pulumi-aws-kotlin/com.pulumi.aws.sagemaker.kotlin/ModelArgs

ModelArgs

data class ModelArgs(val containers: Output<List<ModelContainerArgs>>? = null, val enableNetworkIsolation: Output<Boolean>? = null, val executionRoleArn: Output<String>? = null, val inferenceExecutionConfig: Output<ModelInferenceExecutionConfigArgs>? = null, val name: Output<String>? = null, val primaryContainer: Output<ModelPrimaryContainerArgs>? = null, val tags: Output<Map<String, String>>? = null, val vpcConfig: Output<ModelVpcConfigArgs>? = null) : ConvertibleToJava<ModelArgs>

Provides a SageMaker model resource.

Example Usage

Basic usage:

package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.iam.IamFunctions;
import com.pulumi.aws.iam.inputs.GetPolicyDocumentArgs;
import com.pulumi.aws.iam.Role;
import com.pulumi.aws.iam.RoleArgs;
import com.pulumi.aws.sagemaker.SagemakerFunctions;
import com.pulumi.aws.sagemaker.inputs.GetPrebuiltEcrImageArgs;
import com.pulumi.aws.sagemaker.Model;
import com.pulumi.aws.sagemaker.ModelArgs;
import com.pulumi.aws.sagemaker.inputs.ModelPrimaryContainerArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }
    public static void stack(Context ctx) {
        final var assumeRole = IamFunctions.getPolicyDocument(GetPolicyDocumentArgs.builder()
            .statements(GetPolicyDocumentStatementArgs.builder()
                .actions("sts:AssumeRole")
                .principals(GetPolicyDocumentStatementPrincipalArgs.builder()
                    .type("Service")
                    .identifiers("sagemaker.amazonaws.com")
                    .build())
                .build())
            .build());
        var exampleRole = new Role("exampleRole", RoleArgs.builder()
            .assumeRolePolicy(assumeRole.applyValue(getPolicyDocumentResult -> getPolicyDocumentResult.json()))
            .build());
        final var test = SagemakerFunctions.getPrebuiltEcrImage(GetPrebuiltEcrImageArgs.builder()
            .repositoryName("kmeans")
            .build());
        var exampleModel = new Model("exampleModel", ModelArgs.builder()
            .executionRoleArn(exampleRole.arn())
            .primaryContainer(ModelPrimaryContainerArgs.builder()
                .image(test.applyValue(getPrebuiltEcrImageResult -> getPrebuiltEcrImageResult.registryPath()))
                .build())
            .build());
    }
}

Inference Execution Config

mode - (Required) How containers in a multi-container are run. The following values are valid Serial and Direct.

Import

Models can be imported using the name, e.g.,

$ pulumi import aws:sagemaker/model:Model test_model model-foo

Constructors

ModelArgs

fun ModelArgs(containers: Output<List<ModelContainerArgs>>? = null, enableNetworkIsolation: Output<Boolean>? = null, executionRoleArn: Output<String>? = null, inferenceExecutionConfig: Output<ModelInferenceExecutionConfigArgs>? = null, name: Output<String>? = null, primaryContainer: Output<ModelPrimaryContainerArgs>? = null, tags: Output<Map<String, String>>? = null, vpcConfig: Output<ModelVpcConfigArgs>? = null)

Functions

toJava

open override fun toJava(): ModelArgs

Properties

containers

val containers: Output<List<ModelContainerArgs>>? = null

Specifies containers in the inference pipeline. If not specified, the primary_container argument is required. Fields are documented below.

enableNetworkIsolation

val enableNetworkIsolation: Output<Boolean>? = null

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

executionRoleArn

val executionRoleArn: Output<String>? = null

A role that SageMaker can assume to access model artifacts and docker images for deployment.

inferenceExecutionConfig

val inferenceExecutionConfig: Output<ModelInferenceExecutionConfigArgs>? = null

Specifies details of how containers in a multi-container endpoint are called. see Inference Execution Config.

name

val name: Output<String>? = null

The name of the model (must be unique). If omitted, this provider will assign a random, unique name.

primaryContainer

val primaryContainer: Output<ModelPrimaryContainerArgs>? = null

The primary docker image containing inference code that is used when the model is deployed for predictions. If not specified, the container argument is required. Fields are documented below.