EndpointConfiguration

Provides a SageMaker endpoint configuration resource.

Example Usage

using Pulumi;
using Aws = Pulumi.Aws;

class MyStack : Stack
{
    public MyStack()
    {
        var ec = new Aws.Sagemaker.EndpointConfiguration("ec", new Aws.Sagemaker.EndpointConfigurationArgs
        {
            ProductionVariants = 
            {
                new Aws.Sagemaker.Inputs.EndpointConfigurationProductionVariantArgs
                {
                    InitialInstanceCount = 1,
                    InstanceType = "ml.t2.medium",
                    ModelName = aws_sagemaker_model.M.Name,
                    VariantName = "variant-1",
                },
            },
            Tags = 
            {
                { "Name", "foo" },
            },
        });
    }

}

package main

import (
    "github.com/pulumi/pulumi-aws/sdk/v2/go/aws/sagemaker"
    "github.com/pulumi/pulumi/sdk/v2/go/pulumi"
)

func main() {
    pulumi.Run(func(ctx *pulumi.Context) error {
        _, err := sagemaker.NewEndpointConfiguration(ctx, "ec", &sagemaker.EndpointConfigurationArgs{
            ProductionVariants: sagemaker.EndpointConfigurationProductionVariantArray{
                &sagemaker.EndpointConfigurationProductionVariantArgs{
                    InitialInstanceCount: pulumi.Int(1),
                    InstanceType:         pulumi.String("ml.t2.medium"),
                    ModelName:            pulumi.String(aws_sagemaker_model.M.Name),
                    VariantName:          pulumi.String("variant-1"),
                },
            },
            Tags: pulumi.StringMap{
                "Name": pulumi.String("foo"),
            },
        })
        if err != nil {
            return err
        }
        return nil
    })
}

import pulumi
import pulumi_aws as aws

ec = aws.sagemaker.EndpointConfiguration("ec",
    production_variants=[{
        "initialInstanceCount": 1,
        "instance_type": "ml.t2.medium",
        "modelName": aws_sagemaker_model["m"]["name"],
        "variantName": "variant-1",
    }],
    tags={
        "Name": "foo",
    })

import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const ec = new aws.sagemaker.EndpointConfiguration("ec", {
    productionVariants: [{
        initialInstanceCount: 1,
        instanceType: "ml.t2.medium",
        modelName: aws_sagemaker_model_m.name,
        variantName: "variant-1",
    }],
    tags: {
        Name: "foo",
    },
});

Create a EndpointConfiguration Resource

new EndpointConfiguration(name: string, args: EndpointConfigurationArgs, opts?: CustomResourceOptions);

def EndpointConfiguration(resource_name, opts=None, kms_key_arn=None, name=None, production_variants=None, tags=None, __props__=None);

func NewEndpointConfiguration(ctx *Context, name string, args EndpointConfigurationArgs, opts ...ResourceOption) (*EndpointConfiguration, error)

public EndpointConfiguration(string name, EndpointConfigurationArgs args, CustomResourceOptions? opts = null)

name string: The unique name of the resource.
args EndpointConfigurationArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

resource_name str: The unique name of the resource.
opts ResourceOptions: A bag of options that control this resource's behavior.

ctx Context: Context object for the current deployment.
name string: The unique name of the resource.
args EndpointConfigurationArgs: The arguments to resource properties.
opts ResourceOption: Bag of options to control resource's behavior.

name string: The unique name of the resource.
args EndpointConfigurationArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

EndpointConfiguration Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Programming Model docs.

Inputs

The EndpointConfiguration resource accepts the following input properties:

ProductionVariants List<EndpointConfigurationProductionVariantArgs>: Fields are documented below.
KmsKeyArn string: Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
Name string: The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.
Tags Dictionary<string, string>: A mapping of tags to assign to the resource.

ProductionVariants []EndpointConfigurationProductionVariant: Fields are documented below.
KmsKeyArn string: Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
Name string: The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.
Tags map[string]string: A mapping of tags to assign to the resource.

productionVariants EndpointConfigurationProductionVariant[]: Fields are documented below.
kmsKeyArn string: Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
name string: The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.
tags {[key: string]: string}: A mapping of tags to assign to the resource.

production_variants List[EndpointConfigurationProductionVariant]: Fields are documented below.
kms_key_arn str: Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
name str: The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.
tags Dict[str, str]: A mapping of tags to assign to the resource.

