Resumo:
This article explores the application of large language models (LLM) in the oil and gas  sector, specifically within well construction and maintenance tasks. The study evaluates the performances of a single-agent and a multi-agent LLM-based architecture in processing different tasks, offering a comparative perspective on their accuracy and the cost implications of their implementation. The results indicate that multi-agent systems offer improved performance in question and answer tasks, with a truthfulness measure 28% higher than single-agent systems, but at a higher financial cost. Specifically, the multi-agent architecture incurs costs that are, on average, 3.7 times higher than those of the single-agent setup due to the increased number of tokens processed. Conversely, single-agent systems excel in text-to-SQL (Structured Query Language) tasks, particularly when using Generative Pre-Trained Transformer 4 (GPT-4), achieving a 15% higher score compared to multi-agent configurations, suggesting that simpler architectures can sometimes outpace complexity. The novelty of this work lies in its original examination of the specific challenges presented by the complex, technical, unstructured data inherent in well construction operations, contributing to strategic planning for adopting generative AI applications, providing a basis for optimizing solutions against economic and technological parameters.