Module hybrid 

Hybrid search combining vector similarity and full-text search

Provides a unified search experience by combining:

• Vector similarity scores (cosine, euclidean, dot product)
• Full-text BM25 scores

Two fusion strategies are supported:

• RRF (default): Reciprocal Rank Fusion — score(d) = Σ 1/(k + rank_r(d)), k=60
• MinMax: weighted linear combination of min-max normalised scores

Structs

HybridConfig

Configuration for hybrid search

HybridResult

Result of hybrid search

HybridSearcher

Hybrid search engine that combines vector and text search

Functions

adaptive_vector_weight

Return an adaptive vector_weight (0.0–1.0) for a HybridSearcher based on the inferred [QueryKind].