Location

https://www.kennesaw.edu/ccse/events/computing-showcase/sp24-cday-program.php

Streaming Media

Event Website

https://aletheianomous-ai.github.io

Document Type

Event

Start Date

25-4-2024 4:00 PM

Description

For this project, our group aimed to create an intelligent chat bot that was accessible through the web client interface. Aletheianomous, our chat bot, was designed to provide accurate information ethically, aligned with human values. When applicable, the AI would offer the user citations to support its responses. For the back-end, a virtual machine (VM) server in AWS with access to the Graphics Processing Unit (GPU) would run three types of models: Sentence Separation Model, Search Query Extractor Model, and the Response Model. The front-end server using Microsoft Azure generates the web page for the user, exchanges chat data with the Microsoft SQL server, and communicates with the back-end server via REST APIs to request the chat bot to respond to user input. By using this architecture, the overall quality of our product exceeded our standards.

Share

COinS
 
Apr 25th, 4:00 PM

UC-43 Aletheianomous AI: The Chat Bot Providing the Most Accurate Knowledge Information

https://www.kennesaw.edu/ccse/events/computing-showcase/sp24-cday-program.php

For this project, our group aimed to create an intelligent chat bot that was accessible through the web client interface. Aletheianomous, our chat bot, was designed to provide accurate information ethically, aligned with human values. When applicable, the AI would offer the user citations to support its responses. For the back-end, a virtual machine (VM) server in AWS with access to the Graphics Processing Unit (GPU) would run three types of models: Sentence Separation Model, Search Query Extractor Model, and the Response Model. The front-end server using Microsoft Azure generates the web page for the user, exchanges chat data with the Microsoft SQL server, and communicates with the back-end server via REST APIs to request the chat bot to respond to user input. By using this architecture, the overall quality of our product exceeded our standards.

https://digitalcommons.kennesaw.edu/cday/Spring_2024/Undergraduate_Capstone/11