Bio-Eng-LLM AI Assist: A modular chatbot platform for interdisciplinary research and education

IF 2.4 4区计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING

SoftwareX Pub Date : 2025-07-18 DOI:10.1016/j.softx.2025.102260

Ali Forootani , Danial Esmaeili Aliabadi , Daniela Thrän

{"title":"Bio-Eng-LLM AI Assist: A modular chatbot platform for interdisciplinary research and education","authors":"Ali Forootani , Danial Esmaeili Aliabadi , Daniela Thrän","doi":"10.1016/j.softx.2025.102260","DOIUrl":null,"url":null,"abstract":"<div><div>This article presents <span>Bio-Eng-LLM</span> <span>AI</span> <span>chatbot</span> Assist, a versatile platform designed to support interactive learning and research across multiple disciplines. Initially developed for biomass research, the system’s capabilities have since expanded to serve broader educational and scientific domains. It integrates large language models (<span>LLM</span>s) with advanced tools for document analysis, real-time file and web data integration, image understanding, and speech recognition. At the core of the platform lies a Retrieval Augmented Generation (<span>RAG</span>) framework, which improves the contextual relevance and factual accuracy of responses by incorporating external information sources. <span>Bio-Eng-LLM</span> also includes image generation via diffusion models and secure web-based search and summarization features. Its user-friendly interface supports multimodal interactions – text, image, and voice – enabling dynamic and personalized assistance in academic environments. By simplifying access to complex information and promoting interdisciplinary collaboration, <span>Bio-Eng-LLM</span> fosters <span>AI</span> literacy and facilitates both knowledge discovery and communication.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"31 ","pages":"Article 102260"},"PeriodicalIF":2.4000,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"SoftwareX","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352711025002274","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

Abstract

This article presents Bio-Eng-LLM AI chatbot Assist, a versatile platform designed to support interactive learning and research across multiple disciplines. Initially developed for biomass research, the system’s capabilities have since expanded to serve broader educational and scientific domains. It integrates large language models (LLMs) with advanced tools for document analysis, real-time file and web data integration, image understanding, and speech recognition. At the core of the platform lies a Retrieval Augmented Generation (RAG) framework, which improves the contextual relevance and factual accuracy of responses by incorporating external information sources. Bio-Eng-LLM also includes image generation via diffusion models and secure web-based search and summarization features. Its user-friendly interface supports multimodal interactions – text, image, and voice – enabling dynamic and personalized assistance in academic environments. By simplifying access to complex information and promoting interdisciplinary collaboration, Bio-Eng-LLM fosters AI literacy and facilitates both knowledge discovery and communication.

查看原文本刊更多论文

Bio-Eng-LLM AI Assist：一个跨学科研究和教育的模块化聊天机器人平台

本文介绍了Bio-Eng-LLM AI聊天机器人辅助，一个多功能平台，旨在支持跨多个学科的交互式学习和研究。该系统最初是为生物质的研究而开发的，其功能已经扩展到更广泛的教育和科学领域。它将大型语言模型（llm）与用于文档分析、实时文件和web数据集成、图像理解和语音识别的高级工具集成在一起。该平台的核心是检索增强生成（RAG）框架，该框架通过整合外部信息源来提高响应的上下文相关性和事实准确性。Bio-Eng-LLM还包括通过扩散模型和安全的基于网络的搜索和总结功能生成图像。它的用户友好界面支持多模式交互——文本、图像和语音——在学术环境中实现动态和个性化的帮助。通过简化对复杂信息的访问和促进跨学科合作，Bio-Eng-LLM培养了人工智能素养，促进了知识发现和交流。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

SoftwareX COMPUTER SCIENCE, SOFTWARE ENGINEERING-

CiteScore

5.50

自引率

2.90%

发文量

184

审稿时长

9 weeks

期刊介绍： SoftwareX aims to acknowledge the impact of software on today''s research practice, and on new scientific discoveries in almost all research domains. SoftwareX also aims to stress the importance of the software developers who are, in part, responsible for this impact. To this end, SoftwareX aims to support publication of research software in such a way that: The software is given a stamp of scientific relevance, and provided with a peer-reviewed recognition of scientific impact; The software developers are given the credits they deserve; The software is citable, allowing traditional metrics of scientific excellence to apply; The academic career paths of software developers are supported rather than hindered; The software is publicly available for inspection, validation, and re-use. Above all, SoftwareX aims to inform researchers about software applications, tools and libraries with a (proven) potential to impact the process of scientific discovery in various domains. The journal is multidisciplinary and accepts submissions from within and across subject domains such as those represented within the broad thematic areas below: Mathematical and Physical Sciences; Environmental Sciences; Medical and Biological Sciences; Humanities, Arts and Social Sciences. Originating from these broad thematic areas, the journal also welcomes submissions of software that works in cross cutting thematic areas, such as citizen science, cybersecurity, digital economy, energy, global resource stewardship, health and wellbeing, etcetera. SoftwareX specifically aims to accept submissions representing domain-independent software that may impact more than one research domain.