sagemaker deploy async endpoint

deploy-async.py

import boto3

sm_client = boto3.client('sagemaker', region_name='us-east-1')

endpoint_config_name = 'titanic-survival-async-endpoint-config'
print(endpoint_config_name)

create_endpoint_config_response = sm_client.create_endpoint_config(
    EndpointConfigName=endpoint_config_name, # You will specify this name in a CreateEndpoint request.
    # List of ProductionVariant objects, one for each model that you want to host at this endpoint.
    ProductionVariants=[
        {
            "VariantName": "AllTraffic", # The name of the production variant.
            "ModelName": 'titanic-survival-v1',
            "InstanceType": "ml.m5.2xlarge", # Specify the compute instance type.
            "InitialInstanceCount": 1 # Number of instances to launch initially.
        }
    ],
    AsyncInferenceConfig={
        "OutputConfig": {
            # Location to upload response outputs when no location is provided in the request.
            "S3OutputPath": "s3://<your bucket>/sagemaker-async-out",
            # (Optional) specify Amazon SNS topics
            "NotificationConfig": {
                "SuccessTopic": "<sns topic arn>",
                "ErrorTopic": "<sns topic arn>",
            }
        },
        "ClientConfig": {
            "MaxConcurrentInvocationsPerInstance": 1 #increase this value upto throughput peak for best performance
        }
    }
)

endpoint_name = 'titanic-survival-async-endpoint'
print("EndpointName={}".format(endpoint_name))

create_endpoint_response = sm_client.create_endpoint(
    EndpointName=endpoint_name,
    EndpointConfigName=endpoint_config_name)
print(create_endpoint_response['EndpointArn'])