3.1Standard
Search millions of embeddings with low latency.
Manage differences from exact search.
Choose two decisions.
× Incorrect
Compare recall, p95 latency, index build, update rate, and memory, and test misses against exact search for important queries.
Detailed explanation
IncorrectChoose by latency only
Quality and update cost are ignored.
IncorrectApproximate search always returns the exact same results
Speed involves a recall trade-off.
CorrectCompare recall, p95 latency, index build, updates, and memory
Speed and retrieval loss are measured.
CorrectTest differences and missed evidence against exact search for critical queries
Impact of approximation is known.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 3.1のベクトル検索、スケーラビリティ、評価を確認する。
Official references
What to confirm
近似検索の速度・容量と再現率・取りこぼしを比較できる。
Key points
- ANN
- Recall
- Latency
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
Approximate nearest-neighbor search
A vector search method that trades some exactness for faster retrieval.
Recall loss
Relevant candidates missed because a retrieval method is approximate or filtered.
Question IDAWS-AIF-378
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