import urllib
import chatglm_cpp
import gradio as gr

DEFAULT_MODEL_PATH = "chatglm3-6b.bin"
urllib.request.urlretrieve(
    "https://huggingface.co/Braddy/chatglm3-6b-chitchat/resolve/main/q5_1.bin?download=true", 
    DEFAULT_MODEL_PATH
    )


pipeline = chatglm_cpp.Pipeline(DEFAULT_MODEL_PATH)
system_message = chatglm_cpp.ChatMessage(role="system", content="请你现在扮演一个软件工程师，名字叫做贺英旭。你需要以这个身份和朋友们对话。")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_new_tokens,
    temperature,
    top_p,
):
    messages = [chatglm_cpp.ChatMessage(role="system", content=system_message)]
    # messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            # messages.append({"role": "user", "content": val[0]})
            messages.append(chatglm_cpp.ChatMessage(role="user", content=val[0]))
        if val[1]:
            messages.append(chatglm_cpp.ChatMessage(role="assistant", content=val[1]))

    messages.append(chatglm_cpp.ChatMessage(role="user", content=message))

    generation_kwargs = dict(
        max_new_tokens=max_new_tokens,
        do_sample=temperature > 0,
        top_p=top_p,
        temperature=temperature,
        stream=True,
    )

    response = ""
    for chunk in pipeline.chat(messages, **generation_kwargs):
        response += chunk.content
        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()