"""Example FastAPI server for llama.cpp.

To run this example:

```bash
pip install fastapi uvicorn sse-starlette
export MODEL=../models/7B/...
```

Then run:
```
uvicorn llama_cpp.server.app:app --reload
```

or

```
python3 -m llama_cpp.server
```

Then visit http://localhost:8000/docs to see the interactive API docs.

"""
import os
import uvicorn

from llama_cpp.server.app import app, init_llama

if __name__ == "__main__":
    init_llama()

    uvicorn.run(
        app, host=os.getenv("HOST", "localhost"), port=int(os.getenv("PORT", 8000))
    )