A community concert band wants one search index that can do keyword lookup and nearest-neighbor embedding search over program notes. Which AWS store fits that job?

Amazon OpenSearch Service is the store that can host one index for both classical keyword retrieval and nearest-neighbor embedding search over the concert band's program notes. Keyword fields support exact and lexical lookups (titles, dates, conductor names), while k-NN vector fields and hybrid query patterns let staff find notes that are semantically close even when the wording differs. That dual capability is why OpenSearch fits a single-index design instead of bolting unrelated products together.

Amazon Polly synthesizes speech from text; it is not a searchable vector or keyword index, so it cannot answer 'find similar program notes.' Amazon QuickSight (often shortened conversationally to Quick in dashboards) visualizes metrics—it does not store embeddings or run nearest-neighbor retrieval over narrative program text. A paper card catalog has no embedding space, no hybrid query API, and no operational path to keep notes synchronized with a living digital archive.

Exam caveat: OpenSearch is appropriate when you need search semantics (lexical, vector, or hybrid) inside one managed search domain; it is not automatically the right answer for pure relational reporting or for graph traversals of crew and vessel relationships.

Operational check: confirm the domain has both text fields mapped for analyzers and a k-NN vector field sized to your embedding model, then run a hybrid query on a known program-note pair and verify that keyword and vector hits both surface before promoting the index to the band's public helper.