LLM-Based conversational assistant for technical recommendations in banana cultivation
DOI:
https://doi.org/10.35381/i.p.v8i14.4885Keywords:
Agriculture, crop, banana, artificial intelligence, information retrieval, (UNESCO Thesaurus).Abstract
This work consisted of developing a conversational assistant to provide technical recommendations for banana cultivation in response to the limited technical assistance available to small producers. The CRISP-DM methodology was applied for development, and an approach combining information retrieval and response generation supported by a language model was used, with integration into Telegram for text and voice interaction, storage of dialogue history, and consultation of a corpus of 61 official technical documents from Latin American institutions. The results were obtained through a survey of 13 agronomy specialists using user experience criteria, which reported a high mean rating and full acceptance regarding applicability, domain delimitation, conversational memory, and usability, as well as high acceptance in technical validity and clarity. In conclusion, the assistant proved feasible for supporting good phytosanitary practices, with the possibility of being extended to other crops.
Downloads
References
Ariyo Okaiyeto, S., Bai, J., Wang, J., Mujumdar, A., Xiao, H. (2025). Success of DeepSeek and potential benefits of free access to AI for global-scale use. International Journal of Agricultural and Biological Engineering, 18(1), 304-306. https://doi.org/10.25165/j.ijabe.20251801.9733
Becerra-Encinales, J. F., Bernal-Hernandez, P., Beltrán-Giraldo, J. A., Cooman, A. P., Reyes, L. H., y Cruz, J. C. (2024). Agricultural Extension for Adopting Technological Practices in Developing Countries: A Scoping Review of Barriers and Dimensions. Sustainability, 16(9), 3555. https://doi.org/10.3390/su16093555
Boros, A., Szólik, E., Desalegn, G., y Tőzsér, D. (2025). A Systematic Review of Opportunities and Limitations of Innovative Practices in Sustainable Agriculture. Agronomy, 15(1), 76. https://doi.org/10.3390/agronomy15010076
Caffaro, F., y Rizzo, G. (2024). Knowledge-Enhanced Conversational Agents. Journal of Computer Science and Technology, 39(3), 585-609. https://doi.org/10.1007/s11390-024-2883-4
Calvo-Valverde, L.-A., Rojas-Salazar, K., Hidalgo-Rodríguez, J. F., Mora, V., Sandoval, J. A., Bolaños-Céspedes, E., & Quirós, C. (2023). Un estudio de tecnologías sobre agentes conversacionales para la asistencia de agricultores del plátano. Revista Tecnología En Marcha, 36(4), 3-18. https://doi.org/10.18845/tm.v36i4.6242
Coggins, S., Munshi, S., Smith, J., Yadav, A. K., Poonia, S. P., Patil, S., Singh, N. K., Sawarn, A., Ireland, D. C., McDonald, A. J., Singh, D. K., Sherpa, S. R., y Craufurd, P. (2025). How do chat apps support the use of farming videos in agricultural extension: A case study from Bihar, India. NJAS: Impact in Agricultural and Life Sciences, 97(1), 2420803. https://doi.org/10.1080/27685241.2024.2420803
Esguera, J. G., Balendres, M. A., Paguntalan, D. P. (2024). Overview of the Sigatoka leaf spot complex in banana and its current management. Tropical Plants, 3(1). https://doi.org/10.48130/tp-0024-0001
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., y Wang, H. (2023). Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv. https://doi.org/10.48550/ARXIV.2312.10997
Graham, C., y Roll, N. (2024). Evaluating OpenAI’s Whisper ASR: Performance analysis across diverse accents and speaker traits. JASA Express Letters, 4(2), 025206. https://doi.org/10.1121/10.0024876
Guamán-Rivera, S. A. (2022). Desarrollo de Políticas Agrarias y su Influencia en los Pequeños Agricultores Ecuatorianos. Revista Científica Zambos, 1(3), 15-28. https://doi.org/10.69484/rcz/v1/n3/30
Gupta, S., Ranjan, R., y Singh, S. N. (2024). A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions. arXiv. https://doi.org/10.48550/ARXIV.2410.12837
Ibrahim, A., Senthilkumar, K., y Saito, K. (2024). Evaluating responses by ChatGPT to farmers’ questions on irrigated lowland rice cultivation in Nigeria. Scientific Reports, 14(1), 3407. https://doi.org/10.1038/s41598-024-53916-1
