Lightning IR
Your one-stop shop for fine-tuning and running neural ranking models.
Lightning IR is a library for fine-tuning and running neural ranking models. It is built on top of PyTorch Lightning to provide a simple and flexible interface to interact with neural ranking models.
You want to for example:
fine-tune your own cross- or bi-encoder models?
index and search through a collection of documents with ColBERT or SPLADE?
re-rank documents with state-of-the-art models?
Lightning IR has you covered!
Installation
We are working on making Lightning IR available on PyPI. For now, you can install Lightning IR from source:
pip install git+https://github.com/webis-de/lightning-ir.git
Getting Started
See the Quickstart guide to get started with Lightning IR