FastAPI with ollama on Fly.io

app.py

import os
from fastapi import FastAPI
from ollama import AsyncClient

OLLAMA_HOST = os.getenv('OLLAMA_HOST')
ollama_client = AsyncClient(OLLAMA_HOST)
app = FastAPI()

@app.get("/")
async def read_root():
    resp = await ollama_client.generate(
        model="llama3.1",
        prompt="Why is the sky not green?",
    )
    return resp