QuestionQ65

VerifiedOperational Efficiency and Optimization for GenAI Applications

A company offers a service that helps users worldwide discover new restaurants. The service has 50 million monthly active users. The company plans to implement a semantic search solution over a database containing 20 million restaurants and 200 million reviews. The company currently stores this data in a PostgresQL database.

The solution must support complex natural-language queries and return results for at least 95% of queries within 500 ms. It must preserve data freshness for restaurant details that are updated hourly. The solution must also scale cost-effectively during periods of peak usage.

Which solution meets these requirements with the LEAST development effort?

Explanation

Amazon Bedrock Knowledge Bases is a managed retrieval service that ingests source content, automatically converts it into vector embeddings, stores those embeddings in a configured vector store, and retrieves relevant content through the Retrieve API using natural-language input. A custom data source can ingest or update documents directly, supporting hourly restaurant-detail refreshes. This avoids building the separate embedding pipeline, query-embedding logic, and similarity-search implementation required by self-managed OpenSearch or pgvector designs. Amazon Bedrock documentation: https://docs.aws.amazon.com/bedrock/latest/userguide/kb-how-data.html

Learn more

Community Discussion

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