Storia-AI/sage

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

Ouverte

#55 ouverte le 4 oct. 2024

 (5 commentaires) (0 réaction) (1 personne assignée)Python (116 forks)auto 404
good first issuehacktoberfest🔥 difficulty: 1

Métriques du dépôt

Stars
 (1 267 étoiles)
Métriques de merge PR
 (Métriques PR en attente)

Description

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

Guide contributeur