AWS Amazon SageMaker Endpoint Configuration
This page shows how to write Terraform and CloudFormation for Amazon SageMaker Endpoint Configuration and write them securely.
aws_sagemaker_endpoint_configuration (Terraform)
The Endpoint Configuration in Amazon SageMaker can be configured in Terraform with the resource name aws_sagemaker_endpoint_configuration
. The following sections describe 5 examples of how to use the resource and its parameters.
Example Usage from GitHub
resource "aws_sagemaker_endpoint_configuration" "invalid" {
name = "my-endpoint-config"
production_variants {
variant_name = "variant-1"
model_name = "name"
resource "aws_sagemaker_endpoint_configuration" "kms_key_arn_is_set" {
kms_key_arn = aws_kms_key.test_key.arn
production_variants {
model_name = aws_sagemaker_model.test_model.name
initial_instance_count = 1
resource "aws_sagemaker_endpoint_configuration" "kms_key_arn_is_set" {
kms_key_arn = aws_kms_key.test_key.arn
production_variants {
model_name = aws_sagemaker_model.test_model.name
initial_instance_count = 1
resource "aws_sagemaker_endpoint_configuration" "examplea" {
name = "my-endpoint-config"
kms_key_arn = aws_kms_key.examplea.arn
production_variants {
variant_name = "variant-1"
resource "aws_sagemaker_endpoint_configuration" "this" {
name = "rs-model-a-Staging"
production_variants {
model_name = aws_sagemaker_model.this.name
initial_instance_count = 1
Parameters
-
arn
optional computed - string -
id
optional computed - string -
kms_key_arn
optional - string -
name
optional computed - string -
tags
optional - map from string to string -
data_capture_config
list block-
destination_s3_uri
required - string -
enable_capture
optional - bool -
initial_sampling_percentage
required - number -
kms_key_id
optional - string -
capture_content_type_header
list block-
csv_content_types
optional - set of string -
json_content_types
optional - set of string
-
-
capture_options
list block-
capture_mode
required - string
-
-
-
production_variants
list block-
accelerator_type
optional - string -
initial_instance_count
required - number -
initial_variant_weight
optional - number -
instance_type
required - string -
model_name
required - string -
variant_name
optional computed - string
-
Explanation in Terraform Registry
Provides a SageMaker endpoint configuration resource.
AWS::SageMaker::EndpointConfig (CloudFormation)
The EndpointConfig in SageMaker can be configured in CloudFormation with the resource name AWS::SageMaker::EndpointConfig
. The following sections describe how to use the resource and its parameters.
Example Usage from GitHub
An example could not be found in GitHub.
Parameters
-
DataCaptureConfig
optional - DataCaptureConfig -
ProductionVariants
required - List of ProductionVariant -
KmsKeyId
optional - String -
AsyncInferenceConfig
optional - AsyncInferenceConfig -
EndpointConfigName
optional - String -
Tags
optional - List of Tag
Explanation in CloudFormation Registry
The
AWS::SageMaker::EndpointConfig
resource creates a configuration for an Amazon SageMaker endpoint. For more information, see CreateEndpointConfig in the SageMaker Developer Guide.
Frequently asked questions
What is AWS Amazon SageMaker Endpoint Configuration?
AWS Amazon SageMaker Endpoint Configuration is a resource for Amazon SageMaker of Amazon Web Service. Settings can be wrote in Terraform and CloudFormation.
Where can I find the example code for the AWS Amazon SageMaker Endpoint Configuration?
For Terraform, the Cigna/confectionery, ffsclyh/config-lint and stelligent/config-lint source code examples are useful. See the Terraform Example section for further details.