AI engineering glossary · RAG vector search
What is reranker?
Reranker: A model that scores how well each candidate passage answers a query, by reading query and passage together. Rerankers are more accurate than embedding similarity but too slow to run over an entire collection, so they only rescore a shortlist.
Reranker: an example
A reranker gives the correct paragraph a score of 0.94, lifting it from rank 12 to rank 1.
Related terms
More RAG vector search terms
- Reranking
- Rescoring
- Retrieval evaluation
- Retrieval-augmented generation
- Retriever
- Scalar quantisation
- Score fusion
- Self-RAG
Where you learn it
Reranker is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.