import gradio as gr
# from huggingface_hub import InferenceClient
from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "12345"
openai_api_base = "https://a502-131-112-63-87.ngrok-free.app/v1"
model_name = "cyberagent/calm3-22b-chat"
"""
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("HuggingFaceH4/zephyr-7b-beta")
client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    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 = ""

    """
    #streaming無し: gradio側が対応してない
    completion = client.chat.completions.create(model=model_name,
                                                messages=messages,
                                                temperature=temperature,
                                                max_tokens=max_tokens,
                                                top_p=top_p,
                                                )
    text = completion.choices[0].message.content.strip()
    return text
    """
    for message in client.chat.completions.create(
        model=model_name,
        messages=messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        # response += token
        if token is not None:
            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,
    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()