QuestionQ80

VerifiedDeployment and Orchestration of ML Workflows

An ML engineer must build an AI assistant using Retrieval Augmented Generation (RAG) in Amazon Bedrock. The company keeps a collection of PDF text files in an Amazon S3 bucket. The ML engineer needs to create an Amazon Bedrock knowledge base that processes the PDF files and stores the processed files in a vector store.

Which solution satisfies these requirements?

Explanation

Amazon Bedrock Knowledge Bases require an embedding model to transform ingested document text into vector embeddings for storage and retrieval in a vector store. Cohere Embed Multilingual is a supported Amazon Bedrock embedding model, whereas the listed Titan, Mistral, and Claude alternatives are not the appropriate document-embedding choice.

Learn more

Community Discussion

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