Reciprocal rank fusion merges two ranked lists — say, BM25 results and vector-search results over...
Reciprocal rank fusion merges two ranked lists — say, BM25 results and vector-search results over your chargeback cases — into one. It has exactly one parameter, k. And the answer is just... 60. Not tuned per dataset. Not learned. Sixty, from the original paper, works essentially everywhere.
The entire algorithm:
def rrf(rankings: list[list[str]], k: int = 60) -> list[tuple[str, float]]:
"""Each ranking is a list of doc IDs, best first. Score = sum of 1/(k + rank)."""
scores = {}
Hybrid search is commonly used in the search systems which runs several retrievers for a given same...
Reciprocal Rank Fusion (RRF) on Elasticsearch is gated to the Enterprise tier. On the Basic/free...
Combine dense embeddings and sparse keyword search using Reciprocal Rank Fusion to eliminate retrieval failure modes in…
IntroductionTabby has made significant advancements in its code context understanding with the introduction of a semantic…
Compare top reranking models for RAG pipelines in 2026. Learn how cross-encoders, LLM rerankers, and late-interaction models…
How metadata filtering, tenant scope, and data locality reduce the vector search space before ranking in a RAG database.
