llm.py

import os
import requests

HF_TOKEN = os.environ["HF_TOKEN"]
MODEL = os.getenv("HF_MODEL", "Qwen/Qwen3-8B")

def chat(messages):

    r = requests.post(
        "https://router.huggingface.co/v1/chat/completions",
        headers={
            "Authorization": f"Bearer {HF_TOKEN}"
        },
        json={
            "model": MODEL,
            "messages": messages
        }
    )

    return r.json()["choices"][0]["message"]["content"]