Aplicação prática da arquitetura RAG no desenvolvimento de interfaces educacionais com IA

Daniel Souza Coelho; Nelson Nascimento Junior; Alice Silva Marinho Gomes

doi:10.47734/regrasp.v10.04.p69-74

Daniel Souza Coelho IFSP – Campus Cubatão https://orcid.org/0009-0004-2849-8311
Nelson Nascimento Junior IFSP – Campus Cubatão https://orcid.org/0000-0002-5853-0528
Alice Silva Marinho Gomes IFSP – Campus Cubatão https://orcid.org/0009-0008-3439-8180

DOI: https://doi.org/10.47734/regrasp.v10.04.p69-74

Keywords: artificial intelligence, retrieval-augmented generation (RAG), large language models (LLMs)

Abstract

This work presents the development of an interactive educational web interface using Generative Artificial Intelligence (GAI) applied to the construction of innovative solutions for Integrated Technical High School. The proposal aims to support educators in pedagogical planning and the creation of interdisciplinary activities through a platform that integrates GAI resources into the web development workflow. The system was implemented using HTML, CSS, JavaScript, and integration with external APIs, utilizing techniques such as prompt engineering and automatic component rendering supported by language models. The modular web architecture allows for the coupling of educational functionalities, with the primary example being the application of the RAG (Retrieval-Augmented Generation) architecture for natural language queries of the Course Pedagogical Project (PPC). This application seeks to identify connections between disciplines and support interdisciplinary projects in a practical and automated manner. The prototype was published online and demonstrated technical viability, interface clarity, and flexibility for integration with AI-based services. The research highlights how the use of AI in educational web development can promote personalization, accessibility, and innovation in contemporary pedagogical practices.

Author Biographies

Daniel Souza Coelho, IFSP – Campus Cubatão

Estudante do Ensino Médio Integrado ao Técnico em Informática

Nelson Nascimento Junior, IFSP – Campus Cubatão

Doutor em Ciência da Computação pela UFABC (Universidade Federal do ABC), Mestre em Engenharia da Informação pela UFABC (Universidade Federal do ABC), Pós-Graduado (Latu Sensu) em Ciência e Tecnologia pela Universidade Federal do ABC (UFABC), Pós-Graduado (Latu Sensu) em Engenharia da Computação pela UFU (Universidade Federal de Uberlândia) e Bacharel em Ciências da Computação pela UNISANTA (Universidade Santa Cecília). Professor do IFSP (Instituto Federal de Educação, Ciência e Tecnologia de São Paulo). Professor por 8 anos da FATEC (Faculdade de Tecnologia do Centro Paula Souza), atualmente pesquiso o uso das TICs no processo de ensino e aprendizagem com especial interesse em Inteligência Artificial, Visão Computacional e Jogos Educacionais Digitais (JED).

Alice Silva Marinho Gomes, IFSP – Campus Cubatão

Estudante do Curso Superior de Tecnologia em Análise e Desenvolvimento de Sistemas.

References

Brown, T. B. (2020). Language models are few-shot learners. arXiv. https://arxiv.org/abs/2005.14165.

Gao, Y., et al. (2023). Retrieval-augmented generation for large language models: A survey. arXiv. https://arxiv.org/abs/2312.10997.

Kaluarachchi, T., & Wickramasinghe, M. (2023). A systematic literature review on automatic website generation. Journal of Computer Languages, 75, 101202. https://doi.org/10.1016/j.cola.2023.101202

Kocaballi, B. (s.d.). Conversational AI-powered design: ChatGPT as designer, user and product. University of Technology Sydney.

Lewis, P., et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems (NeurIPS 2020).

Norman, D. A. (2013). The design of everyday things (Rev. ed.). MIT Press.

OpenAI, et al. (2023). GPT-4 technical report. arXiv. https://arxiv.org/abs/2303.08774

Rodriguez, D. V., et al. (2024). Leveraging generative AI tools to support the development of digital solutions in health care research: Case study. JMIR Human Factors, 11(1), e52885. https://doi.org/10.2196/52885

Shumakova, N. I., Lloyd, J. J., & Titova, E. V. (2023). Towards legal regulations of generative AI in the creative industry. Journal of Digital Technologies and Law, 1(4), 880–908.

Velásquez-Henao, J. D., Franco-Cardona, C. J., & Cadavid-Higuita, L. (2023). Prompt engineering: A methodology for optimizing interactions with AI-language models in the field of engineering. Revista DYNA, 90(230), 9–17. https://doi.org/10.15446/dyna.v90n230.111700.