A historic clock-tower society stores handbook PDFs in object storage and does not want to hand-build chunk, embed, and retrieve plumbing. Which AWS option is the managed RAG path?
Select an answer to reveal the explanation.
Short Explanation
Think of wanting RAG without soldering the pipes yourself. Bedrock Knowledge Bases chunk, embed, and retrieve for you. A blank training cluster, a dashboard, and Polly do not pull passages.
Full Explanation
The historic clock-tower society stores handbook PDFs in object storage and does not want to hand-build chunk, embed, and retrieve plumbing. Amazon Bedrock Knowledge Bases is the managed RAG path that performs those steps so the society can ground answers without assembling a custom retrieval stack. Managed RAG still uses the society’s documents; it simply removes the need to solder chunking, embeddings, and vector query infrastructure by hand.
A blank training cluster the society must assemble itself fails because that is undifferentiated heavy lifting, not a managed RAG offering, and it points the team toward training rather than retrieval. A business-intelligence dashboard with no retrieval step fails because dashboards chart data; they do not retrieve handbook passages into a generative answer flow. Amazon Polly fails because speech synthesis is not managed RAG and does not chunk, embed, or retrieve PDF passages for grounding.
Exam caveat: Bedrock Knowledge Bases is the named managed RAG capability to recognize when a scenario wants retrieval without custom vector plumbing. Operational check: connect the handbook bucket to a Knowledge Base, run a visitor question whose answer exists only in a PDF, and confirm retrieved passages appear in the grounded response without a homemade embed pipeline.