Outputs

All input properties are implicitly available as output properties. Additionally, the EndpointConfiguration resource produces the following output properties:

Arn string: The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
Id string: The provider-assigned unique ID for this managed resource.

Arn string: The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
Id string: The provider-assigned unique ID for this managed resource.

arn string: The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
id string: The provider-assigned unique ID for this managed resource.

arn str: The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
id str: The provider-assigned unique ID for this managed resource.

Look up an Existing EndpointConfiguration Resource

Get an existing EndpointConfiguration resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

public static get(name: string, id: Input<ID>, state?: EndpointConfigurationState, opts?: CustomResourceOptions): EndpointConfiguration

static get(resource_name, id, opts=None, arn=None, kms_key_arn=None, name=None, production_variants=None, tags=None, __props__=None);

func GetEndpointConfiguration(ctx *Context, name string, id IDInput, state *EndpointConfigurationState, opts ...ResourceOption) (*EndpointConfiguration, error)

public static EndpointConfiguration Get(string name, Input<string> id, EndpointConfigurationState? state, CustomResourceOptions? opts = null)

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

resource_name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

The following state arguments are supported:

Arn string: The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
KmsKeyArn string: Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
Name string: The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.
ProductionVariants List<EndpointConfigurationProductionVariantArgs>: Fields are documented below.
Tags Dictionary<string, string>: A mapping of tags to assign to the resource.

Arn string: The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
KmsKeyArn string: Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
Name string: The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.
ProductionVariants []EndpointConfigurationProductionVariant: Fields are documented below.
Tags map[string]string: A mapping of tags to assign to the resource.

arn string: The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
kmsKeyArn string: Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
name string: The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.
productionVariants EndpointConfigurationProductionVariant[]: Fields are documented below.
tags {[key: string]: string}: A mapping of tags to assign to the resource.

arn str: The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
kms_key_arn str: Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
name str: The name of the endpoint configuration. If omitted, this provider will assign a random, unique name.
production_variants List[EndpointConfigurationProductionVariant]: Fields are documented below.
tags Dict[str, str]: A mapping of tags to assign to the resource.

Supporting Types

EndpointConfigurationProductionVariant

See the input and output API doc for this type.

InitialInstanceCount int: Initial number of instances used for auto-scaling.
InstanceType string: The type of instance to start.
ModelName string: The name of the model to use.
AcceleratorType string: The size of the Elastic Inference (EI) instance to use for the production variant.
InitialVariantWeight double: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
VariantName string: The name of the variant. If omitted, this provider will assign a random, unique name.

InitialInstanceCount int: Initial number of instances used for auto-scaling.
InstanceType string: The type of instance to start.
ModelName string: The name of the model to use.
AcceleratorType string: The size of the Elastic Inference (EI) instance to use for the production variant.
InitialVariantWeight float64: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
VariantName string: The name of the variant. If omitted, this provider will assign a random, unique name.

initialInstanceCount number: Initial number of instances used for auto-scaling.
instanceType string: The type of instance to start.
modelName string: The name of the model to use.
acceleratorType string: The size of the Elastic Inference (EI) instance to use for the production variant.
initialVariantWeight number: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
variantName string: The name of the variant. If omitted, this provider will assign a random, unique name.

initialInstanceCount float: Initial number of instances used for auto-scaling.
instance_type str: The type of instance to start.
modelName str: The name of the model to use.
acceleratorType str: The size of the Elastic Inference (EI) instance to use for the production variant.
initialVariantWeight float: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
variantName str: The name of the variant. If omitted, this provider will assign a random, unique name.

Package Details

Repository: https://github.com/pulumi/pulumi-aws
License: Apache-2.0
Notes: This Pulumi package is based on the aws Terraform Provider.

The Pulumi Platform

Get Started

Migrate to Pulumi

Solutions for All Teams and Engineers

Any Code

Any Cloud