通过任务分解和RAG生成低代码完整工作流
Generating a Low-code Complete Workflow via Task Decomposition and RAG
AI总结:
本文将任务分解与RAG形式化为GenAI系统设计模式,分析其工程权衡,并结合企业级工作流生成应用总结全开发周期实践经验。
摘要:
AI技术正迅速从研究走向生产。随着生成文本、图像和视频的基础模型(FMs)的普及,基于AI的系统正变得越来越复杂。与传统的基于AI的软件相比,采用FMs的系统(即基于GenAI的系统)由于其规模和多功能性而更难设计。这使得有必要记录可在各类GenAI应用中使用的最佳实践,这些实践在软件工程中被称为设计模式。我们的第一项贡献是将任务分解和检索增强生成(RAG)这两种技术形式化为基于GenAI的系统的设计模式。我们从软件质量属性的角度讨论了它们的权衡,并对替代方法进行了评述。我们建议AI从业者不仅从科学角度,而且从灵活性、可维护性、安全性和保密性等期望的工程属性角度来考虑这些技术。作为第二项贡献,我们描述了应用任务分解和RAG为企业用户构建复杂的真实GenAI应用——工作流生成(Workflow Generation)的行业经验。生成工作流的任务需要以用户需求为输入,使用来自系统环境的数据生成特定计划。由于这两种模式会影响整个AI开发生命周期,我们解释了它们如何影响数据集创建、模型训练、模型评估和部署阶段。
英文摘要:
AI technologies are moving rapidly from research to production. With the popularity of Foundation Models (FMs) that generate text, images, and video, AI-based systems are increasing their complexity. Compared to traditional AI-based software, systems employing FMs, or GenAI-based systems, are more difficult to design due to their scale and versatility. This makes it necessary to document best practices, known as design patterns in software engineering, that can be used across GenAI applications. Our first contribution is to formalize two techniques, Task Decomposition and Retrieval-Augmented Generation (RAG), as design patterns for GenAI-based systems. We discuss their trade-offs in terms of software quality attributes and comment on alternative approaches. We recommend to AI practitioners to consider these techniques not only from a scientific perspective but also from the standpoint of desired engineering properties such as flexibility, maintainability, safety, and security. As a second contribution, we describe our industry experience applying Task Decomposition and RAG to build a complex real-world GenAI application for enterprise users: Workflow Generation. The task of generating workflows entails generating a specific plan using data from the system environment, taking as input a user requirement. As these two patterns affect the entire AI development cycle, we explain how they impacted the dataset creation, model training, model evaluation, and deployment phases.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。