app.py

import streamlit as st
from huggingface_hub import InferenceClient
import os

# Retrieve the Hugging Face token from environment variables
hf_token = os.getenv("HF_TOKEN")

# Initialize the Hugging Face Inference Client
client = InferenceClient(
    model="Qwen/Qwen2-7B",
    token=hf_token,
)

def get_chat_completion(message):
    try:
        response = client.chat_completion(
            messages=[{"role": "user", "content": message}],
            max_tokens=500,
            stream=False,
        )
        completion = response[0]['choices'][0]['message']['content']
        return completion
    except Exception as e:
        return f"Error: {e}"

# Streamlit app layout
st.title("Chat with Hugging Face Model")

# Input from the user
user_input = st.text_input("Enter your message:")

if st.button("Send"):
    if user_input:
        # Get response from the model
        response = get_chat_completion(user_input)
        st.write("**Response:**")
        st.write(response)
    else:
        st.write("Please enter a message.")