Run your LLMs Locally with Ollama

This is a quick demo of how to get a fully local model up and running with Mistral 7b.

Ollama, an accessible tool for MacOS, Linux, and Windows users, offers seamless installation from its official website https://ollama.com/download.

just open your terminal & run:

$ ollama run mistral

Clone this repository and run the below command from this Repository to install the dependencies

$ pip install -r requirements.txt

A very simple streamlit app that demonstrates how to use LLM chat in a web app.

$ streamlit run chatbot_app.py

In terminal you will see a local host link, click on it to open the app in your browser.

example: http://localhost:8501