Update app.py

app.py

@@ -28,37 +28,55 @@ IMAGE_WIDTH = 512
 CHAT_HISTORY = List[Tuple[Optional[Union[Tuple[str], str]], Optional[str]]]
 
 def preprocess_image(image: Image.Image) -> Optional[Image.Image]:
-    """Redimensiona la imagen para que se ajuste a la aplicación."""
     if image:
         image_height = int(image.height * IMAGE_WIDTH / image.width)
         return image.resize((IMAGE_WIDTH, image_height))
 
 def cache_pil_image(image: Image.Image) -> str:
-    """Guarda la imagen procesada en el sistema de archivos temporal."""
     image_filename = f"{uuid.uuid4()}.jpeg"
     os.makedirs(IMAGE_CACHE_DIRECTORY, exist_ok=True)
     image_path = os.path.join(IMAGE_CACHE_DIRECTORY, image_filename)
     image.save(image_path, "JPEG")
     return image_path
 
+def upload_to_gemini(path, mime_type=None):
+    """Uploads the given file to Gemini."""
+    file = genai.upload_file(path, mime_type=mime_type)
+    print(f"Uploaded file '{file.display_name}' as: {file.uri}")
+    return file
+
+def wait_for_files_active(files):
+    """Waits for the given files to be active."""
+    print("Waiting for file processing...")
+    for name in (file.name for file in files):
+        file = genai.get_file(name)
+        while file.state.name == "PROCESSING":
+            print(".", end="", flush=True)
+            time.sleep(10)
+            file = genai.get_file(name)
+        if file.state.name != "ACTIVE":
+            raise Exception(f"File {file.name} failed to process")
+    print("...all files ready")
+    print()
+
 def upload(files: Optional[List[str]], chatbot: CHAT_HISTORY) -> CHAT_HISTORY:
-    """Sube los archivos y los agrega al historial de chat."""
+    gemini_files = []
     for file in files:
-        if file.name.endswith(('.jpg', '.jpeg', '.png')):
-            image = Image.open(file).convert('RGB')
-            image_preview = preprocess_image(image)
-            if image_preview:
-                # Muestra una vista previa de la imagen subida
-                gr.Image(image_preview).render()
-            image_path = cache_pil_image(image)
-            chatbot.append(((image_path,), None))
-        else:
-            # Si es un PDF u otro tipo de archivo, solo se guarda la ruta
-            chatbot.append(((file.name,), None))
+        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)
+        gemini_file = upload_to_gemini(image_path, mime_type="image/jpeg")
+        gemini_files.append(gemini_file)
+
+    # Wait for files to be ready in Gemini
+    wait_for_files_active(gemini_files)
+    chatbot.append(((gemini_file.uri,), None))
     return chatbot
 
 def user(text_prompt: str, chatbot: CHAT_HISTORY):
-    """Procesa la entrada del usuario y la agrega al historial."""
     if text_prompt:
         chatbot.append((text_prompt, None))
     return "", chatbot
@@ -68,27 +86,22 @@ def bot(
     model_choice: str,
     chatbot: CHAT_HISTORY
 ):
-    """Genera una respuesta utilizando la API de Gemini."""
     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)
     generation_config = genai.types.GenerationConfig(
-        temperature=0.7,
-        max_output_tokens=8192,
-        top_k=10,
-        top_p=0.9
+        temperature=0.7,  # Valor predeterminado
+        max_output_tokens=8192,  # Fijar el límite de tokens a 8,192
+        top_k=10,  # Valor predeterminado
+        top_p=0.9   # Valor predeterminado
     )
 
-    # Procesar los archivos
     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 file.name.endswith(('.jpg', '.jpeg', '.png'))] if files else []
-    pdf_prompt = [file.name for file in files if file.name.endswith('.pdf')] if files else []
-    
-    # Crear el modelo
+    image_prompt = [preprocess_image(Image.open(file).convert('RGB')) for file in files] if files else []
     model = genai.GenerativeModel(model_choice)
-    response = model.generate_content(text_prompt + image_prompt + pdf_prompt, stream=True, generation_config=generation_config)
+    response = model.generate_content(text_prompt + image_prompt, stream=True, generation_config=generation_config)
 
     chatbot[-1][1] = ""
     for chunk in response:
@@ -98,7 +111,6 @@ def bot(
             time.sleep(0.01)
             yield chatbot
 
-# Componentes de la interfaz de usuario con Gradio
 chatbot_component = gr.Chatbot(
     label='Gemini',
     bubble_full_width=False,
@@ -109,7 +121,7 @@ text_prompt_component = gr.Textbox(
     placeholder="Message...", show_label=False, autofocus=True, scale=8
 )
 upload_button_component = gr.UploadButton(
-    label="Upload Files", file_count="multiple", file_types=["image", "pdf"], scale=1
+    label="Upload Images", file_count="multiple", file_types=["image"], scale=1
 )
 run_button_component = gr.Button(value="Run", variant="primary", scale=1)
 model_choice_component = gr.Dropdown(
@@ -131,8 +143,8 @@ bot_inputs = [
 ]
 
 with gr.Blocks() as demo:
-    gr.HTML("<h1 align='center'>Gemini Playground ✨</h1>")
-    gr.HTML("<h2 align='center'>Play with Gemini Pro and Gemini Pro Vision</h2>")
+    gr.HTML(TITLE)
+    gr.HTML(SUBTITLE)
     with gr.Column():
         chatbot_component.render()
         with gr.Row():
@@ -169,3 +181,4 @@ with gr.Blocks() as demo:
 demo.queue(max_size=99).launch(debug=False, show_error=True)
 
 
+