Search & IndexingTechnical Definition

Reciprocal Rank Fusion (RRF)

Reciprocal Rank Fusion (RRF) is an algorithmic scoring method that merges and ranks search results from multiple independent retrieval pipelines.

Core Technical Definition

Reciprocal Rank Fusion (RRF) is an algorithm that combines the ranked results of multiple search algorithms (such as vector and keyword search) into a single unified ranking based on their reciprocal positions.

How RRF works in practice

Because vector similarity scores (0.0 to 1.0) and keyword scores (BM25) use incompatible scales, simple numerical addition fails. RRF scores documents based strictly on their ranking position: $RRF(d) = \sum \frac{1}{k + r(d)}$.

Documents that appear near the top of both the semantic vector list and the exact keyword list receive exponentially higher composite scores.

How SiteMind implements RRF

SiteMind’s hybrid search pipeline uses RRF with a standard constant ($k=60$) to fuse dense vector matches, full-text tsvector hits, and trigram candidates into an optimal context ranking.

Test our AI tools in your browser (100% Free)

Estimate support savings, token counts, or test prompt injection security guardrails with our zero-cost sandboxes.

Explore Free Tools →