We built a better reranker and open sourced it
Family of instruction-following multilingual rerankers on the cost/performance Pareto frontier across public and customer benchmarks. Reranker v2 was designed specifically for agentic RAG, supports instruction following (our v1 was the first to introduce this), and is multilingual.
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
Contextual AI Reranker
docs.contextual.ai1st reranker that follows custom instructions
Metarank
demo.metarank.aiopen-source hybrid search with LLMs
Memora
usememora.appA Vector DB with Multistage Reranking
R2R V2
github.comA open source RAG engine with prod features
Towards agentic Graph RAG
blog.kuzudb.comEnhancing graph retrieval with vector search