import gradio as gr
import requests
import os

# Set up the API endpoint and key
API_URL = os.getenv("BASE_URL")
API_KEY = os.getenv("RUNPOD_API_KEY")  # Make sure to set this in your Hugging Face Space secrets

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

def respond(message, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]
    
    for human, assistant in history:
        messages.append({"role": "user", "content": human})
        messages.append({"role": "assistant", "content": assistant})
    
    messages.append({"role": "user", "content": message})
    
    data = {
        "model": "forcemultiplier/fmx-reflective-2b",  # Adjust if needed
        "messages": messages,
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p
    }
    
    response = requests.post(API_URL, headers=headers, json=data)
    
    if response.status_code == 200:
        return response.json()['choices'][0]['message']['content']
    else:
        return f"Error: {response.status_code} - {response.text}"

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(
            value="You are an advanced artificial intelligence system, capable of <thinking> <reflection> and you output a brief and to-the-point <output>.",
            label="System message"
        ),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max tokens"),
        gr.Slider(minimum=0.1, maximum=2.0, 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()