MLREL-01: Use APIs to abstract change from model consuming applications
Use a flexible application and API design to abstract change from model consuming applications. Ensure that changes to an ML model are introduced with minimal or no interruption to existing workload capabilities. Minimize the changes across other downstream applications.
Implementation plan
-
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- After you train your model, you can deploy it using Amazon
SageMaker to get predictions. To establish a persistent endpoint to get one prediction at a time, use SageMaker hosting services. To get predictions for an entire dataset, use SageMaker 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.
Documents
Blogs
Videos
Examples
