Designing RAG chunks | AWS Certified AI Practitioner (AIF-C01) original practice question

3.1Standard

Policies must be split before indexing.

Preserve context while controlling cost.

Choose two designs.

Hint 1: Focus on the requirement

Identify what must change and what must remain unchanged. Then choose the command whose scope matches that requirement.

Hint 2: Check each command's role

Separate commands that display information, change state, remove data, or affect a child process.

見出し・段落・表など意味のまとまりを保ち、適切なサイズで分割する: Results retain context.
境界で情報が切れないよう小さな重複を試し、検索品質とトークン費用を測る: Boundary loss and cost can be compared.
全資料を一つの巨大チャンクにする: Granularity and limits suffer.
分割サイズを固定し、文書形式や質問の長さを評価しない: The design may not fit.

Detailed explanation

CorrectPreserve headings, paragraphs, and tables in appropriately sized chunks

Results retain context.

CorrectTest a small overlap and measure retrieval quality and token cost

Boundary loss and cost can be compared.

IncorrectPut the entire corpus in one giant chunk

Granularity and limits suffer.

IncorrectUse one fixed size without testing formats or question length

The design may not fit.

An example you can run in a temporary verification environment.

AWS公式AIF-C01 Domain 3.1のRAG、チャンク、埋め込み、検索を確認する。

文書構造と検索品質・費用を考慮してチャンク分割を調整できる。

Foundation review

Check whether the command acts on the current shell, a new process, an existing process, or a file.

Use the supplied command and compare the output with the expected result.

Question IDAWS-AIF-420

EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認

Last technical review2026-08-20