DescribeInferenceComponent
Returns information about an inference component.
Request Syntax
{
"InferenceComponentName": "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.
- InferenceComponentName
-
The name of the inference component.
Type: String
Length Constraints: Minimum length of 0. Maximum length of 63.
Pattern:
[a-zA-Z0-9]([\-a-zA-Z0-9]*[a-zA-Z0-9])?Required: Yes
Response Syntax
{
"CreationTime": number,
"EndpointArn": "string",
"EndpointName": "string",
"FailureReason": "string",
"InferenceComponentArn": "string",
"InferenceComponentName": "string",
"InferenceComponentStatus": "string",
"LastDeploymentConfig": {
"AutoRollbackConfiguration": {
"Alarms": [
{
"AlarmName": "string"
}
]
},
"RollingUpdatePolicy": {
"MaximumBatchSize": {
"Type": "string",
"Value": number
},
"MaximumExecutionTimeoutInSeconds": number,
"RollbackMaximumBatchSize": {
"Type": "string",
"Value": number
},
"WaitIntervalInSeconds": number
}
},
"LastModifiedTime": number,
"RuntimeConfig": {
"CurrentCopyCount": number,
"DesiredCopyCount": number
},
"Specification": {
"BaseInferenceComponentName": "string",
"ComputeResourceRequirements": {
"MaxMemoryRequiredInMb": number,
"MinMemoryRequiredInMb": number,
"NumberOfAcceleratorDevicesRequired": number,
"NumberOfCpuCoresRequired": number
},
"Container": {
"ArtifactUrl": "string",
"DeployedImage": {
"ResolutionTime": number,
"ResolvedImage": "string",
"SpecifiedImage": "string"
},
"Environment": {
"string" : "string"
}
},
"DataCacheConfig": {
"EnableCaching": boolean
},
"ModelName": "string",
"StartupParameters": {
"ContainerStartupHealthCheckTimeoutInSeconds": number,
"ModelDataDownloadTimeoutInSeconds": number
}
},
"VariantName": "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.
- CreationTime
-
The time when the inference component was created.
Type: Timestamp
- EndpointArn
-
The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
Type: String
Length Constraints: Minimum length of 20. Maximum length of 2048.
Pattern:
arn:aws[a-z\-]*:sagemaker:[a-z0-9\-]*:[0-9]{12}:endpoint/.* - EndpointName
-
The name of the endpoint that hosts the inference component.
Type: String
Length Constraints: Minimum length of 0. Maximum length of 63.
Pattern:
[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62} - FailureReason
-
If the inference component status is
Failed, the reason for the failure.Type: String
Length Constraints: Minimum length of 0. Maximum length of 1024.
- InferenceComponentArn
-
The Amazon Resource Name (ARN) of the inference component.
Type: String
Length Constraints: Minimum length of 20. Maximum length of 2048.
- InferenceComponentName
-
The name of the inference component.
Type: String
Length Constraints: Minimum length of 0. Maximum length of 63.
Pattern:
[a-zA-Z0-9]([\-a-zA-Z0-9]*[a-zA-Z0-9])? - InferenceComponentStatus
-
The status of the inference component.
Type: String
Valid Values:
InService | Creating | Updating | Failed | Deleting - LastDeploymentConfig
-
The deployment and rollback settings that you assigned to the inference component.
Type: InferenceComponentDeploymentConfig object
- LastModifiedTime
-
The time when the inference component was last updated.
Type: Timestamp
- RuntimeConfig
-
Details about the runtime settings for the model that is deployed with the inference component.
Type: InferenceComponentRuntimeConfigSummary object
- Specification
-
Details about the resources that are deployed with this inference component.
Type: InferenceComponentSpecificationSummary object
- VariantName
-
The name of the production variant that hosts the inference component.
Type: String
Length Constraints: Minimum length of 0. Maximum length of 63.
Pattern:
[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}
Errors
For information about the errors that are common to all actions, see Common Errors.
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