Kim, T.-S., John Ignacio, M., Yu, S., Jin, H., y Kim, Y.-G. (2024). UI/UX for Generative AI: Taxonomy, Trend, and Challenge. IEEE Access, 12, 179891-179911. https://doi.org/10.1109/ACCESS.2024.3502628
Klesel, M., y Wittmann, H. F. (2025). Retrieval-Augmented Generation (RAG). Business & Information Systems Engineering, 67(4), 551-561. https://doi.org/10.1007/s12599-025-00945-3
Korir, M. K., Mwangi, W., y Kimwele, M. W. (2023). Artificial Intelligence-Based Chatbot Model Providing Expert Advice to Potato Farmers in Kenya. 2023 IEEE AFRICON, 1-6. https://doi.org/10.1109/AFRICON55910.2023.10293557
Kuska, M. T., Wahabzada, M., y Paulus, S. (2024). AI for crop production – Where can large language models (LLMs) provide substantial value? Computers and Electronics in Agriculture, 221, 108924. https://doi.org/10.1016/j.compag.2024.108924
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., y Kiela, D. (2021, abril). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv. https://doi.org/10.48550/arXiv.2005.11401
Lubawa, A. R., Nyambo, D. G., Mduma, N., y Sinde, R. (2025). A Response-by-Retrieval Chatbot for Enhancing Horticulture Extension Services in Tanzania. Engineering, Technology y Applied Science Research, 15(5), 27703-27709. https://doi.org/10.48084/etasr.12761
Munhoz, T., Vargas, J., Teixeira, L., Staver, C., y Dita, M. (2024). Fusarium Tropical Race 4 in Latin America and the Caribbean: Status and global research advances towards disease management. Frontiers in Plant Science, 15. https://doi.org/10.3389/fpls.2024.1397617
Peñalver-Higuera, M. J., Rodríguez-Alegre, L. R., López-Padilla, R. D. P., y Isea-Argüelles, J. J. (2025). Ingeniería de prompts en la industria 4.0: Optimización y automatización inteligente de procesos industriales. Ingenium et Potentia, 7(12), 35–49. https://doi.org/10.35381/i.p.v7i12.4438
Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., y Sutskever, I. (2022, diciembre). Robust Speech Recognition via Large-Scale Weak Supervision. arXiv. https://doi.org/10.48550/arXiv.2212.04356
Romero-García, C. V., Saraguro-Reyes, C. M., Mazon-Olivo, B. E., y Morocho-Román, R. F. (2025). Agricultura de precisión en la producción de banano. Revisión sistemática. Ingenium et Potentia, 7(12), 50-76. https://doi.org/10.35381/i.p.v7i12.4450
Samuel, D. J., Skarga-Bandurova, I., Sikolia, D., y Awais, M. (2025). AgroLLM: Connecting Farmers and Agricultural Practices through Large Language Models for Enhanced Knowledge Transfer and Practical Application. arXiv. https://doi.org/10.48550/ARXIV.2503.04788
Sapkota, R., Qureshi, R., Usman Hadi, M., Zohaib Hassan, S., Sadak, F., Shoman, M., Sajjad, M., Ali Dharejo, F., Paudel, A., Li, J., Meng, Z., Shutske, J., y Karkee, M. (2025). Multi-Modal LLMs in Agriculture: A Comprehensive Review. IEEE Transactions on Automation Science and Engineering, 22, 22510-22540. https://doi.org/10.1109/TASE.2025.3612154
Singh, N., Wang’ombe, J., Okanga, N., Zelenska, T., Repishti, J., K, J. G., Mishra, S., Manokaran, R., Singh, V., Rafiq, M. I., Gandhi, R., y Nambi, A. (2024). Farmer.Chat: Scaling AI-Powered Agricultural Services for Smallholder Farmers. arXiv. https://doi.org/10.48550/ARXIV.2409.08916
Spielman, D., Lecoutere, E., Makhija, S., y Van Campenhout, B. (2021). Information and Communications Technology (ICT) and Agricultural Extension in Developing Countries. Annual Review of Resource Economics, 13(1), 177-201. https://doi.org/10.1146/annurev-resource-101520-08065
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Gabriel Emilio García-Mazón, Bryan Steve Moreno-Morocho, Wilmer Rivas-Asanza, Eduardo Tusa-Jumbo
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
CC BY-NC-SA : Esta licencia permite a los reutilizadores distribuir, remezclar, adaptar y construir sobre el material en cualquier medio o formato solo con fines no comerciales, y solo siempre y cuando se dé la atribución al creador. Si remezcla, adapta o construye sobre el material, debe licenciar el material modificado bajo términos idénticos.
OAI-PMH URL: https://fundacionkoinonia.com.ve/ojs/index.php/ingeniumetpotentia/oai
