This workshop will introduce how Retrieval-Augmented Generation (RAG) works and how to set up a RAG system on your own device using Ollama, LlamaIndex, and Chroma DB. You’ll explore how RAG improves AI-generated responses by retrieving relevant information from a vector database. We’ll guide you through installing and configuring the necessary tools and demonstrate how to store and query your data. By the end, you’ll be able to efficiently retrieve and generate answers based on your local documents!
| Content | Time estimate | Description |
|---|---|---|
| Exercise 0 | 10 minutes | Getting your python environment ready |
| Exercise 1 | 20 minutes | Get started with Ollama |
| Exercise 2 | 30 minutes | Ingest some documents |
| Exercise 3 | 10 minutes | Your first RAG |
| Exercise 4 | 40 minutes | Explore further |
- A Python 3.11 environment
- Jupyter Notebook set up
Basic python