Cohere Rerank
A reranking API service provided by Cohere that uses a cross-encoder to score the relevance of query-document pairs, and is used for reranking retrieval results in RAG.
Core Facts
Commonly used Rerank models include Cohere Rerank and BGE-Reranker.
Reranking models such as Cohere Rerank and BGE-Reranker use a Cross-Encoder architecture to perform fine-grained relevance scoring between queries and documents, and are a key component in optimizing RAG precision.
Timeline (last 90 days)
Reranking uses a cross-encoder to score query-document pairs one by one, with accuracy far higher than vector similarity but at higher computational cost, so fine ranking is done only on the small number of candidates after coarse ranking, forming a two-stage architecture of coarse ranking plus fine ranking.
Common open-source re-ranking models include Cohere Rerank, BGE-Reranker, and the ms-marco series.
Enterprise-grade RAG retrieval pipelines typically include multiple stages such as recall (vector retrieval + BM25 keyword retrieval), reranking (using Cross-Encoders such as Cohere Rerank and BGE-Reranker), and post-filtering processing.
常用开源reranker包括Cohere Rerank、bge-reranker和cross-encoder/ms-marco系列
生产中典型做法是先用向量检索和BM25快速召回50-100个候选结果，再用reranker精排取top-k送入LLM，常用开源reranker包括Cohere Rerank、bge-reranker和cross-encoder/ms-marco系列
重排序通常使用交叉编码器实现，将查询和候选文档拼接后同时输入，通常只对Top-50到Top-100候选重排，最终选取Top-3到Top-5送入生成模型
All Facts (9)
Commonly used Rerank models include Cohere Rerank and BGE-Reranker.
80%VerifiedReranking models such as Cohere Rerank and BGE-Reranker use a Cross-Encoder architecture to perform fine-grained relevance scoring between queries and documents, and are a key component in optimizing RAG precision.
65%UnverifiedReranker模型（如Cohere Rerank、BGE-Reranker、bce-reranker）同时考虑Query和Document的交互信息，排序精度更高但计算成本也更大
90%UnverifiedReranking uses a cross-encoder to score query-document pairs one by one, with accuracy far higher than vector similarity but at higher computational cost, so fine ranking is done only on the small number of candidates after coarse ranking, forming a two-stage architecture of coarse ranking plus fine ranking.
50%UnverifiedCommon open-source re-ranking models include Cohere Rerank, BGE-Reranker, and the ms-marco series.
50%UnverifiedEnterprise-grade RAG retrieval pipelines typically include multiple stages such as recall (vector retrieval + BM25 keyword retrieval), reranking (using Cross-Encoders such as Cohere Rerank and BGE-Reranker), and post-filtering processing.
50%Unverified常用开源reranker包括Cohere Rerank、bge-reranker和cross-encoder/ms-marco系列
50%Unverified生产中典型做法是先用向量检索和BM25快速召回50-100个候选结果，再用reranker精排取top-k送入LLM，常用开源reranker包括Cohere Rerank、bge-reranker和cross-encoder/ms-marco系列
50%Unverified重排序通常使用交叉编码器实现，将查询和候选文档拼接后同时输入，通常只对Top-50到Top-100候选重排，最终选取Top-3到Top-5送入生成模型
50%