2025-11-09 –, Tutorial Track 2
LLMs have a lot of hype around them these days. Let’s demystify how they work and see how we can put them in context for data science use. As data scientists, we want to make sure our results are inspectable, reliable, reproducible, and replicable. We already have many tools to help us in this front. However, LLMs provide a new challenge; we may not always be given the same results back from a query. This means trying to work out areas where LLMs excel in, and use those behaviors in our data science artifacts. This talk will introduce you to LLMs, the Chatlas packages, and how they can be integrated into a Shiny to create an AI-powered dashboard (using querychat). We’ll see how we can leverage the tasks LLMs are good at to better our data science products.
This talk will introduce the applications of the Chatlas python package to interface with multiple LLM providers and how we can create inspectable data science artifacts.
Breakdown:
0-5: introduction to LLMs
5-15: anatomy of a conversation
15-20: the Chatlas package
20-25: Basic chatlas code examples and output
25-30: tool calls
30-35: LLMs with dashboards using querychat
35-40: Q+A
No previous knowledge expected
Lecturer at the University of British Columbia and Data Science Educator at Posit, PBC