Use of Artificial Intelligence in the Development of a Chatbot for Academic and Administrative Support at IFPI

• Larissa Souza do Nascimento IFPI
• Ricardo Moura Sekeff Budaruiche IFPI

DOI: https://doi.org/10.5753/enucompi.2025.9768

Abstract

This paper presents the proposed development of an institutional chatbot for IFPI, leveraging advanced artificial intelligence technologies. The solution integrates the LLaMA 3 language model, the LangChain framework, and the ChromaDB vector database within an AI orchestration architecture. The system aims to deliver precise and contextualized responses to user queries, optimizing communication and institutional information management. The methodology includes fine-tuning strategies and Retrieval-Augmented Generation (RAG), enabling continuous chatbot personalization based on user feedback and normative updates.

References

de Brito, L. (2021). Zuboff, shoshana. the age of surveillance capitalism: The fight for a human future at the new frontier of power. new york: Publicaffairs, 2019, 691p. isbn 9781610395694. Mural Internacional, 12:e55150.

et al., O. (2024). Gpt-4 technical report.

Mathur, S. and Chhabra, A. (2024). Vector search algorithms: A brief survey. In 2024 4th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS), pages 365–371.

Saad, M. and Qawaqneh, Z. (2024). Closed domain question-answering techniques in an institutional chatbot. In 2024 4th International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), pages 1–8.

Susskind, R. (2019). Online Courts and the Future of Justice. Oxford University Press.

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need.