import gradio as gr
from huggingface_hub import InferenceClient

MODELS = {
    "Zephyr 7B Beta": "HuggingFaceH4/zephyr-7b-beta",
    "DeepSeek Coder V2": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
    "Meta Llama 3.1 8B": "meta-llama/Meta-Llama-3.1-8B-Instruct",
    "Mixtral 8x7B": "mistralai/Mixtral-8x7B-Instruct-v0.1",
    "Cohere Command R+": "CohereForAI/c4ai-command-r-plus",
}

def get_client(model_name):
    return InferenceClient(MODELS[model_name])

def respond(
    message,
    chat_history,
    model_name,
    max_tokens,
    temperature,
    top_p,
    system_message,
):
    client = get_client(model_name)
    messages = [{"role": "system", "content": system_message}]

    for human, assistant in chat_history:
        messages.append({"role": "user", "content": human})
        messages.append({"role": "assistant", "content": assistant})

    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,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response

with gr.Blocks() as demo:
    gr.Markdown("# Advanced AI Chatbot")
    gr.Markdown("Chat with different language models and customize your experience!")

    with gr.Row():
        with gr.Column(scale=1):
            model_name = gr.Radio(
                choices=list(MODELS.keys()),
                label="Language Model",
                value="Zephyr 7B Beta"
            )
            max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max New Tokens")
            temperature = gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature")
            top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
            system_message = gr.Textbox(
                value="You are a friendly and helpful AI assistant.",
                label="System Message",
                lines=3
            )

        with gr.Column(scale=2):
            chatbot = gr.Chatbot()
            msg = gr.Textbox(label="Your message")
            clear = gr.Button("Clear")

    msg.submit(respond, [msg, chatbot, model_name, max_tokens, temperature, top_p, system_message], chatbot)
    clear.click(lambda: None, None, chatbot, queue=False)

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