "string"
            }
         },
         "ModelName": "string",
         "VariantName": "string"
      }
   ],
   "DesiredState": "string",
   "ModelVariantActions": { 
      "string" : "string" 
   },
   "Name": "string",
   "Reason": "string"
}

Request Parameters

For information about the parameters that are common to all actions, see Common Parameters.

The request accepts the following data in JSON format.

DesiredModelVariants

An array of ModelVariantConfig objects. There is one for each variant that you want to deploy after the inference experiment stops. Each ModelVariantConfig describes the infrastructure configuration for deploying the corresponding variant.

Type: Array of ModelVariantConfig objects

Array Members: Minimum number of 1 item. Maximum number of 2 items.

Required: No

DesiredState

The desired state of the experiment after stopping. The possible states are the following:

Completed: The experiment completed successfully
Cancelled: The experiment was canceled

Type: String

Valid Values: Completed | Cancelled

Required: No

ModelVariantActions

Array of key-value pairs, with names of variants mapped to actions. The possible actions are the following:

Promote - Promote the shadow variant to a production variant
Remove - Delete the variant
Retain - Keep the variant as it is

Type: String to string map

Map Entries: Maximum number of 2 items.

Key Length Constraints: Maximum length of 63.

Key Pattern: ^[a-zA-Z0-9]([\-a-zA-Z0-9]*[a-zA-Z0-9])?

Valid Values: Retain | Remove | Promote

Required: Yes

Name

The name of the inference experiment to stop.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 120.

Pattern: ^[a-zA-Z0-9](-*[a-zA-Z0-9]){0,119}

Required: Yes

Reason

The reason for stopping the experiment.

Type: String

Length Constraints: Maximum length of 1024.

Pattern: .*

Required: No

Response Syntax


{
   "InferenceExperimentArn": "string"
}

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

InferenceExperimentArn

The ARN of the stopped inference experiment.

Type: String

Length Constraints: Maximum length of 256.

Pattern: arn:aws[a-z\-]*:sagemaker:[a-z0-9\-]*:[0-9]{12}:inference-experiment/.*

Errors

For information about the errors that are common to all actions, see Common Errors.

ConflictException

There was a conflict when you attempted to modify a SageMaker entity such as an Experiment or Artifact.

HTTP Status Code: 400

ResourceNotFound

Resource being access is not found.

HTTP Status Code: 400