3.1Standard
Pass the top k search results to generation.
Compare relevant-document retrieval.
Choose two practices.
× Incorrect
Compute Recall@k against known relevant documents and also measure ranking, evidence accuracy, latency, cost, and authorization.
Detailed explanation
CorrectCompare known relevant documents with the top k results to compute Recall@k
Misses become measurable.
IncorrectCompute an average without defining relevant documents
The metric has no clear meaning.
CorrectAlso evaluate ranking, evidence accuracy, latency, cost, and authorization
Search-to-generation impact is covered.
IncorrectHigh Recall@k guarantees correct top evidence
Ranking and content need separate checks.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 3.1の検索評価、Recall@k、RAG品質を確認する。
Official references
What to confirm
検索の取りこぼしと上位根拠の品質を分けて測定できる。
Key points
- Recall@k
- Relevant document
- Ranking
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Recall@k
The share of known relevant results present among the first k retrieved items.
Ranking quality
The extent to which more relevant evidence appears near the top of results.
Question IDAWS-AIF-398
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
Report an error or rights issue