Ty Ebsen, Richard S. Segall, Hyacinthe Aboudja, Daniel Berleant

Proceedings of the 15th International Multi-Conference on Complexity, Informatics and Cybernetics: IMCIC 2024, pp. 148-156 (2024); https://doi.org/10.54808/IMCIC2024.01.148

Ty Ebsen
University of Arkansas Little Rock, Little Rock, Arkansas, United States

Richard S. Segall
Arkansas State University, State University, Arkansas, United States

Hyacinthe Aboudja
Oklahoma City University, Oklahoma City, Oklahoma, United States

Daniel Berleant
University of Arkansas Little Rock, Little Rock, Arkansas, United States

Cite this paper as:
Ebsen, T., Segall, R. S., Aboudja, H., Berleant, D. (2024). A Customer Service Chatbot Using Python, Machine Learning, and Artificial Intelligence. In N. Callaos, S. Hashimoto, N. Lace, B. Sánchez, M. Savoie (Eds.), Proceedings of the 15th International Multi-Conference on Complexity, Informatics and Cybernetics: IMCIC 2024, pp. 148-156. International Institute of Informatics and Cybernetics. https://doi.org/10.54808/IMCIC2024.01.148

This report shows that with the most recent advancements in Artificial Intelligence (AI) and Natural Language Processing (NLP) using generative-pretrained transformers, we can develop robust AI applications to assist customer service departments with question answer systems. This paper addresses the question answering task using an OpenAI Application Programming Interface (API). This report examines how to create an AI question answering application from documents that generated correct answers to questions about those documents. We used two different approaches to create the question answering system. One was to use just the OpenAI API. The other was to use the LangChain framework and libraries. Both applications did answer questions correctly. LangChain used less code with a higher learning curve. The OpenAI API used more code and provided more detailed answers.