DEVELOPING A CHATBOT SYSTEM FOR UNIVERSITY WEBSITE USING LARGE LANGUAGE MODELS AND RETRIEVAL-AUGMENTED GENERATION VIA FLOWISE PLATFORM
Article Sidebar
Main Article Content
Abstract
This research aimed to develop a chatbot system for a university website using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) techniques via the Flowise platform, which simplifies chatbot development through low-code/no-code concepts. The data utilized for development were obtained from the university website and various course catalogs, stored as text files and vector embeddings in a Postgres database with pgvector extension, while conversation histories were recorded in MongoDB. The development process comprised data preparation, embedding model configuration, document store setup, and chatflow design to create a chatbot capable of answering queries related to the university and its academic programs. The system underwent qualitative testing and evaluation, revealing that most responses were accurate and appropriate. However, some incomplete or inaccurate responses were attributed to suboptimal data management and configuration settings.
Overall performance evaluation indicated that the chatbot successfully answered most inquiries, particularly those concerning university history, administrative structure, and contact information. Nevertheless, the system encountered difficulties in providing complete and accurate information for certain queries, such as comprehensive lists of academic programs within faculties. This study demonstrates the potential of the Flowise platform in streamlining chatbot development by reducing both time requirements and technical complexity, while also providing valuable guidance for implementing AI technologies in educational institutions.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright Notice
The copyright of research articles published in the VRU Research and Development Journal Science and Technology Journal belongs to the Research and Development Institute, Valaya Alongkorn Rajabhat University under the Royal Patronage. Reproduction of the content, in whole or in part, is prohibited without prior written permission from the university.
Responsibility
The content published in the VRU Research and Development Journal Science and Technology Journal is the sole responsibility of the author(s). The journal does not assume responsibility for errors arising from the printing process.
References
Aloqayli, A., & Abdelhafez, H. 2023). Intelligent chatbot for admission in higher education. International Journal of Information and Education Technology, 13(9), 1348-1357.
Arslan, M., Ghanem, H., Munawar, S., & Cruz, C. (2024). A Survey on RAG with LLMs. Procedia computer science, 246, 3781-3790.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., & Amodei, D. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems, 2020-December.
Ismail, M., Kachadoorian, D., Mirani, S., Boyer, D. M., Ransom, T., & Sabuncu, A. C. (2025). BOARD# 63: AI Chatbot for Enhancing Troubleshooting in Engineering Labs. 2025 ASEE Annual Conference & Exposition.
Izacard, G., & Grave, E. (2021). Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, (pp. 874–880).
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W. T., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems, 33, 9459-9474.
Radziwill, N. M., & Benton, M. C. (2017). Evaluating the quality of chatbots and intelligent conversational agents. arXiv preprint arXiv:1704.04579. Retrieved from https://arxiv.org/abs/1704.
Reis, J. A., Almeida, J. R., Almeida, T. M., & Oliveira, J. L. (2024). Using Flowise to Streamline Biomedical Data Discovery and Analysis. 2024 IEEE 22nd Mediterranean Electrotechnical Conference (MELECON). (pp. 695-700).
Tunstall, L., Von Werra, L., & Wolf, T. (2022). Natural language processing with transformers. O'Reilly Media, Inc.
Yu, J., Zhang, Y., Zhang, Z., Yang, Z., Zhao, G., Sun, F., Zhang, F., Liu Q., Sun, J., Liang, J., & Zhang, Y. (2024, October). Rag-guided large language models for visual spatial description with adaptive hallucination corrector. Proceedings of the 32nd ACM International Conference on Multimedia (pp. 11407-11413).
