Update app.py

app.py

@@ -5,11 +5,11 @@ import os
 import time
 import uuid
 from typing import List, Tuple, Optional, Dict, Union
+
 import google.generativeai as genai
 import gradio as gr
 from PIL import Image
 from dotenv import load_dotenv
-from langdetect import detect
 
 # Cargar las variables de entorno desde el archivo .env
 load_dotenv()
@@ -27,7 +27,6 @@ IMAGE_CACHE_DIRECTORY = "/tmp"
 IMAGE_WIDTH = 512
 CHAT_HISTORY = List[Tuple[Optional[Union[Tuple[str], str]], Optional[str]]]
 
-# Preprocesamiento y configuración de secuencias y imágenes
 def preprocess_stop_sequences(stop_sequences: str) -> Optional[List[str]]:
     return [sequence.strip() for sequence in stop_sequences.split(",")] if stop_sequences else None
 
@@ -48,6 +47,7 @@ def upload(files: Optional[List[str]], chatbot: CHAT_HISTORY) -> CHAT_HISTORY:
         image = Image.open(file).convert('RGB')
         image_preview = preprocess_image(image)
         if image_preview:
+            # Display a preview of the uploaded image
             gr.Image(image_preview).render()
         image_path = cache_pil_image(image)
         chatbot.append(((image_path,), None))
@@ -65,18 +65,13 @@ def bot(
     stop_sequences: str,
     top_k: int,
     top_p: float,
-    model_name: str,  # Recibimos el modelo seleccionado
     chatbot: CHAT_HISTORY
 ):
     if not GOOGLE_API_KEY:
         raise ValueError("GOOGLE_API_KEY is not set.")
 
+    # Configurar la API con la clave
     genai.configure(api_key=GOOGLE_API_KEY)
-
-    # Detectar el idioma del texto ingresado
-    text_prompt = [chatbot[-1][0]] if chatbot and chatbot[-1][0] and isinstance(chatbot[-1][0], str) else []
-    detected_language = detect(text_prompt[-1]) if text_prompt else 'en'
-
     generation_config = genai.types.GenerationConfig(
         temperature=temperature,
         max_output_tokens=max_output_tokens,
@@ -85,9 +80,11 @@ def bot(
         top_p=top_p
     )
 
-    # Configurar el modelo seleccionado
-    model = genai.GenerativeModel(model_name)  # Usamos el modelo seleccionado por el usuario
-    response = model.generate_content(text_prompt + [], stream=True, generation_config=generation_config)
+    text_prompt = [chatbot[-1][0]] if chatbot and chatbot[-1][0] and isinstance(chatbot[-1][0], str) else []
+    image_prompt = [preprocess_image(Image.open(file).convert('RGB')) for file in files] if files else []
+    model_name = 'gemini-1.5-flash'
+    model = genai.GenerativeModel(model_name)
+    response = model.generate_content(text_prompt + image_prompt, stream=True, generation_config=generation_config)
 
     chatbot[-1][1] = ""
     for chunk in response:
@@ -97,29 +94,67 @@ def bot(
             time.sleep(0.01)
             yield chatbot
 
-# Dropdown para seleccionar el modelo
-model_dropdown = gr.Dropdown(
-    label="Selecciona un modelo",
-    choices=["gemini-1.5-flash", "gemini-2.0-flash-exp", "gemini-1.5-pro"],  # Opciones de modelo
-    value="gemini-1.5-flash",  # Valor predeterminado
-    type="value",  # Valor que se selecciona
+chatbot_component = gr.Chatbot(
+    label='Gemini',
+    bubble_full_width=False,
+    scale=2,
+    height=300
+)
+text_prompt_component = gr.Textbox(
+    placeholder="Message...", show_label=False, autofocus=True, scale=8
+)
+upload_button_component = gr.UploadButton(
+    label="Upload Images", file_count="multiple", file_types=["image"], scale=1
 )
-
-# Componente Gradio
-chatbot_component = gr.Chatbot(label='Gemini', bubble_full_width=False, scale=2, height=300)
-text_prompt_component = gr.Textbox(placeholder="Message...", show_label=False, autofocus=True, scale=8)
-upload_button_component = gr.UploadButton(label="Upload Images", file_count="multiple", file_types=["image"], scale=1)
 run_button_component = gr.Button(value="Run", variant="primary", scale=1)
-temperature_component = gr.Slider(minimum=0, maximum=1.0, value=0.4, step=0.05, label="Temperature")
-max_output_tokens_component = gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="Token limit")
-stop_sequences_component = gr.Textbox(label="Add stop sequence", value="", type="text", placeholder="STOP, END")
-top_k_component = gr.Slider(minimum=1, maximum=40, value=32, step=1, label="Top-K")
-top_p_component = gr.Slider(minimum=0, maximum=1, value=1, step=0.01, label="Top-P")
+temperature_component = gr.Slider(
+    minimum=0,
+    maximum=1.0,
+    value=0.4,
+    step=0.05,
+    label="Temperature",
+)
+max_output_tokens_component = gr.Slider(
+    minimum=1,
+    maximum=2048,
+    value=1024,
+    step=1,
+    label="Token limit",
+)
+stop_sequences_component = gr.Textbox(
+    label="Add stop sequence",
+    value="",
+    type="text",
+    placeholder="STOP, END",
+)
+top_k_component = gr.Slider(
+    minimum=1,
+    maximum=40,
+    value=32,
+    step=1,
+    label="Top-K",
+)
+top_p_component = gr.Slider(
+    minimum=0,
+    maximum=1,
+    value=1,
+    step=0.01,
+    label="Top-P",
+)
+
+user_inputs = [
+    text_prompt_component,
+    chatbot_component
+]
 
-user_inputs = [text_prompt_component, chatbot_component]
 bot_inputs = [
-    upload_button_component, temperature_component, max_output_tokens_component,
-    stop_sequences_component, top_k_component, top_p_component, model_dropdown, chatbot_component
+    upload_button_component,
+    temperature_component,
+    max_output_tokens_component,
+    stop_sequences_component,
+    top_k_component,
+    top_p_component,
+    chatbot_component
 ]
 
 with gr.Blocks() as demo: