import gradio as gr
from huggingface_hub import InferenceClient
import os
api_key=os.environ.get('qwen_API_KEY')
"""
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",token=api_key)
latex_delimiters = [
    {"left": "\\(", "right": "\\)", "display": False},
    {"left": "\\[", "right": "\\]", "display": True},
    {"left": "\\begin{equation}", "right": "\\end{equation}", "display": True},
    {"left": "\\begin{align}", "right": "\\end{align}", "display": True},
    {"left": "\\begin{alignat}", "right": "\\end{alignat}", "display": True},
    {"left": "\\begin{gather}", "right": "\\end{gather}", "display": True},
    {"left": "\\begin{CD}", "right": "\\end{CD}", "display": True},
]

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    latex_delimiters=None
):
    messages = [{"role": "system", "content": system_message}]

    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=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
        latex_delimiters=latex_delimiters
    ):
        token = message.choices[0].delta.content

        response += 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,
    examples=[["你好，你是谁?"], ["你是谁开发的？"]],
    cache_examples=False,
    title="千问2.5-72B",
    description="千问2.5-72B聊天机器人",
    additional_inputs=[
        gr.Textbox(value="You are Qwen, created by Alibaba Cloud. You are a helpful assistant.", label="System message"),
        gr.Slider(minimum=1, maximum=8888, value=2048, 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()