Query an Amazon Bedrock Knowledge Base with RetrieveAndGenerate for grounded RAG responses

Steps

1. Create a Bedrock Agent Runtime client: client = boto3.client('bedrock-agent-runtime')
2. Call client.retrieve_and_generate(input={'text': query}, retrieveAndGenerateConfiguration={...}) with a knowledgeBaseId and modelArn
3. On the first call, no sessionId is needed — Bedrock returns one in the response; pass it in all subsequent calls in the same conversation session
4. Use client.retrieve() separately if you want only the source chunks without model generation — it returns an array of retrieval results
5. Tune the number of retrieved results via the retrievalConfiguration numberOfResults field to control context window usage
6. Inspect the citations field in the response to surface source document links in your UI