A financial services company is using Amazon Bedrock to generate investment summaries. They want to ensure that the model outputs are factually accurate and based on the latest market data. Which combination of services should they use to achieve this? (Select TWO)
Trap 1: Amazon SageMaker Ground Truth for data labeling
Ground Truth is for creating labeled datasets, not for retrieval-augmented generation.
Trap 2: Amazon DynamoDB as the knowledge base store
DynamoDB is a key-value and document database, not designed for vector similarity search.
Trap 3: Amazon Kendra for indexing the knowledge base
Kendra is a search service but not the vector store used directly by Bedrock Knowledge Bases.
- A
Amazon SageMaker Ground Truth for data labeling
Why wrong: Ground Truth is for creating labeled datasets, not for retrieval-augmented generation.
- B
Amazon DynamoDB as the knowledge base store
Why wrong: DynamoDB is a key-value and document database, not designed for vector similarity search.
- C
Amazon Kendra for indexing the knowledge base
Why wrong: Kendra is a search service but not the vector store used directly by Bedrock Knowledge Bases.
- D
Amazon Aurora with the pgvector extension
Aurora with pgvector can store and query embeddings for RAG.
- E
Amazon Bedrock Knowledge Bases with RAG
RAG retrieves relevant, up-to-date information from a knowledge base.