import gradio as gr
from huggingface_hub import InferenceClient

# لاحظ: يجب تمرير التوكن بطريقة أخرى، مثلاً عبر متغير بيئة أو إعدادات المساحة
# هنا ننشئ العميل بدون توكن (إذا النموذج يسمح)
client = InferenceClient("mradermacher/airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp-GGUF")

def respond(messages, system_message, max_tokens, temperature, top_p):
    chat_messages = [{"role": "system", "content": system_message}] + messages

    response = ""
    prompt = ""
    for msg in chat_messages:
        role = msg.get("role", "")
        content = msg.get("content", "")
        if role == "system":
            prompt += f"System: {content}\n"
        elif role == "user":
            prompt += f"User: {content}\n"
        elif role == "assistant":
            prompt += f"Assistant: {content}\n"
    prompt += "Assistant: "

    generation = client.text_generation(
        prompt,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=True,
    )

    for token in generation:
        response += token.text
        yield response

demo = gr.ChatInterface(
    fn=respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
    type="messages",
)

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