app.py

import gradio as gr
from huggingface_hub import InferenceClient

# මෙහි ඔබේ Token එක කෙලින්ම ඇතුළත් කරන්න
client = InferenceClient("Qwen/Qwen2.5-1.5B-Instruct", token="HF_TOKEN")

def respond(message, history):
    messages = [{"role": "system", "content": "You are MINZO AI, a strategic assistant for Commander MINZO-PRIME."}]
    
    for val in history:
        if val[0]: messages.append({"role": "user", "content": val[0]})
        if val[1]: messages.append({"role": "assistant", "content": val[1]})

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

    response = ""
    for message in client.chat_completion(
        messages,
        max_tokens=1024,
        stream=True,
        temperature=0.7,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response

demo = gr.ChatInterface(respond)

if __name__ == "__main__":
    demo.launch()