app.py

import gradio as gr
from groq import Groq
import os
from dotenv import load_env

load_env()

# Initialize the Groq client
client = Groq(api_key=os.getenv("API_KEY"))

# Synchronous function to handle responses
def generate_response(prompt, history, temperature=0.5, max_tokens=1024, top_p=1.0):
    """
    Generates a response synchronously using Groq client and returns the output.
    """
    try:
        # Format the conversation history
        messages = [{"role": "system", "content": "You are a helpful assistant."}]
        for user_input, bot_response in history:
            messages.append({"role": "user", "content": user_input})
            messages.append({"role": "assistant", "content": bot_response})
        messages.append({"role": "user", "content": prompt})

        # Call the Groq API for response
        stream = client.chat.completions.create(
            messages=messages,
            model="llama3-8b-8192",
            temperature=temperature,
            max_tokens=max_tokens,
            top_p=top_p,
            stream=True,
        )

        # Collect the output from the stream
        output = ""
        for chunk in stream:
            output += str(chunk.choices[0].delta.content)
        return output

    except Exception as e:
        return f"Error: {str(e)}"

# Slider inputs for optional parameters
additional_inputs = [
    gr.Slider(label="Temperature", value=0.5, minimum=0.0, maximum=1.0, step=0.05),
    gr.Slider(label="Max Tokens", value=1024, minimum=1, maximum=2048, step=64),
    gr.Slider(label="Top-p", value=1.0, minimum=0.0, maximum=1.0, step=0.05),
]

# Define the Gradio interface
interface = gr.ChatInterface(
    fn=generate_response,
    chatbot=gr.Chatbot(show_label=False),
    additional_inputs=additional_inputs,
    title="Sync APX Copilot Chatbot 🦜",
    description="An AI chatbot powered by Groq for synchronous responses.",
)

# Launch the Gradio app
interface.launch(show_api=False, share=True)