Bedrock feature that implements RAG in a managed way: it ingests documents, converts them into embeddings, indexes them in a vector database, and automatically connects them to a foundation model to enrich its responses with your own context.
In AIF-C01 (Domain 3) it's the recommended way to implement RAG on AWS without building the pipeline manually. Question: give a Bedrock model access to the company's internal documentation with minimal configuration → Knowledge Bases.
Amazon Bedrock Knowledge Bases is a concept that can show up on the exam. Check the full guide to see it in context.