Ontology Alignment (OA) is fundamental for achieving semantic interoperability across diverse knowledge systems. We present OntoAligner, a comprehensive, modular, and robust Python toolkit for ontology alignment, designed to address current limitations with existing tools faced by practitioners. Existing tools are limited in scalability, modularity, and ease of integration with recent AI advances. OntoAligner provides a flexible architecture integrating existing lightweight OA techniques such as fuzzy matching but goes beyond by supporting contemporary methods with retrieval-augmented generation and large language models for OA. The framework prioritizes extensibility, enabling researchers to integrate custom alignment algorithms and datasets. This paper details the design principles, architecture, and implementation of the OntoAligner, demonstrating its utility through benchmarks on standard OA tasks. Our evaluation highlights OntoAligner's ability to handle large-scale ontologies efficiently with few lines of code while delivering high alignment quality. By making OntoAligner open-source, we aim to provide a resource that fosters innovation and collaboration within the OA community, empowering researchers and practitioners with a toolkit for reproducible OA research and real-world applications.

翻译：本体对齐（OA）是实现异构知识系统间语义互操作的基础。我们提出了OntoAligner，一个全面、模块化且鲁棒的Python本体对齐工具包，旨在解决从业者使用现有工具时面临的局限性。现有工具在可扩展性、模块化以及与最新人工智能进展的集成便利性方面存在不足。OntoAligner提供了一个灵活的架构，不仅集成了模糊匹配等现有轻量级OA技术，更进一步支持了基于检索增强生成和大语言模型的现代OA方法。该框架强调可扩展性，使研究人员能够集成自定义的对齐算法和数据集。本文详细阐述了OntoAligner的设计原则、架构和实现，并通过在标准OA任务上的基准测试展示了其实用性。我们的评估凸显了OntoAligner能够以少量代码高效处理大规模本体，同时提供高质量的对齐结果。通过将OntoAligner开源，我们旨在为OA社区提供一个促进创新与协作的资源，为研究人员和从业者提供一个支持可复现OA研究及实际应用的工具包。