app.py

import os
import streamlit as st
from huggingface_hub import InferenceClient

client = InferenceClient(api_key=os.environ['HF_KEY'])

messages = [
	{
		"role": "user",
		"content": "What is the capital of France?"
	}
]

stream = client.chat.completions.create(
    model="HuggingFaceTB/SmolLM2-1.7B-Instruct", 
	messages=messages, 
	max_tokens=500,
	stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="")