A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
🔥 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.
R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
allRank is a framework for training learning-to-rank neural models based on PyTorch.
State-of-the-Art Embeddings, Retrieval, and Reranking
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
Simple RL training for reasoning
1 capture since 2026-05-25
