Seattle LLMs and Unstructured Data, September
If you're interested in learning about LLMs, and how to evaluate them, come learn from the best in the industry with us on Thursday, September 5th from 5 to 8pm at the Microsoft Reactor!
Agenda:
5:00 - 5:30: Arrival
5:30 - 5:40: Introduction
5:45 - 6:15: Evaluating LLM Agents, Arize AI
6:20 - 6:50: Agentic RAG w/ LlamaIndex, Yujian Tang
6:55 - 8:00: Networking
Talk Abstracts
Evaluating LLM Agents
This talk will outline strategies and technologies you can use to evaluate the performance of LLM Agents. Whether you're developing agents via a framework like LlamaIndex Workflows or LangGraph or programming the routing logic by hand, tracking the performance of your agent across each step of its journey is extremely difficult. We'll show how you can use Arize Phoenix to run structured evaluations on your agentic applications, and measure the true performance increases with each improvement you make.
Agentic RAG w/ LlamaIndex
This talk covers how to build an AI Agent to perform RAG using LlamaIndex. We'll cover the different pieces of AI Agents and RAG as well as how to put them together using LlamaIndex, a leading framework in LLM orchestration.