Requirements

• Docker
• Ollama

Setup

• Grab the embedding model: ollama pull mxbai-embed-large
• Grab the LLM: ollama pull llama3.1

Startup

• docker compose up

In the console, the app logs will tell you port the application is running on, typically http://localhost:3000/

The application is broken into a number of sections which demonstrate the data store, the embedding process, the vector store and then a full RAG chatbot.