pulumi-aws-kotlin/com.pulumi.aws.sagemaker.kotlin.inputs/ModelContainerArgs

ModelContainerArgs

data class ModelContainerArgs(val containerHostname: Output<String>? = null, val environment: Output<Map<String, String>>? = null, val image: Output<String>? = null, val imageConfig: Output<ModelContainerImageConfigArgs>? = null, val inferenceSpecificationName: Output<String>? = null, val mode: Output<String>? = null, val modelDataSource: Output<ModelContainerModelDataSourceArgs>? = null, val modelDataUrl: Output<String>? = null, val modelPackageName: Output<String>? = null, val multiModelConfig: Output<ModelContainerMultiModelConfigArgs>? = null) : ConvertibleToJava<ModelContainerArgs>

Constructors

ModelContainerArgs

constructor(containerHostname: Output<String>? = null, environment: Output<Map<String, String>>? = null, image: Output<String>? = null, imageConfig: Output<ModelContainerImageConfigArgs>? = null, inferenceSpecificationName: Output<String>? = null, mode: Output<String>? = null, modelDataSource: Output<ModelContainerModelDataSourceArgs>? = null, modelDataUrl: Output<String>? = null, modelPackageName: Output<String>? = null, multiModelConfig: Output<ModelContainerMultiModelConfigArgs>? = null)

Properties

containerHostname

val containerHostname: Output<String>? = null

The DNS host name for the container.

environment

val environment: Output<Map<String, String>>? = null

Environment variables for the Docker container. A list of key value pairs.

image

val image: Output<String>? = null

The registry path where the inference code image is stored in Amazon ECR.

imageConfig

val imageConfig: Output<ModelContainerImageConfigArgs>? = null

Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For more information see Using a Private Docker Registry for Real-Time Inference Containers. see Image Config.

inferenceSpecificationName

val inferenceSpecificationName: Output<String>? = null

The inference specification name in the model package version.

mode

val mode: Output<String>? = null

The container hosts value SingleModel/MultiModel. The default value is SingleModel.

modelDataSource

val modelDataSource: Output<ModelContainerModelDataSourceArgs>? = null

The location of model data to deploy. Use this for uncompressed model deployment. For information about how to deploy an uncompressed model, see Deploying uncompressed models in the AWS SageMaker AI Developer Guide.

modelDataUrl

val modelDataUrl: Output<String>? = null

The URL for the S3 location where model artifacts are stored.

modelPackageName

val modelPackageName: Output<String>? = null

The Amazon Resource Name (ARN) of the model package to use to create the model.

multiModelConfig

val multiModelConfig: Output<ModelContainerMultiModelConfigArgs>? = null

Specifies additional configuration for multi-model endpoints. see Multi Model Config.

Functions

toJava

open override fun toJava(): ModelContainerArgs