A recipe site wants one query to match exact ingredient names and also find recipes whose embeddings are close to a shopper's free-form description. Which query mode should the developer use?
Show answer and explanation
Answer: D
Hybrid search runs a keyword query and a vector query in one request, then merges the ranked results using reciprocal rank fusion. The exact ingredient names benefit from lexical matching, while the free-form description benefits from vector similarity. Autocomplete suggests completions for partial input, faceting counts field values, and knowledge store persists enrichment, so none of them combine both retrieval styles.
Why the other options are wrong
- A. Autocomplete proposes completions for partial input as the user types. It does not run embedding similarity across recipe content.
- B. Faceted navigation groups and counts field values for refinement. It does not perform vector similarity matching on a free-form description.
- C. A knowledge store saves enriched outputs to storage for analysis. It does not run queries against the index to return ranked recipes.