Overview

Overview#

Avoid the privacy issues of sending prompts to cloud based large language models (LLMs like ChatGPT) by installing and managing a local instance of Ollama, an open source downloadable LLM and API. We’ll set up a chatbot and practice directly querying the LLM for generative outputs, text clustering, and classification.

Learning Goals#

After completing this workshop, learners should be able to:

  • Describe control, customization, and data privacy issues of cloud-based AI systems

  • Install Ollama in your local environment

  • Deploy and a chatbot

  • Deploy a Retrieval-Augmented Generation (RAG) application

  • Understand how to conduct text clustering and classification on a corpus using LLMs

Prerequisites#

This workshop is not an introduction to programming; learners should have basic fluency in Python if they would like to code along.

Computing Requirements#

To code along during the workshop users must have:

  • A local computer on which they have administrative rights to install software

  • A working Python environment such as Jupiter, VSCode, or via the Command Line.

Contents