mmr_rerank: Maximal Marginal Relevance (MMR) reranking

In VectrixDB: Lightweight Vector Database with Embedded Machine Learning Models

Maximal Marginal Relevance (MMR) reranking

Description

Maximal Marginal Relevance (MMR) reranking

Usage

mmr_rerank(
  query_vector,
  doc_vectors,
  doc_ids,
  scores,
  lambda = 0.7,
  limit = 10
)

Arguments

query_vector	Query embedding
doc_vectors	Matrix of document embeddings
doc_ids	Vector of document IDs
scores	Initial relevance scores
lambda	Diversity parameter (0-1)
limit	Number of results to return

Value

Data frame with reranked results

VectrixDB documentation built on Feb. 20, 2026, 5:09 p.m.