A company wants to build and operate a proprietary generative AI application using foundation models. Which AWS fully managed service allows the company to access foundation models from multiple providers through a single API?
A question asking to select the service for building generative AI applications with foundation models.
Amazon Bedrock
This is correct. Amazon Bedrock is a fully managed service that enables customers to build generative AI applications by accessing foundation models from multiple providers through a single API. It requires no infrastructure management and supports customization with proprietary data, including RAG (Retrieval-Augmented Generation).
Amazon Rekognition
Amazon Rekognition is an AI service for image and video analysis.
It is not a platform for building generative AI applications with foundation models, so this is incorrect.
Amazon Polly
Amazon Polly is a text-to-speech service.
It is not a service for building generative AI applications with foundation models, so this is incorrect.
Amazon SageMaker
Amazon SageMaker is an ML platform for building, training, and deploying custom machine learning models from scratch.
It is a service for building models from the ground up. For the requirement of immediately accessing foundation models from multiple providers through a single API, Bedrock is more appropriate. This is incorrect.
'Foundation models,' 'build generative AI,' and 'single API' all point to Amazon Bedrock. If a ready-made generative AI assistant is needed, use Amazon Q. If custom models need to be built and trained from scratch, use SageMaker. Distinguish: foundation (Bedrock) vs. assistant (Q) vs. custom build (SageMaker).