import gradio as gr
from huggingface_hub import InferenceClient
import os

# Retrieve your token from the environment variable
hf_token = os.getenv("HF_TOKEN_NEW")

# Initialize InferenceClient with the token
client = InferenceClient(
    model="abhillubillu/ai_gameapp",
    token=hf_token  # Use your token stored in HF_TOKEN_NEW
)

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 = ""

    # Stream the response from the model
    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,  # Ensure your model supports streaming
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response

# Setting up Gradio Chat Interface
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(show_error=True)