Storia-AI/sage
Feature request: Implement reciprocal rank fusion for combining multiple retriever outputs
Ouverte
#55 ouverte le 4 oct. 2024
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