QuestionQ19

VerifiedDeployment and Orchestration of ML Workflows

A company is building an internal cost-estimation tool that uses an ML model in Amazon SageMaker AI. Users upload high-resolution images to the tool.

The model must process every image and predict the cost of the object shown in the image. The model must also notify the user when processing has finished.

Which solution meets these requirements?

Explanation

Amazon SageMaker AI Asynchronous Inference uses Amazon S3 for request payloads and processes inference requests asynchronously. Its endpoint configuration can specify Amazon SNS success and error topics, allowing users to be notified when processing completes.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!