MLREL-01: Use APIs to abstract change from model consuming applications

Adopt best practices in use of APIs -Expose your ML endpoints through APIs so that changes to the model can be introduced without disrupting upstream communications. Document your API in a central repository or documentation site so that any calling services can easily understand your API routes and flags. Ensure that any changes to your API are communicated with any calling services.

Deploy a model in Amazon SageMaker AI- After you train your model, you can deploy it using Amazon SageMaker AI to get predictions. To establish a persistent endpoint to get one prediction at a time, use SageMaker AI hosting services. To get predictions for an entire dataset, use SageMaker AI batch transform.

Use Amazon API Gateway to create APIs - Amazon API Gateway is a fully managed service that enables developers to create, publish, maintain, monitor, and secure APIs. Using API Gateway, you can create RESTful APIs and WebSocket APIs that enable real-time two-way communication applications. API Gateway supports containerized and serverless workloads, as well as web applications.

Deploy a Model in Amazon SageMaker AI

What is Amazon API Gateway?

API Gateway Pattern

Build a serverless frontend for an Amazon SageMaker AI endpoint

Creating a machine learning-powered REST API with Amazon API Gateway mapping templates and Amazon SageMaker AI

Deploying machine learning models with serverless templates

Deploy Your ML Models to Production at Scale with Amazon SageMaker AI

AWS Solutions Constructs aws-apigateway-sagemaker endpoint

AWS MLOps Framework

Amazon SageMaker AI Safe Deployment Pipeline

Amazon SageMaker AI Inference Client Application