3.1Standard
Compare search quality and index cost.
Candidate embedding models have different dimensions.
Choose two comparisons.
× Incorrect
Measure retrieval quality on the same queries and compare dimensions, storage, latency, updates, cost, and language performance.
Detailed explanation
IncorrectChoose the smallest vector without measuring quality
Relevance may be lost.
CorrectInclude storage, latency, update cost, and language quality
Operational fit is part of selection.
IncorrectLarger vectors are always more accurate
Quality depends on model and data.
CorrectMeasure recall and ranking quality with the same documents and queries
Semantic quality is comparable.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 3.1の埋め込みと検索設計を確認する。
Official references
What to confirm
ベクトル次元を品質とコストのトレードオフで選べる。
Key points
- Dimensions
- Retrieval
- Storage
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
Vector dimension
The number of numeric components in an embedding vector.
Retrieval recall
The proportion of relevant candidates returned by a retrieval process.
Question IDAWS-AIF-326
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