面向基建领域的多模态智能助手，能准确回答图文混合问题。
InfoTech Assistant: A Multimodal Conversational Agent for InfoTechnology Web Portal Queries
- 结合网页抓取与RAG技术，用LLM生成精准响应。
- 在专业任务中准确率达95%，回复质量高。
- 适合基建从业者快速获取图文信息。
本初步研究介绍了InfoTech Assistant的开发，这是一个针对桥梁评估和基础设施技术领域设计的多模态聊天机器人。系统通过整合网页数据抓取、大语言模型（LLMs）和检索增强生成（RAG），提供准确且上下文相关的回答。数据包括文本描述和图像，来自InfoTechnology网站的公开文档，并以JSON格式组织以支持高效查询。系统架构包含基于HTML的界面和通过LLM Studio连接Llama 3.1模型的Flask后端。评估结果显示，该系统在特定领域任务中准确率约为95%，相似度评分高，证实了回复质量。此RAG增强结构使InfoTech Assistant能够处理复杂的多模态查询，响应中同时包含文本和视觉信息。该助手在为基础设施专业人士提供高准确性和相关性输出方面展现出巨大潜力。
原文摘要 · Abstract (English)
This pilot study presents the development of the InfoTech Assistant, a domain-specific, multimodal chatbot engineered to address queries in bridge evaluation and infrastructure technology. By integrating web data scraping, large language models (LLMs), and Retrieval-Augmented Generation (RAG), the InfoTech Assistant provides accurate and contextually relevant responses. Data, including textual descriptions and images, are sourced from publicly available documents on the InfoTechnology website and organized in JSON format to facilitate efficient querying. The architecture of the system includes an HTML-based interface and a Flask back end connected to the Llama 3.1 model via LLM Studio. Evaluation results show approximately 95 percent accuracy on domain-specific tasks, with high similarity scores confirming the quality of response matching. This RAG-enhanced setup enables the InfoTech Assistant to handle complex, multimodal queries, offering both textual and visual information in its responses. The InfoTech Assistant demonstrates strong potential as a dependable tool for infrastructure professionals, delivering high accuracy and relevance in its domain-specific outputs.
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。