2.1Standard
Compare vector-search storage and quality.
Select an embedding specification for requirements.
Choose two appropriate considerations.
× Incorrect
Measure dimension, retrieval quality, storage, and latency, and use the same model and preprocessing for queries and documents.
Detailed explanation
IncorrectMix vectors from a new model with old vectors without versioning
Distances may no longer be meaningful.
CorrectMeasure dimension, search quality, storage, and latency
A larger dimension is not automatically the best trade-off.
IncorrectMore dimensions guarantee correct retrieval
Data, model, queries, and evaluation also matter.
CorrectUse the same embedding model and preprocessing for queries and documents
Vectors must share a comparable space.
Check official documentation
Compare the following points with the official documentation.
Amazon Bedrock Knowledge Bases公式の埋め込み仕様とAIF-C01 Domain 2.1を確認する。
Official references
What to confirm
ベクトル次元と検索品質・コストの関係を説明できる。
Key points
- Dimensions
- Vector space
- Re-embedding
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
Embedding dimension
The number of numeric components used to represent an item as a vector.
Embedding version
An identifier for the model and preprocessing that produced a vector representation.
Question IDAWS-AIF-157
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