rerankers: A Lightweight Python Library to Unify Ranking Methods
This provides a practical tool for practitioners and researchers to easily explore different re-ranking methods with minimal code changes, though it is incremental as it packages existing methods.
The authors tackled the fragmentation of re-ranking approaches in retrieval pipelines by developing rerankers, a lightweight Python library that unifies multiple methods into a single interface, resulting in no performance degradation compared to original implementations.
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.