This chatbot is created using the open-source Llama 2 LLM model from Meta. The models are hosted on the Replicate platform. The app is built with Streamlit and deployed on Streamlit Community Cloud.
The code is adapted from this repository.
pip install -r requirements.txt
streamlit run app.py
docker build -t llama2 .
docker run -p 8501:8501 -v $(pwd):/app llama2
To use this app, you'll need to get your own Replicate API token.
After signing up to Replicate, you can access your API token from this page.
Learn how to build this app in this blog!