LLM Observability and Evaluations

LLM Observability and Evaluations

Explore LLM observability and evaluations in this 11-minute video from Data Council featuring Amber Roberts, ML Engineer & Community Leader at Arize AI. Gain insights into debugging high-level abstractions in LLM-powered applications using LangChain and LlamaIndex. Learn how to leverage Arize Phoenix modules to streamline development and maintenance processes for large language models. Discover industry knowledge, technical architectures, and best practices for building cutting-edge data and AI systems. Enhance your understanding of LLM application complexities and improve your ability to evaluate and observe their performance effectively.