Fix: use pre-built CPU wheel for llama-cpp-python to avoid build timeout

Fix: run uvicorn directly + use root_path='' to fix Gradio UI on HF Spaces

Fix: unpin llama-cpp-python to get newer version without __del__ bug

Fix: use root_path='' in mount_gradio_app to fix static asset 404s

Fix: add demo.queue() before demo.app to fix Jinja2 None error

Fix: use demo.app to fix broken UI (Invalid port/static asset 404s)

Fix: use demo.app to fix broken static assets and Invalid port errors

Fix: use demo.app instead of gr.mount_gradio_app to fix static asset 404s and Invalid port errors

Update app.py

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update requirements.txt

Update app.py

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Create requirements.txt

Update app.py

initial commit

Duplicate from gradio-templates/chatbot