Welcome to LLMs

Install + Setup

Take a look at the course website and go through the setup instructions: https://ubc-mds.github.io/DSCI_532_vis-2_book/

Url is at the bottom of all the slides.

Clone this repo
Install your R + Python packages
Download at least one of the Ollama models. Feel free to pick any other one.
(Optional) use the .env.template file to provide your API key into .env

Note

If you pay for Claude, OpenAI, etc access with their web/desktop application, this is a separate purchase for the API key. Depending on your usage, you may even find that paying for the API key could be cheaper!

Lesson Reference

https://www.youtube.com/watch?v=owDd1CJ17uQ

Also check the documentation

Chatlas: https://posit-dev.github.io/chatlas/
Ellmer: https://ellmer.tidyverse.org/index.html
Ragnar: https://ragnar.tidyverse.org/articles/ragnar.html
mcptools: https://posit-dev.github.io/mcptools/

Poll: Experience with LLMs

Used an LLM before (ChatGPT/Claude/Ollama desktop/web application)?
Used it for a homework assignment?
Tasks outside of school work?
Skeptical about LLMs/AI (1-2 out of 5)? Why?
Neutral about LLMs/AI (3 out of 5)? Why?
Enthusiastic about LLMs/AI (4-5 out of 5)? Why?

Today

Today, we will treat LLMs as black boxes
Practical introduction
Get some hands on practice to demystify using them

Goal

Quick Start course on LLMs. You will leave having used a Chat API.

Security

DO NOT send proprietary code or data to any LLM, unless you are sure IT policies allow it
Local models (e.g., Ollama) typically perform worse than frontier models