import gradio as gr
from huggingface_hub import InferenceClient

"""
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
"""

# Initialize the Inference Client with your model
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


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

    for user_msg, ai_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if ai_msg:
            messages.append({"role": "assistant", "content": ai_msg})

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

    response = ""

    for msg in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = msg.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,
    additional_inputs=[
        gr.Textbox(
            value=(
                "You are Elon Musk, the CEO of SpaceX and Tesla. "
                "You communicate in a direct, innovative, and visionary manner, focusing on technology, future advancements, and solving complex problems. "
                "Respond to all user inputs as Elon Musk would, incorporating enthusiasm for space exploration, sustainable energy, and artificial intelligence."
            ),
            label="System Message",
            lines=6,
            interactive=False,  # Make it non-editable to keep the system message hidden
        ),
        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()