1.3Standard
Search FAQ answers by meaning rather than exact wording.
Handle paraphrased questions.
Choose two correct statements.
× Incorrect
Embeddings map text or images to vectors and similarity ranks candidates, but similarity does not establish factuality, authorization, or reversibility.
Detailed explanation
IncorrectAn embedding always reconstructs the original document
A vector is not reversible encryption.
CorrectEmbeddings convert text or images into vectors representing features or meaning
Different wording can be compared.
CorrectUse cosine or another similarity measure to rank questions and candidates
The result supports semantic search.
IncorrectHigh similarity guarantees facts and access rights
Similarity and correctness or authorization are separate.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.3・3.2とAmazon Bedrock埋め込みの説明を確認する。
Official references
What to confirm
意味類似検索の仕組みと、認可・根拠確認が別に必要な理由を説明できる。
Key points
- Vector
- Cosine similarity
- Separate authorization
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
A numeric vector representation intended to capture useful semantic or feature relationships.
Cosine similarity
A measure of the angle-based similarity between two vectors.
Question IDAWS-AIF-236
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