app.py

import gradio as gr
import random 
from huggingface_hub import InferenceClient

client = InferenceClient("Qwen/Qwen2.5-7B-Instruct")

def random_response(message, history):
    messages = [{"role": "system", "content": "You are a friendly chatbot"}]

    if history:
        messages.extend(history)
    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=1000,
        stream=True
    ):
        token = message.choices[0].delta.content

        if token is not None:
            response += token
            yield response

    #response_options = ["yes", "no", "I need more cosmic energy to answer.", "Very doubtful.", "Signs point to yes."]
    #return random.choices[0].message.content.strip()
    
chatbot = gr.ChatInterface(random_response, title="Chatbot")

chatbot.launch()