import gradio as gr
import requests
import os

#import subprocess
#subprocess.run(["huggingface-cli", "login", "--token", HUGGINGFACE_API_TOKEN_V])

TOKEN = os.getenv("HUGGINGFACE_API_TOKEN_V")

# Check if the API token is set
if not TOKEN:
    raise ValueError("API token is not set. Please set the HUGGINGFACE_API_TOKEN environment variable.")


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})

    headers = {
        "Authorization": f"Bearer {TOKEN}",
        "Content-Type": "application/json"
    }

    payload = {
        "model": "meta-llama/Meta-Llama-3.1-405B-Instruct",
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p,
        "messages": messages
    }

    response = requests.post("https://api-inference.huggingface.co/v1/chat/completions", headers=headers, json=payload, stream=True)
    
    response_text = ""
    for chunk in response.iter_content(chunk_size=None):
        if chunk:
            response_text += chunk.decode('utf-8')
            yield response_text

theme="Nymbo/Nymbo_Theme"

demo = gr.ChatInterface(
    respond,
    theme=theme,
    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()