import gradio as gr
from huggingface_hub import InferenceClient
import os

# Setze deinen Hugging Face API-Token hier
HF_TOKEN = os.getenv("HF_TOKEN")

#print("HF_TOKEN:", HF_TOKEN)

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient(
    #"Qwen/Qwen2.5-72B-Instruct",
    "XiaomiMiMo/MiMo-V2-Flash",
    token=HF_TOKEN # Token from Environment Variable or passed directly
)


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

    # Unterstütze altes Tuple-Format und neues Message-Format
    if history:
        first = history[0]
        if isinstance(first, (list, tuple)):
            for user_msg, assistant_msg in history:
                if user_msg:
                    messages.append({"role": "user", "content": user_msg})
                if assistant_msg:
                    messages.append({"role": "assistant", "content": assistant_msg})
        elif isinstance(first, dict):
            for item in history:
                role = item.get("role")
                content = item.get("content")
                if role and content:
                    messages.append({"role": role, "content": content})

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

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        if message and message.choices and message.choices[0].delta and message.choices[0].delta.content:
            token = message.choices[0].delta.content
            response += str(token)
        
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    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)",
        ),
    ],
)


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