app.py

import os
from groq import Groq
import gradio as gr

#
api_key = os.getenv("GROQ_API_KEY2")

#.
client = Groq(api_key=api_key)

# 
system_prompt = {
    "role": "system",
    "content": "You are a useful assistant. You reply with efficient answers."
}

# 
async def chat_groq(message, history):
    messages = [system_prompt]
    
    for msg in history:
        messages.append({"role": "user", "content": str(msg[0])})
        messages.append({"role": "assistant", "content": str(msg[1])})
        
    messages.append({"role": "user", "content": str(message)})
    
    response_content = ''
    
    # modelo `llama-3.1-70b-versatile`
    stream = client.chat.completions.create(
        model="llama-3.1-70b-versatile",
        messages=messages,
        max_tokens=1024,
        temperature=1.3,
        stream=True
    )

    for chunk in stream:
        content = chunk.choices[0].delta.content
        if content:
            response_content += chunk.choices[0].delta.content 
        yield response_content

# Interface Gradio
with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
    gr.ChatInterface(chat_groq,
                     clear_btn=None, 
                     undo_btn=None, 
                     retry_btn=None)

demo.queue()
demo.launch()