Text-to-SQL Using LLMs #6 - Test Dataset & Evaluations | LangGraph

In this video, I walk through building a test dataset for the Text-to-SQL project and explore evaluations using LangSmith. We create 17 golden ground-truth question–answer pairs and demonstrate how to measure model performance reliably. 🔗 GitHub Repo: https://github.com/v1jaysundaram/text2sql 🎥 Full Playlist: https://youtube.com/playlist?list=PLEHeb1HGikpQJvPlZEyrMLOjopsV5Ui_3&si=8dqEScL-uSyIskqx 🤝 Connect with me on LinkedIn: https://www.linkedin.com/in/vijay-sundaram/