import gradio as gr
from groq import Groq
import os

# Set your Groq API key
API_KEY = os.getenv("API_KEY")
client = Groq(api_key=API_KEY)  # Pass API key explicitly

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

    for user_input, bot_response in history:
        if user_input:
            messages.append({"role": "user", "content": user_input})
        if bot_response:
            messages.append({"role": "assistant", "content": bot_response})

    messages.append({"role": "user", "content": message})

    completion = client.chat.completions.create(
        model="mixtral-8x7b-32768",
        messages=messages,
        temperature=temperature,
        max_completion_tokens=max_tokens,
        top_p=top_p,
        stream=True,
        stop=None,
    )

    response = ""
    for chunk in completion:
        token = chunk.choices[0].delta.content or ""
        response += token
        yield response

# Gradio Interface
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly AI assistant.", 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()