aws-cdk-lib.aws_sagemaker.CfnModelProps

CfnModelProps Struct

Properties for defining a CfnModel.

CfnModelProps

used as props by

• CfnModel

Source

Generated code

Type last changed

v2.114.0 · 5 Dec 2023

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_sagemaker as sagemaker } from 'aws-cdk-lib';

declare const environment: any;
const cfnModelProps: sagemaker.CfnModelProps = {
  containers: [{
    containerHostname: 'containerHostname',
    environment: environment,
    image: 'image',
    imageConfig: {
      repositoryAccessMode: 'repositoryAccessMode',

      // the properties below are optional
      repositoryAuthConfig: {
        repositoryCredentialsProviderArn: 'repositoryCredentialsProviderArn',
      },
    },
    inferenceSpecificationName: 'inferenceSpecificationName',
    mode: 'mode',
    modelDataSource: {
      s3DataSource: {
        compressionType: 'compressionType',
        s3DataType: 's3DataType',
        s3Uri: 's3Uri',

        // the properties below are optional
        hubAccessConfig: {
          hubContentArn: 'hubContentArn',
        },
        modelAccessConfig: {
          acceptEula: false,
        },
      },
    },
    modelDataUrl: 'modelDataUrl',
    modelPackageName: 'modelPackageName',
    multiModelConfig: {
      modelCacheSetting: 'modelCacheSetting',
    },
  }],
  enableNetworkIsolation: false,
  executionRoleArn: 'executionRoleArn',
  inferenceExecutionConfig: {
    mode: 'mode',
  },
  modelName: 'modelName',
  primaryContainer: {
    containerHostname: 'containerHostname',
    environment: environment,
    image: 'image',
    imageConfig: {
      repositoryAccessMode: 'repositoryAccessMode',

      // the properties below are optional
      repositoryAuthConfig: {
        repositoryCredentialsProviderArn: 'repositoryCredentialsProviderArn',
      },
    },
    inferenceSpecificationName: 'inferenceSpecificationName',
    mode: 'mode',
    modelDataSource: {
      s3DataSource: {
        compressionType: 'compressionType',
        s3DataType: 's3DataType',
        s3Uri: 's3Uri',

        // the properties below are optional
        hubAccessConfig: {
          hubContentArn: 'hubContentArn',
        },
        modelAccessConfig: {
          acceptEula: false,
        },
      },
    },
    modelDataUrl: 'modelDataUrl',
    modelPackageName: 'modelPackageName',
    multiModelConfig: {
      modelCacheSetting: 'modelCacheSetting',
    },
  },
  tags: [{
    key: 'key',
    value: 'value',
  }],
  vpcConfig: {
    securityGroupIds: ['securityGroupIds'],
    subnets: ['subnets'],
  },
};

Properties

containers?optionalIResolvable | IResolvable | CfnModel.ContainerDefinitionProperty[]containers?optionaltyping.Union[IResolvable, typing.List[typing.Union[IResolvable, ContainerDefinitionProperty]]]containers?optionalIResolvableContainers?optionalIResolvableContainers?optionalinterface{}#

Specifies the containers in the inference pipeline.

enableNetworkIsolation?optionalboolean | IResolvableenable_network_isolation?optionaltyping.Union[bool, IResolvable]enableNetworkIsolation?optionalBooleanEnableNetworkIsolation?optionalboolEnableNetworkIsolation?optionalinterface{}#

Isolates the model container.

No inbound or outbound network calls can be made to or from the model container.

executionRoleArn?optionalstringexecution_role_arn?optionalstrexecutionRoleArn?optionalStringExecutionRoleArn?optionalstringExecutionRoleArn?optional*string#

The Amazon Resource Name (ARN) of the IAM role that SageMaker can assume to access model artifacts and docker image for deployment on ML compute instances or for batch transform jobs.

notes

Deploying on ML compute instances is part of model hosting. For more information, see SageMaker Roles .

To be able to pass this role to SageMaker, the caller of this API must have the iam:PassRole permission.

inferenceExecutionConfig?optionalIResolvable | CfnModel.InferenceExecutionConfigPropertyinference_execution_config?optionaltyping.Union[IResolvable, InferenceExecutionConfigProperty]inferenceExecutionConfig?optionalIResolvableInferenceExecutionConfig?optionalIResolvableInferenceExecutionConfig?optionalinterface{}#

Specifies details of how containers in a multi-container endpoint are called.

modelName?optionalstringmodel_name?optionalstrmodelName?optionalStringModelName?optionalstringModelName?optional*string#

The name of the new model.

primaryContainer?optionalIResolvable | CfnModel.ContainerDefinitionPropertyprimary_container?optionaltyping.Union[IResolvable, ContainerDefinitionProperty]primaryContainer?optionalIResolvablePrimaryContainer?optionalIResolvablePrimaryContainer?optionalinterface{}#

The location 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.

tags?optionalCfnTag[]tags?optionaltyping.List[CfnTag]tags?optionalList<CfnTag>Tags?optionalCfnTag[]Tags?optional*[]CfnTag#

A list of key-value pairs to apply to this resource.

notes

For more information, see Resource Tag and Using Cost Allocation Tags in the AWS Billing and Cost Management User Guide .

vpcConfig?optionalIResolvable | CfnModel.VpcConfigPropertyvpc_config?optionaltyping.Union[IResolvable, VpcConfigProperty]vpcConfig?optionalIResolvableVpcConfig?optionalIResolvableVpcConfig?optionalinterface{}#

A [VpcConfig](https://docs.aws.amazon.com/sagemaker/latest/dg/API_VpcConfig.html) object that specifies the VPC that you want your model to connect to. Control access to and from your model container by configuring the VPC. `VpcConfig` is used in hosting services and in batch transform. For more information, see [Protect Endpoints by Using an Amazon Virtual Private Cloud](https://docs.aws.amazon.com/sagemaker/latest/dg/host-vpc.html) and [Protect Data in Batch Transform Jobs by Using an Amazon Virtual Private Cloud](https://docs.aws.amazon.com/sagemaker/latest/dg/batch-vpc.html) .