The goal of this competition is to design a code retrieval system that can effectively find relevant files to help answer questions about [Hugging Face's Transformers](https://github.com/huggingface/transformers) library. Our dataset consists of natural language questions paired with relevant file names from the repository.

This will give you the chance to experiment with many of the moving pieces involved in a code retrieval pipeline: file chunking, dense vs sparse embeddings, embedding types, rerankers, etc. While we do provide a training set, we expect to see improvements over the provided baseline without any fine-tuning.