A company is planning to create an internal-only chat interface to help employees handle customer queries. Currently, the employees need to refer to a massive knowledge base of internal documents to…

Question

Options

• ASet up Amazon Bedrock with the Anthropic Claude foundation model.
• BSet up Amazon SageMaker JumpStart with the Llama foundation model.
• CUse Amazon EC2 instances with Amazon API Gateway to invoke the model API.
• DUse AWS Lambda functions with Amazon API Gateway to invoke the model API.
• EUse an Amazon S3 bucket to store vector database dumps and embeddings.
• FUse Amazon RDS for MySQL to store vector database dumps and embeddings.

• A
  80% (20)
• B
  12% (3)
• C
  4% (1)
• F
  4% (1)

Explanation

The solution must be serverless and support a RAG (Retrieval-Augmented Generation) pattern against internal documents. (A) Amazon Bedrock provides fully managed, serverless access to foundation models like Anthropic Claude-no infrastructure to manage. (D) AWS Lambda with Amazon API Gateway is the canonical serverless compute pattern for invoking APIs without managing servers. (E) Amazon S3 is used to store document embeddings and vector data; Amazon Bedrock Knowledge Bases integrates natively with S3 to index documents and perform semantic search. Option B (SageMaker JumpStart) requires managing underlying EC2 instances-not serverless. Option C (EC2 + API Gateway) is explicitly not serverless. Option F (RDS for MySQL) is a relational database with no native vector search capability and requires provisioned infrastructure.

No community discussion yet for this question.