AWS Certified Generative AI – Professional (AIP-C01) — Question 22

A company provides a service that helps users from around the world discover new restaurants. The service has 50 million monthly active users. The company wants to implement a semantic search solution across a database that contains 20 million restaurants and 200 million reviews. The company currently stores the 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. The solution must maintain data freshness for restaurant details that update hourly. The solution must also scale cost-effectively during peak usage periods.
Which solution will meet these requirements with the LEAST development effort?

Answer options

• A. Migrate the restaurant data to Amazon OpenSearch Service. Implement keyword-based search rules that use custom analyzers and relevance tuning to find restaurants based on attributes such as cuisine type, feature, and location. Create Amazon API Gateway HTTP API endpoints to transform user queries into structured search parameters.
• B. Migrate the restaurant data to Amazon OpenSearch Service. Use a foundation model (FM) in Amazon Bedrock to generate vector embeddings from restaurant descriptions, reviews, and menu items. When users submit natural language queries, convert the queries to embeddings by using the same FM. Perform k-nearest neighbors (k-NN) searches to find semantically similar results.
• C. Keep the restaurant data in PostgresQL and implement a pgvector extension. Use a foundation model (FM) in Amazon Bedrock to generate vector embeddings from restaurant data. Store the vector embeddings directly in PostgreSQL. Create an AWS Lambda function to convert natural language queries to vector representations by using the same FM. Configure the Lambda function to perform similarity searches within the database.
• D. Migrate restaurant data to an Amazon Bedrock knowledge base by using a custom ingestion pipeline. Configure the knowledge base to automatically generate embeddings from restaurant information. Use the Amazon Bedrock Retrieve API with built-in vector search capabilities to query the knowledge base directly by using natural language input.

Correct answer: B

Explanation

Option B is the correct choice because it utilizes Amazon OpenSearch Service and a foundation model to generate vector embeddings, which effectively supports complex natural language queries while ensuring fast response times and scalability. The other options either involve more complexity with custom implementations or do not fully leverage the capabilities of semantic search required under the given constraints.