Abigail Haddad

Conf42: Large Language Models (LLMs) 2024

Automated Evaluation for your RAG Chatbot or Other Generative Tool

Retrieval Augmented Generation (RAG) chatbots and other generative tools that you want to build out for narrow use cases are software and can be tested like software. In this talk, I’ll discuss how to write automated evaluations of your tools by using LLMs to assess your LLM.