EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Design and Evaluation of a Retrieval-Augmented Generation LLM Chatbot with Structured Database Access

Juan Burbano, Pablo Landeta-López, Cathy Guevara-Vega, Antonio Quiña-Mera

Applied Sciences · 25.03.2026 · 16 (7) · 3147

DOI: 10.3390/app16073147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 25.03.2026. Verfasst von Juan Burbano und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Técnica del Norte.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Context

The grocery sector is undergoing a massive shift in consumer behavior, with global chatbot usage projected to reach 8.4 billion units by 2024—surpassing the total human population—and online grocery revenue per shopper expected to hit USD 449.00 by 2023. In this competitive landscape, small grocery stores must adopt AI-driven tools to modernize their operations. However, these businesses often face significant inefficiencies in manual inventory management, resulting in errors and reduced competitiveness.

Objective

This research aims to develop and validate a chatbot application using Large Language Models and Retrieval-Augmented Generation (RAG) for operational management of grocery stores.

Method

The method employed a quantitative experimental approach with a five-component system architecture: a web interface, a FastAPI API, a Mistral-7B-Instruct-v0.2 model, a dynamic SQL generator, and a custom RAG application with an FAISS vector database, all integrated through SQLAlchemy 2.0.40.

Results

The results demonstrate that a chatbot achieves an average response time of 0.08 s with 80% overall accuracy, showing a 96.2% improvement in information query time and a 92.9% reduction in operational errors.

Conclusions

Major conclusions suggest that the chatbot system is effective for retail environments and has the potential to enhance the operational efficiency of grocery stores, serving as a foundation for future research in applied conversational assistance.

Förderung

  • Universidad Técnica del Norte

Zitieren

APA

Burbano, J., Landeta-López, P., Guevara-Vega, C., & Quiña-Mera, A. (2026). Design and Evaluation of a Retrieval-Augmented Generation LLM Chatbot with Structured Database Access. Applied Sciences, 16(7), 3147. https://doi.org/10.3390/app16073147

Vancouver

Burbano J, Landeta-López P, Guevara-Vega C, Quiña-Mera A. Design and Evaluation of a Retrieval-Augmented Generation LLM Chatbot with Structured Database Access. Applied Sciences. 2026;16(7):3147. doi:10.3390/app16073147

BibTeX
@article{Burbano2026,
  author = {Burbano, Juan and Landeta-López, Pablo and Guevara-Vega, Cathy and Quiña-Mera, Antonio},
  title = {Design and Evaluation of a Retrieval-Augmented Generation LLM Chatbot with Structured Database Access},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {7},
  pages = {3147},
  doi = {10.3390/app16073147}
}
Kostenlos starten →