Loads of golden nuggets of experience and practical use cases in this excellent deep-dive on LLM-based applications in production. What happens when you start using LLM-based applications at scale? Or when the dataset used to calculate the embeddings is very large? Or when you rely on LLMs for critical parts of your infrastructure and want to use zero downtime deployments and canary rollouts?
Well spoken Philipp Moritz & Yifei Feng , Demetrios Brinkmann, thank you for sharing 🙏
https://www.linkedin.com/video/live/urn:li:ugcPost:7114994414636126212/?isInternal=true