app.py

import os
from huggingface_hub import InferenceClient

client = InferenceClient(
    api_key=os.environ["HF"],
)

stream = client.chat.completions.create(
    model="deepreinforce-ai/Ornith-1.0-9B:featherless-ai",
    messages=[
        {
            "role": "user",
            "content": "What is the capital of France?"
        }
    ],
    stream=True,
)

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