Storia-AI/sage

Feature request: Implement reciprocal rank fusion for combining multiple retriever outputs

开放

#55 创建于 2024年10月4日

 (5 条评论) (0 个反应) (1 位负责人)Python (116 个派生)auto 404
good first issuehacktoberfest🔥 difficulty: 1

仓库指标

星标
 (1,267 个星标)
PR 合并指标
 (PR 指标待抓取)

描述

Right now when we are combining the outputs of a bm25 encoder and a dense retriever we simply do a weighted average of their scores. It's more standard to use reciprocal rank fusion methods to combine multiple scores.

We should implement this alternative hybrid scoring method

贡献者指南