# Rerankers

- Page: https://shared.btbytes.com/p/rerankers
- Date: 2025-06-25

[Rerankers and Two-Stage Retrieval | Pinecone](https://www.pinecone.io/learn/series/rag/rerankers/)

[Boosting Your Search and RAG with Voyage’s Rerankers – Voyage AI](https://blog.voyageai.com/2024/03/15/boosting-your-search-and-rag-with-voyages-rerankers/)

> A reranker is often used as a refinement step in a two-stage retrieval system. In the first stage, [embedding-based methods](https://blog.voyageai.com/2023/10/29/voyage-embeddings/) (or lexical search algorithms such as [BM25](https://en.wikipedia.org/wiki/Okapi_BM25) and [TF-IDF](https://en.wikipedia.org/wiki/Tf%E2%80%93idf)) produce a broad set of initial search results. Following this, a re-ranker evaluates the relevance scores between the query and the candidate documents and selects the most pertinent subset of candidate documents based on the scores.