Yingjun Wu is the founder of RisingWave Labs, a database company developing RisingWave, a distributed SQL database for stream processing. Before running the company, Yingjun was a software engineer at the Redshift team, Amazon Web Services, and a researcher at the Database group, IBM Almaden Research Center. Yingjun received his PhD degree from National University of Singapore, and was a visiting PhD at Carnegie Mellon University. He has been working in the field of stream processing and database systems for over a decade.
Revolutionizing Text Transformation: Going Beyond Standard SQL with LLM.
This talk presents an innovative approach that leverages Large Language Models (LLMs) to transform text into SQL and its extensions, addressing the challenges of different SQL dialects and specialized domains such as stream processing and graph processing. While existing LLM-based solutions excel at converting text to standard SQL, our novel mechanism takes it a step further by directly transforming text to streaming SQL, thereby lowering the barrier for stream processing.
We explore the intricacies of various SQL dialects and highlight the limitations of traditional LLM-based approaches. By harnessing the power of LLMs, we showcase the advantages of our solution, including reduced development time, improved query performance, and enhanced flexibility in handling real-time data. Join us to discover how this transformative approach revolutionizes stream processing workflows, opening up new possibilities for innovation in this rapidly evolving field.