3.2Standard
Search FAQs by product code and natural language.
Tune keyword and vector contributions.
Choose two appropriate evaluations.
× Incorrect
Use exact-match, paraphrase, short, and long query sets and measure recall, top precision, latency, and cost after weighting.
Detailed explanation
IncorrectFix weights from one query
Input types can behave differently.
IncorrectTreat a semantically similar result as exact code equality
Vector similarity does not guarantee string equality.
CorrectCreate queries for exact codes, paraphrases, short questions, and long questions
The strengths of each search signal can be compared.
CorrectMeasure candidate recall, top precision, latency, and cost after tuning
Ranking quality and operations are both evaluated.
Check official documentation
Compare the following points with the official documentation.
Amazon Bedrock Knowledge Bases公式のハイブリッド検索とAIF-C01 Domain 3.2を確認する。
Official references
What to confirm
キーワード・ベクトル双方の検索性能をクエリ群で評価できる。
Key points
- Query set
- Recall
- Precision
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
Candidate recall
The share of relevant documents that enter the retrieval candidate set.
Top-k precision
The share of relevant documents among the first k results shown or passed downstream.
Question IDAWS-AIF-182
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