Abstract
Over the last 10 years, no industry has faced more pressure and scrutiny to gain efficiency than the oil and gas (O&G) industry. Drilling engineers are tasked with leveraging data to optimize design and operations. O&G companies have collected and stored large amounts of high-frequency sensor data and reporting data. Efficient data access is fundamental for upstream projects, and data operations skills are critical for drilling engineers. However, data operations have not become a core competency for most of the drilling engineering community.
A novel solution to this problem is proposed—a framework that, to the best of our knowledge, represents the first application of Text-to-SQL using LLMs within the Oil & Gas (O&G) domain, specifically designed to handle complex database structures. This paper presents a novel solution that bridges the gap between drilling engineers’ need for efficient data access and their lack of specialized data skills. Our Natural Language (NL) to SQL GenAI workflow transforms complex data transformation operations into a seamless process requiring no special expertise and delivering results within seconds. By converting natural language queries into SQL queries, this framework dynamically enriches users’ questions with relevant contextual information before processing them through a Large Language Model (LLM). This ensures that drilling engineers can quickly analyze multi-well data, address critical issues, and capture knowledge for future wells, all while overcoming the challenges of accessing and interpreting large SQL databases.
