Storia-AI/sage

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

Aperta

#55 aperta il 4 ott 2024

 (5 commenti) (0 reazioni) (1 assegnatario)Python (116 fork)auto 404
good first issuehacktoberfest🔥 difficulty: 1

Metriche repository

Star
 (1267 stelle)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

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

Guida contributor