import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# Welcoming message for the assistant
welcome_message = "Hello, I'm Codecat, your Python coding assistant. How can I help you today?"

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Check for empty or whitespace-only input
    if not message.strip():
        return "I'm only here to answer Python-related questions. Please ask something about Python."

    # Create messages for the model
    # Use only the system message for the first response
    messages = [{"role": "system", "content": f"{system_message}\n{welcome_message}"}] if len(history) == 0 else []

    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 = ""

    try:
        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

    except Exception as e:
        return "I'm sorry, there seems to be an error with your input. Please check the syntax and try again."

    # Fallback for unrecognized input
    if not response:
        return "I'm not sure I understand. Can you please clarify your question?"

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()