model_api.py

from huggingface_hub import InferenceClient
import os
from dotenv import load_dotenv

load_dotenv()

def query_model(prompt):

    HF_TOKEN = os.getenv("HF_TOKEN")

    client = InferenceClient(
        model="meta-llama/Llama-3.2-3B-Instruct",
        token=HF_TOKEN
    )

    response = client.chat_completion(
        messages=[
            {"role": "system", "content": "You are a professional fitness trainer."},
            {"role": "user", "content": prompt}
        ],
        max_tokens=800,
        temperature=0.7
    )

    return response.choices[0].message.content