Help an AI answer from your own documents — Bedrock Knowledge Bases and S3 and OpenSearch Serverless

Your goal

Configure a knowledge base and connect a practice document bucket.

Why this matters

An AI knowledge base needs a defined document source and storage configuration. You will connect those API records using a practice S3 document. The lab does not generate embeddings, retrieve passages, or produce an answer.

Words you will use

A knowledge base describes source data and its storage setup. A data source points to documents. Vector storage holds numeric representations used for retrieval. This lab connects records without creating those representations.

How to proceed

Start a fresh emulator, read each numbered step, and enter the practice settings shown. Run the action, inspect its API receipt, then continue. Finish lab checks the emulator state again before saving your progress.

1. Create the source bucket and storage configuration

Create a private S3 bucket, a practice document, and a vector collection configuration. These are API resources; this lab will not compute real embeddings or generate an AI answer.

2. Connect the knowledge source

Create a vector knowledge-base configuration, then attach the practice S3 bucket as its data source. Inspect the returned knowledge-base and data-source IDs.

3. Inspect the connected source

Read the data-source configuration and verify the bucket ARN. This proves the source connection was saved. Ingestion, retrieval quality, access checks, and answer quality need separate testing.

Practice, then check your understanding

Perform the actions yourself and inspect the returned state. Errors keep your settings so you can retry. Starting another lab clears the previous live environment. Earned XP is kept, and signed-in achievements sync to your account. Replay does not award duplicate XP.

Read the official AWS documentation for service behavior and production details.