xpmir/mice

Late Interaction Models Training & Retrieval

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

A Python framework for performing information retrieval experiments, building on http://terrier.org/

🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techniques, 24+ state-of-the-art Reranking models, and multiple RAG methods.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

State-of-the-Art Embeddings, Retrieval, and Reranking