Monitoring LLMs in Production with Hugging Face & WhyLabs

Discover how to effectively monitor and manage Large Language Models (LLMs) in production using Hugging Face and WhyLabs in this comprehensive 1-hour 12-minute webinar. Learn about WhyLabs' powerful new tool, LangKit, designed for continuous monitoring and responsible operation of LLM applications. Gain practical knowledge on evaluating user interactions, configuring guardrails, and setting up monitors and alerts to prevent undesirable behavior. Explore techniques for troubleshooting and monitoring large language models, including evaluating prompts, responses, and user interactions, as well as detecting malicious prompts, toxic responses, hallucinations, and jailbreak attempts.