[0:00] Feeback
[7:45] Review of RAG, from mild to wild
[17:23] Weights and Biases Prompts for caching, tracing, debugging, etc.
[25:13] Tracing and Caching with WandB Demo
[50:45] LangSmith Overview and Demo of Monitoring a RAG System
[1:07:45] Final Project Overview
[1:12:20] The Big Picture of LLM Ops, from a16z
[1:18:35] Conclusions
Course Materials:
🧑💻 GitHub Repository of Visibility Tools in LLM Ops: https://github.com/AI-Maker-Space/LLM-Ops-Cohort-1/tree/main/Week%204/Tuesday
🧑🏫 Slide Deck: https://www.canva.com/design/DAFtJGudEEk/bgY71J31OQwdrF_tr4aiww/edit?utm_content=DAFtJGudEEk&utm_campaign=designshare&utm_medium=link2&utm_source=sharebutton