Storia-AI/sage
Feature request: Implement reciprocal rank fusion for combining multiple retriever outputs
オープン
#55 opened on 2024/10/04
good first issuehacktoberfest🔥 difficulty: 1
Repository metrics
- Stars
- (1,267 個のスター)
- PR merge metrics
- (PR metrics pending)
説明
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