This is the code that we used in the July 23 and August 23 The Scoop on Embedding: Teaching Large Language Models the “Flavor of the Day” at Culvers demo. This is a command line interface (CLI) app but you can expand it to be a web service. This should run on a Windows PC but these instructions assume that you are using MacOS.
- Install Ollama on your computer
- Pull down this project from Github
- Navigate to the project folder in iterm2 (or Terminal)
- Pull down llama3
ollama pull llama3:8b
- Pull down nomic-embed-text
ollama pull nomic-embed-text
- Set up your Python virtual environment
pip3 install virtualenv
(if needed)python3 -m venv ragdemo
source ragdemo/bin/activate
- Install ollama, chromadb, and requests
pip3 install ollama
pip3 install requests
pip3 install chromadb
- Run the app (making an actual query)
python3 app.py "What is today's custard flavor at the Port Washington location?"