DescribeEndpointConfig
Returns the description of an endpoint configuration created using the
CreateEndpointConfig API.
Request Syntax
{
"EndpointConfigName": "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.
- EndpointConfigName
-
The name of the endpoint configuration.
Type: String
Length Constraints: Minimum length of 0. Maximum length of 63.
Pattern:
[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}Required: Yes
Response Syntax
{
"AsyncInferenceConfig": {
"ClientConfig": {
"MaxConcurrentInvocationsPerInstance": number
},
"OutputConfig": {
"KmsKeyId": "string",
"NotificationConfig": {
"ErrorTopic": "string",
"IncludeInferenceResponseIn": [ "string" ],
"SuccessTopic": "string"
},
"S3FailurePath": "string",
"S3OutputPath": "string"
}
},
"DataCaptureConfig": {
"CaptureContentTypeHeader": {
"CsvContentTypes": [ "string" ],
"JsonContentTypes": [ "string" ]
},
"CaptureOptions": [
{
"CaptureMode": "string"
}
],
"DestinationS3Uri": "string",
"EnableCapture": boolean,
"InitialSamplingPercentage": number,
"KmsKeyId": "string"
},
"EnableNetworkIsolation": boolean,
"EndpointConfigArn": "string",
"EndpointConfigName": "string",
"ExecutionRoleArn": "string",
"ExplainerConfig": {
"ClarifyExplainerConfig": {
"EnableExplanations": "string",
"InferenceConfig": {
"ContentTemplate": "string",
"FeatureHeaders": [ "string" ],
"FeaturesAttribute": "string",
"FeatureTypes": [ "string" ],
"LabelAttribute": "string",
"LabelHeaders": [ "string" ],
"LabelIndex": number,
"MaxPayloadInMB": number,
"MaxRecordCount": number,
"ProbabilityAttribute": "string",
"ProbabilityIndex": number
},
"ShapConfig": {
"NumberOfSamples": number,
"Seed": number,
"ShapBaselineConfig": {
"MimeType": "string",
"ShapBaseline": "string",
"ShapBaselineUri": "string"
},
"TextConfig": {
"Granularity": "string",
"Language": "string"
},
"UseLogit": boolean
}
}
},
"KmsKeyId": "string",
"MetricsConfig": {
"EnableDetailedObservability": boolean,
"EnableEnhancedMetrics": boolean,
"MetricPublishFrequencyInSeconds": number
},
"ProductionVariants": [
{
"AcceleratorType": "string",
"CapacityReservationConfig": {
"CapacityReservationPreference": "string",
"MlReservationArn": "string"
},
"ContainerStartupHealthCheckTimeoutInSeconds": number,
"CoreDumpConfig": {
"DestinationS3Uri": "string",
"KmsKeyId": "string"
},
"EnableSSMAccess": boolean,
"InferenceAmiVersion": "string",
"InitialInstanceCount": number,
"InitialVariantWeight": number,
"InstancePools": [
{
"InstanceType": "string",
"ModelNameOverride": "string",
"Priority": number
}
],
"InstanceType": "string",
"ManagedInstanceScaling": {
"MaxInstanceCount": number,
"MinInstanceCount": number,
"ScaleInPolicy": {
"CooldownInMinutes": number,
"MaximumStepSize": number,
"Strategy": "string"
},
"Status": "string"
},
"ModelDataDownloadTimeoutInSeconds": number,
"ModelName": "string",
"RoutingConfig": {
"PrefixAwareRoutingConfig": {
"ConcurrencyThreshold": number,
"PrefixLength": number
},
"RoutingStrategy": "string"
},
"ServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"VariantInstanceProvisionTimeoutInSeconds": number,
"VariantName": "string",
"VolumeSizeInGB": number
}
],
"ShadowProductionVariants": [
{
"AcceleratorType": "string",
"CapacityReservationConfig": {
"CapacityReservationPreference": "string",
"MlReservationArn": "string"
},
"ContainerStartupHealthCheckTimeoutInSeconds": number,
"CoreDumpConfig": {
"DestinationS3Uri": "string",
"KmsKeyId": "string"
},
"EnableSSMAccess": boolean,
"InferenceAmiVersion": "string",
"InitialInstanceCount": number,
"InitialVariantWeight": number,
"InstancePools": [
{
"InstanceType": "string",
"ModelNameOverride": "string",
"Priority": number
}
],
"InstanceType": "string",
"ManagedInstanceScaling": {
"MaxInstanceCount": number,
"MinInstanceCount": number,
"ScaleInPolicy": {
"CooldownInMinutes": number,
"MaximumStepSize": number,
"Strategy": "string"
},
"Status": "string"
},
"ModelDataDownloadTimeoutInSeconds": number,
"ModelName": "string",
"RoutingConfig": {
"PrefixAwareRoutingConfig": {
"ConcurrencyThreshold": number,
"PrefixLength": number
},
"RoutingStrategy": "string"
},
"ServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"VariantInstanceProvisionTimeoutInSeconds": number,
"VariantName": "string",
"VolumeSizeInGB": number
}
],
"VpcConfig": {
"SecurityGroupIds": [ "string" ],
"Subnets": [ "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.
- AsyncInferenceConfig
-
Returns the description of an endpoint configuration created using the
CreateEndpointConfigAPI.Type: AsyncInferenceConfig object
- DataCaptureConfig
-
Configuration to control how SageMaker AI captures inference data.
Type: DataCaptureConfig object
- EnableNetworkIsolation
-
Indicates whether all model containers deployed to the endpoint are isolated. If they are, no inbound or outbound network calls can be made to or from the model containers.
Type: Boolean
- EndpointConfigArn
-
The Amazon Resource Name (ARN) of the endpoint configuration.
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-config/.* - EndpointConfigName
-
Name of the SageMaker endpoint configuration.
Type: String
Length Constraints: Minimum length of 0. Maximum length of 63.
Pattern:
[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62} - ExecutionRoleArn
-
The Amazon Resource Name (ARN) of the IAM role that you assigned to the endpoint configuration.
Type: String
Length Constraints: Minimum length of 20. Maximum length of 2048.
Pattern:
arn:aws[a-z\-]*:iam::\d{12}:role/?[a-zA-Z_0-9+=,.@\-_/]+ - ExplainerConfig
-
The configuration parameters for an explainer.
Type: ExplainerConfig object
- KmsKeyId
-
AWS KMS key ID Amazon SageMaker uses to encrypt data when storing it on the ML storage volume attached to the instance.
Type: String
Length Constraints: Minimum length of 0. Maximum length of 2048.
Pattern:
[a-zA-Z0-9:/_-]* - MetricsConfig
-
The configuration parameters for utilization metrics.
Type: MetricsConfig object
- ProductionVariants
-
An array of
ProductionVariantobjects, one for each model that you want to host at this endpoint.Type: Array of ProductionVariant objects
Array Members: Minimum number of 1 item. Maximum number of 10 items.
- ShadowProductionVariants
-
An array of
ProductionVariantobjects, one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified onProductionVariants.Type: Array of ProductionVariant objects
Array Members: Minimum number of 1 item. Maximum number of 10 items.
- VpcConfig