AWS Certified Generative AI Developer - Professional AIP-C01

By Amazon · Question Mode

QuestionQ55

Operational Efficiency and Optimization for GenAI Applications

A financial services company is developing a customer support application that retrieves relevant financial-regulation documents from a database according to semantic similarity with user queries. The application must integrate with Amazon Bedrock to generate responses. It must be able to search documents in English, Spanish, and Portuguese, and filter documents by metadata such as publication date, regulatory agency, and document type.

The database holds approximately 10 million document embeddings. To reduce operational overhead, the company needs a solution that minimizes management and maintenance work. The application must deliver low-latency responses for real-time customer interactions.

Which solution meets these requirements?

Explanation

Amazon OpenSearch Serverless supports vector search and metadata filtering, and Amazon Bedrock Knowledge Bases provides a managed retrieval-augmented generation workflow that can use an OpenSearch Serverless vector store. OpenSearch Serverless automatically handles capacity scaling, cluster sizing and tuning, software updates, and index lifecycle management, making it suitable for a large, low-latency vector-search workload with minimal operational maintenance. A multilingual embedding model can be used for the English, Spanish, and Portuguese content.

Learn more

Community Discussion

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