AWS Certified Generative AI Developer - Professional
Get started today
Ultimate access to all questions.
Ultimate access to all questions.
A financial services company is developing a Retrieval Augmented Generation (RAG) application to help investment analysts query complex financial relationships across multiple investment vehicles, market sectors, and regulatory environments. The dataset contains highly interconnected entities that have multi-hop relationships. Analysts must examine relationships holistically to provide accurate investment guidance. The application must deliver comprehensive answers that capture indirect relationships between financial entities and must respond in less than 3 seconds.
Which solution will meet these requirements with the LEAST operational overhead?
A
Use Amazon Bedrock Knowledge Bases with GraphRAG and Amazon Neptune Analytics to store financial data. Analyze multi-hop relationships between entities and automatically identify related information across documents.
B
Use Amazon Bedrock Knowledge Bases and an Amazon OpenSearch Service vector store to implement custom relationship identification logic that uses AWS Lambda to query multiple vector embeddings in sequence.
C
Use Amazon OpenSearch Serverless vector search with k-nearest neighbor (k-NN). Implement manual relationship mapping in an application layer that runs on Amazon EC2 Auto Scaling.
D
Use Amazon DynamoDB to store financial data in a custom indexing system. Use AWS Lambda to query relevant records. Use Amazon SageMaker to generate responses.
No comments yet.