app.py

import os
#from huggingface_hub import InferenceApi
#import streamlit as st

#x = st.slider('Select a value')
#st.write(x, 'squared is', x * x)

# Get the API key from the environment variable 
api_key = os.getenv("HF_API_KEY")

# Initialize the Inference API with your model and API key 
#api = InferenceApi(repo_id="gpt-3", token=api_key)




from huggingface_hub import InferenceClient

client = InferenceClient(api_key=api_key)

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

completion = client.chat.completions.create(
    model="Qwen/Qwen2.5-Coder-32B-Instruct", 
	messages=messages, 
	max_tokens=500
)

print(completion.choices[0].message)