Ndcg Python Packages

libauc

LibAUC: A Deep Learning Library for X-Risk Optimization

ranklab

Learning-to-rank losses and evaluation

retrieval-eval

Every re-chunk quietly invalidates part of your RAG test suite. retrieval-eval tells you which labels are still true, and repairs the ones it can.

recsys-eval

Open-source infrastructure for building recommender systems. Offline evaluation and promotion gating, extracted from production.

allrank

allRank is a framework for training learning-to-rank neural models based on PyTorch.

ranx-k

Korean-optimized RAG evaluation toolkit with Kiwi tokenizer, ROUGE metrics, and IR evaluation for retrieval systems (Hit@K, NDCG@K, MRR, etc.)

veritail

LLM-as-a-Judge evaluation platform for ecommerce search. Scores relevance, computes IR metrics, and flags quality issues across multiple retail verticals

recsys-candidates

Open-source infrastructure for building recommender systems. Offline evaluation and promotion gating, extracted from production.

rankkit

Ranking evaluation with error bars: NDCG, MRR and MAP with confidence intervals, plus position-bias correction for click logs. No dependencies.

allrank-mod

allRank is a framework for training learning-to-rank neural models based on PyTorch.