AWS Certified Generative AI Developer - Professional AIP-C01

By Amazon · Question Mode

QuestionQ50

Implementation and Integration

A financial services company is developing a Retrieval Augmented Generation (RAG) application that uses Amazon Bedrock to produce summaries of market activities. The application depends on a vector database that stores a small proprietary dataset with a low index count. The application must run similarity searches, and the Amazon Bedrock model responses must maximize accuracy while maintaining high performance.

The company needs to configure the vector database and integrate it with the application.

Which solution meets these requirements?

Explanation

MemoryDB's FLAT vector index performs a brute-force linear comparison of every vector and returns exact nearest-neighbor results within distance-calculation precision. For a small index, this preserves maximum retrieval accuracy without the large-index latency disadvantage of exhaustive search. HNSW and IVFFlat are approximate indexing methods that can improve speed by accepting possible recall loss.

Learn more

Community Discussion

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