Make sure you have ollama installed locally (https://ollama.com/)
ollama run llama3
pipenv shell
pip install -r requirements.txt
- LLM with UI (Gradio)
python main.py
head over to [http://127.0.0.1:7860]
- LLM without UI (Console)
python run-without-ui.py
- Quite and Fast with Open WebUI (suggested)
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
head over to [http://127.0.0.1:3000]