Documents are added, changed, and deleted.
Do not retrieve stale vectors.
Choose two practices.
Link source versions to vector versions, process update and delete events, detect failures, and quarantine or stop use of stale versions.
Detailed explanation
Freshness and auditability are lost.
Changes reach the index.
Deleted data can remain retrievable.
Silent staleness is avoided.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 3.2のベクトル索引、データ更新、監視を確認する。
Official references
What to confirm
原本変更とベクトル索引の整合性を保ち、更新失敗を検知できる。
Key points
- Index update
- Version link
- Deletion
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 index
A search structure that stores embeddings for nearest-neighbor retrieval.
Version linkage
Metadata connecting a derived vector or index entry to its source revision.