app.py

import gradio as gr
import google.generativeai as genai
import os
from dotenv import load_dotenv

# Cargar variables de entorno
load_dotenv()

# Configurar la API de Google Gemini
genai.configure(api_key=os.getenv("GEMINI_API_KEY"))

def respond(
    message,
    history,
    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})

    # Configurar el modelo de Gemini
    model_name = "gemini-1.5-pro"  # Ajusta el modelo según sea necesario
    generation_config = {
        "temperature": temperature,
        "top_p": top_p,
        "max_output_tokens": max_tokens,
        "response_mime_type": "text/plain",
    }
    model = genai.GenerativeModel(model_name=model_name, generation_config=generation_config)
    chat_session = model.start_chat(
        history=messages
    )
    response = chat_session.send_message(message)
    return response.text


# Crear la interfaz de Gradio
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a helpful 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()