AWS Certified Generative AI Developer - Professional
Get started today
Ultimate access to all questions.
Ultimate access to all questions.
No comments yet.
A university is building a search system for digitized academic papers. The system must allow researchers to find papers by semantic similarity of abstracts, not just keyword matching. The digitized files have no keywords or tags in their metadata, so the system must be able to match abstracts based on similarity of meaning. The university wants to minimize operational overhead. The system will have fewer than 1 million digitized files. Which solution will meet these requirements with the LEAST operational overhead?
A
Use Amazon SageMaker AI to deploy a sentence-transformer model endpoint. Use the endpoint to create vector embeddings for each digitized file. Store the embeddings in an Amazon OpenSearch Service domain that has the k-NN plugin enabled.
B
Use Amazon Comprehend to extract topics from the digitized files. Store the topics as metadata in an Amazon OpenSearch Service domain. Use the OpenSearch Service domain to search for papers by topic.
C
Use Amazon SageMaker AI to deploy a sentence-transformer model endpoint. Use the endpoint to create vector embeddings for each digitized file. Store the embeddings in an Amazon Aurora PostgreSQL Serverless database that has the pgvector extension.
D
Use Amazon Titan Embeddings in Amazon Bedrock to create vector representations of the digitized files. Store embeddings in an Amazon Aurora PostgreSQL Serverless database that has the pgvector extension.