
Ultimate access to all questions.
No comments yet.
Which solution provides scalable semantic search, rich metadata filtering, and tight integration with Amazon Bedrock while minimizing operational overhead for a financial services company building a multilingual RAG application with 10 million document embeddings?
A
Use Amazon OpenSearch Serverless with vector search capabilities. Configure a knowledge base in Amazon Bedrock to manage embeddings and retrieval.
B
Deploy Amazon Aurora PostgreSQL with pgvector extension. Implement custom embedding generation and retrieval logic in the application.
C
Use Amazon DynamoDB with vector embeddings stored as attributes. Implement similarity search using cosine distance calculations in application code.
D
Set up an Amazon Neptune Analytics database with a vector index. Use graph-based retrieval and Amazon Bedrock for response generation.