rerankers: A Lightweight Python Library to Unify Ranking Methods

TL;DR

rerankers is a lightweight Python library that unifies various re-ranking methods into a single, easy-to-use interface, enabling quick experimentation with minimal dependencies and no performance loss.

Contribution

It introduces a unified, user-friendly Python library for multiple re-ranking approaches, simplifying implementation and comparison in retrieval pipelines.

Findings

Provides a single interface for diverse re-ranking methods

Ensures minimal dependencies and no performance degradation

Regularly updated with supported models

Abstract

This paper presents rerankers, a Python library which provides an easy-to-use interface to the most commonly used re-ranking approaches. Re-ranking is an integral component of many retrieval pipelines; however, there exist numerous approaches to it, relying on different implementation methods. rerankers unifies these methods into a single user-friendly interface, allowing practitioners and researchers alike to explore different methods while only changing a single line of Python code. Moreover ,rerankers ensures that its implementations are done with the fewest dependencies possible, and re-uses the original implementation whenever possible, guaranteeing that our simplified interface results in no performance degradation compared to more complex ones. The full source code and list of supported models are updated regularly and available at https://github.com/answerdotai/rerankers.