BotGBIF: A tool to query GBIF data in natural language

Authors

  • Marcos Zárate Universidad Nacional de la Patagonia San Juan Bosco, Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Argentina https://orcid.org/0000-0001-8851-8602
  • Gustavo Nuñez Universidad Nacional de la Patagonia San Juan Bosco, Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Argentina https://orcid.org/0009-0007-0215-2699
  • Dario Ceballos Universidad Abierta Interamericana, Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Argentina https://orcid.org/0009-0002-9207-7023
  • Macarena Repetto Universidad Nacional de la Patagonia San Juan Bosco, Argentina
  • Nora Morgan Universidad de Buenos Aires, Argentina

Keywords:

GPT4, large language model, API rest, GBIF

Abstract

This project introduces BotGBIF, a prototype chatbot designed to enhance user access to biodiversity data from the Global Biodiversity Information Facility (GBIF) through natural language queries. Utilizing the Python Streamlit library for the frontend, the GBIF REST API for data retrieval, and the capabilities of GPT-4 as a large language model (LLM), BotGBIF aims to simplify the interaction with complex datasets for users who may lack technical expertise in utilizing the GBIF portal. By integrating the GBIF API with GPT-4, the chatbot allows users to ask questions in everyday language and receive intuitive responses, thereby making biodiversity data more accessible to a range of stakeholders, including researchers, conservationists, and the general public. 

Downloads

Published

2025-10-15

Issue

Section

ASAID - Argentine Symposium on Artificial Intelligence and Data Science

How to Cite

Zárate, M., Nuñez, G., Ceballos, D., Repetto, M., & Morgan, N. (2025). BotGBIF: A tool to query GBIF data in natural language. JAIIO, Jornadas Argentinas De Informática, 11(1), 221-234. https://revistas.unlp.edu.ar/JAIIO/article/view/19797