Question

A financial services company wants to build a chatbot that answers employee questions using their internal policy documents stored in Amazon S3. The team wants to minimize infrastructure management and avoid building a custom pipeline for chunking documents, generating embeddings, and storing them in a vector database. Which Amazon Bedrock capability best fits this need?

Accepted Answer

Amazon Bedrock Knowledge Bases, which manages document ingestion, chunking, embedding generation, and vector storage for retrieval-augmented workflows

Answer

Amazon Bedrock model fine-tuning to embed all policy documents directly into the foundation model's weights

Answer

Amazon Bedrock Guardrails to filter and store the policy documents as approved responses

Answer

Amazon Bedrock provisioned throughput to reserve dedicated capacity for storing document embeddings