Module diversifier 

Maximal Marginal Relevance (MMR) diversification for semantic search results.

This module implements the MMR algorithm which selects top-k results that balance relevance to the query with diversity among the selected items. The trade-off is controlled by a lambda parameter: 1.0 = pure relevance, 0.0 = pure diversity.

Structs

DiversificationCandidate

A single candidate for diversified selection.

DiversifiedResult

A single result from the diversified selection process.

DiversifierConfig

Configuration for the MMR diversification algorithm.

DiversifierStats

Aggregate statistics across all select calls made on a SemanticDiversifier instance.

SemanticDiversifier

Diversifies a ranked list of candidates using Maximal Marginal Relevance.

Functions

cosine_similarity

Cosine similarity between two vectors.