👋 Very Practical v*irtual series on LLM evals* starts this
Thursday, May 9 at 10am PT
As you may know, one area where LLMs with in-context learning show promise is in generating SQL queries from natural language. Achieving results is often tricky in practice, given the difficulty in understanding what is happening under the hood with RAG workflows. We’ll address a scalable technique to evaluate LLMs, and key considerations and best practices for LLM evaluation in router setups.
Session 1: May 9, 10am PT |
SQL Generation Evals: LLMs-as-a-Judge
Session 2: May 16, 10am PT |
LLM Evals for Router-Based Architectures
https://arize.com/resource/sql-gen-and-router-evals/