Text-to-SQL: chat with a DB exploiting the Generative AI

John Lathouwers - Oracle / Corrado De Bari - Oracle

The endeavor to translate natural language queries into SQL has been a long-standing objective within the realm of computational linguistics and database management. Recent advancements in Generative Artificial Intelligence mark a pivotal moment in this journey. Current benchmarks have showcased that Large Language Models (LLMs) extend their utility beyond mere code generation to embrace specialized tasks such as Text-to-SQL conversion. This seminar aims to explore the cutting-edge developments in this field, highlighting effective methodologies based on frameworks that transcend the traditional tools and languages commonly associated with data science, like Spring Boot and the innovative “Spring AI” APIs, showing how these modern frameworks can facilitate equally the development of a bridge between natural language processing and database interaction.