arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2504.03343cs.AIcs.HCcs.IR
收藏

Talk2X —— 一个促进在Web上部署LLM驱动聊天机器人的开源工具包

Talk2X -- An Open-Source Toolkit Facilitating Deployment of LLM-Powered Chatbots on the Web

German Research Center for Artificial Intelligence(德国人工智能研究中心);RPTU Kaiserslautern-Landau(凯撒斯劳滕-兰道工业大学);coneno GmbH(科内诺有限公司)

Lars Krupp, Daniel Geißler, Peter Hevesi, Marco Hirsch, Paul Lukowicz, Jakob Karolus

AI总结:

本文提出开源智能体Talk2X,结合改进的RAG与自动生成的向量数据库,为任意网站提供即用型LLM聊天机器人集成工具,显著提升了用户信息检索的任务效率与体验。

摘要:

集成到网站中的LLM驱动聊天机器人提供了导航和信息检索的替代方式,导致用户在Web上访问信息的方式发生了转变。然而,主要是闭源解决方案限制了其在网站托管者中的普及,并且在实现细节和能源效率方面缺乏透明度。在这项工作中,我们提出了我们公开可用的智能体Talk2X,它利用了改进的检索增强生成方法(RAG)与自动生成的向量数据库相结合,从而提升了能源效率。Talk2X的架构可泛化至任意网站,为开发者提供了一个即用型集成工具。采用混合方法,我们通过让用户从开放科学存储库获取特定资产来评估Talk2X的可用性。与标准用户-网站交互相比,Talk2X显著改善了任务完成时间、正确性和用户体验,帮助用户快速定位特定信息。我们的发现为我们访问Web信息方式的持续范式转变提供了技术进步。

英文摘要:

Integrated into websites, LLM-powered chatbots offer alternative means of navigation and information retrieval, leading to a shift in how users access information on the web. Yet, predominantly closed-sourced solutions limit proliferation among web hosts and suffer from a lack of transparency with regard to implementation details and energy efficiency. In this work, we propose our openly available agent Talk2X leveraging an adapted retrieval-augmented generation approach (RAG) combined with an automatically generated vector database, benefiting energy efficiency. Talk2X's architecture is generalizable to arbitrary websites offering developers a ready to use tool for integration. Using a mixed-methods approach, we evaluated Talk2X's usability by tasking users to acquire specific assets from an open science repository. Talk2X significantly improved task completion time, correctness, and user experience supporting users in quickly pinpointing specific information as compared to standard user-website interaction. Our findings contribute technical advancements to an ongoing paradigm shift of how we access information on the web.

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。

↑