用大模型激活分散的科学计算知识库，提升代码使用与开发效率。
AI Assistants to Enhance and Exploit the PETSc Knowledge Base
- 构建基于RAG和重排序的LLM系统，整合PETSc多源知识。
- 实测显示模型能准确回答关于稀疏求解器的复杂技术问题。
- 适合科研人员、开发者及需要快速掌握高性能计算工具的用户。
生成式AI，尤其是大语言模型（LLMs），正改变技术知识的获取与利用方式。PETSc作为广泛使用的高性能科学计算数值库，历经三十年发展积累了丰富的知识资源，涵盖源码、文档、邮件列表、GitLab问题、Discord对话、技术论文等，但这些知识大多非正式且难以访问。为更高效地激活和利用该知识库，PETSc团队正构建一个基于LLM的系统，结合检索增强生成（RAG）、重排序算法和聊天机器人等定制工具，以辅助用户、支持开发者并建议正式文档更新。本文报告了系统设计与评估的初步经验，包括架构设计、针对PETSc的RAG与重排序应用、多种LLMs与嵌入模型的评估方法，以及用户界面设计。依托阿贡领导力计算设施资源，我们分析了LLM响应如何提升数值软件的开发与使用效率，初期聚焦于可扩展的Krylov求解器。目标是建立可扩展的知识中心型AI框架，实现可扩展支持、丰富文档与优化研发流程。最后，提出将系统拓展为稳健演进平台的未来方向，推动软件生态加速科学发现。
原文摘要 · Abstract (English)
Generative AI, especially through large language models (LLMs), is transforming how technical knowledge can be accessed, reused, and extended. PETSc, a widely used numerical library for high-performance scientific computing, has accumulated a rich but fragmented knowledge base over its three decades of development, spanning source code, documentation, mailing lists, GitLab issues, Discord conversations, technical papers, and more. Much of this knowledge remains informal and inaccessible to users and new developers. To activate and utilize this knowledge base more effectively, the PETSc team has begun building an LLM-powered system that combines PETSc content with custom LLM tools -- including retrieval-augmented generation (RAG), reranking algorithms, and chatbots -- to assist users, support developers, and propose updates to formal documentation. This paper presents initial experiences designing and evaluating these tools, focusing on system architecture, using RAG and reranking for PETSc-specific information, evaluation methodologies for various LLMs and embedding models, and user interface design. Leveraging the Argonne Leadership Computing Facility resources, we analyze how LLM responses can enhance the development and use of numerical software, with an initial focus on scalable Krylov solvers. Our goal is to establish an extensible framework for knowledge-centered AI in scientific software, enabling scalable support, enriched documentation, and enhanced workflows for research and development. We conclude by outlining directions for expanding this system into a robust, evolving platform that advances software ecosystems to accelerate scientific discovery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。