AI engineering glossary · RAG vector search
What is RRF (reciprocal rank fusion)?
Reciprocal rank fusion (also called RRF): A method for merging several ranked lists by scoring each item as the sum of 1 / (k + rank) across lists, where k is often 60. It needs no score calibration and rewards items ranked highly by multiple retrievers.
Reciprocal rank fusion: an example
A document ranked 1st by BM25 and 3rd by vector search scores 1/61 + 1/63, about 0.0323.
Related terms
More RAG vector search terms
- Recursive character splitting
- Reranker
- Reranking
- Rescoring
- Retrieval evaluation
- Retrieval-augmented generation
- Retriever
- Scalar quantisation
Where you learn it
Reciprocal rank fusion is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.