serverless_endpoint.py

# Setup clients
import boto3

client = boto3.client(service_name="sagemaker")
runtime = boto3.client(service_name="sagemaker-runtime")

# Endpoint Configuration Creation
from time import gmtime, strftime
model_name="imba-image-classifier"
classifier_epc_name = "classifier-serverless-epc" + strftime("%Y-%m-%d-%H-%M-%S", gmtime())

endpoint_config_response = client.create_endpoint_config(
    EndpointConfigName=classifier_epc_name,
    ProductionVariants=[
        {
            "VariantName": "byoVariant",
            "ModelName": model_name,
            "ServerlessConfig": {
                "MemorySizeInMB": 4096,
                "MaxConcurrency": 1,
            },
        },
    ],
)

print("Endpoint Configuration Arn: " + endpoint_config_response["EndpointConfigArn"])
print("Endpoint config Name:", "", classifier_epc_name)

# Serverless Endpoint Creation

endpoint_name = "classifier-serverless-ep" + strftime("%Y-%m-%d-%H-%M-%S", gmtime())
print("Endpoint Name:", "", endpoint_name)
create_endpoint_response = client.create_endpoint(
    EndpointName=endpoint_name,
    EndpointConfigName=classifier_epc_name,
)

print("Endpoint Arn: " + create_endpoint_response["EndpointArn"])

# wait for endpoint to reach a terminal state (InService) using describe endpoint
import time

describe_endpoint_response = client.describe_endpoint(EndpointName=endpoint_name)

while describe_endpoint_response["EndpointStatus"] == "Creating":
    describe_endpoint_response = client.describe_endpoint(EndpointName=endpoint_name)
    print(describe_endpoint_response["EndpointStatus"])
    time.sleep(15)

describe_endpoint_response