Bio-Eng-LMM AI Assist chatbot: A Comprehensive Tool for Research and Education

arXiv - EE - Systems and Control Pub Date : 2024-09-11 DOI:arxiv-2409.07110

Ali Forootani, Danial Esmaeili Aliabadi, Daniela Thraen

{"title":"Bio-Eng-LMM AI Assist chatbot: A Comprehensive Tool for Research and Education","authors":"Ali Forootani, Danial Esmaeili Aliabadi, Daniela Thraen","doi":"arxiv-2409.07110","DOIUrl":null,"url":null,"abstract":"This article introduces Bio-Eng-LMM AI chatbot, a versatile platform designed\nto enhance user interaction for educational and research purposes. Leveraging\ncutting-edge open-source Large Language Models (LLMs), Bio-Eng-LMM operates as\na sophisticated AI assistant, exploiting the capabilities of traditional models\nlike ChatGPT. Central to Bio-Eng-LMM is its implementation of Retrieval\nAugmented Generation (RAG) through three primary methods: integration of\npreprocessed documents, real-time processing of user-uploaded files, and\ninformation retrieval from any specified website. Additionally, the chatbot\nincorporates image generation via a Stable Diffusion Model (SDM), image\nunderstanding and response generation through LLAVA, and search functionality\non the internet powered by secure search engine such as DuckDuckGo. To provide\ncomprehensive support, Bio-Eng-LMM offers text summarization, website content\nsummarization, and both text and voice interaction. The chatbot maintains\nsession memory to ensure contextually relevant and coherent responses. This\nintegrated platform builds upon the strengths of RAG-GPT and Web-Based RAG\nQuery (WBRQ) where the system fetches relevant information directly from the\nweb to enhance the LLMs response generation.","PeriodicalId":501175,"journal":{"name":"arXiv - EE - Systems and Control","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Systems and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07110","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

This article introduces Bio-Eng-LMM AI chatbot, a versatile platform designed to enhance user interaction for educational and research purposes. Leveraging cutting-edge open-source Large Language Models (LLMs), Bio-Eng-LMM operates as a sophisticated AI assistant, exploiting the capabilities of traditional models like ChatGPT. Central to Bio-Eng-LMM is its implementation of Retrieval Augmented Generation (RAG) through three primary methods: integration of preprocessed documents, real-time processing of user-uploaded files, and information retrieval from any specified website. Additionally, the chatbot incorporates image generation via a Stable Diffusion Model (SDM), image understanding and response generation through LLAVA, and search functionality on the internet powered by secure search engine such as DuckDuckGo. To provide comprehensive support, Bio-Eng-LMM offers text summarization, website content summarization, and both text and voice interaction. The chatbot maintains session memory to ensure contextually relevant and coherent responses. This integrated platform builds upon the strengths of RAG-GPT and Web-Based RAG Query (WBRQ) where the system fetches relevant information directly from the web to enhance the LLMs response generation.

查看原文本刊更多论文

生物工程-LMM 人工智能辅助聊天机器人：用于研究和教育的综合工具

本文介绍了 Bio-Eng-LMM 人工智能聊天机器人，这是一个多功能平台，旨在增强教育和研究目的的用户交互。利用尖端的开源大语言模型（LLM），Bio-Eng-LMM 可作为一个复杂的人工智能助手运行，并利用 ChatGPT 等传统模型的功能。Bio-Eng-LMM 的核心是通过三种主要方法实现检索增强生成（RAG）：整合预处理文档、实时处理用户上传的文件以及从任何指定网站检索信息。此外，聊天机器人还通过稳定扩散模型（SDM）生成图像，通过 LLAVA 生成图像理解和响应，并通过 DuckDuckGo 等安全搜索引擎在互联网上提供搜索功能。为了提供全面的支持，Bio-Eng-LMM 提供了文本摘要、网站内容摘要以及文本和语音交互功能。聊天机器人可保持会话记忆，确保回复与上下文相关且连贯一致。这个集成平台借鉴了 RAG-GPT 和基于网络的 RAGQuery (WBRQ) 的优势，系统直接从网上获取相关信息，以增强 LLM 的回复生成能力。

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

arXiv - EE - Systems and Control

自引率

0.00%

发文量