Update app.py

app.py

@@ -3,19 +3,15 @@ SUBTITLE = """<h2 align="center">Play with Gemini Pro and Gemini Pro Vision</h2>
 
 import os
 import time
-import uuid
 from typing import List, Tuple, Optional, Union
 
 import google.generativeai as genai
 import gradio as gr
-from PIL import Image
 from dotenv import load_dotenv
 
 # Cargar las variables de entorno desde el archivo .env
 load_dotenv()
 
-print("google-generativeai:", genai.__version__)
-
 # Obtener la clave de la API de las variables de entorno
 GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
 
@@ -23,10 +19,17 @@ GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
 if not GOOGLE_API_KEY:
     raise ValueError("GOOGLE_API_KEY is not set in environment variables.")
 
+# Configurar la API
+genai.configure(api_key=GOOGLE_API_KEY)
+
+# Constantes
 IMAGE_WIDTH = 512
 CHAT_HISTORY = List[Tuple[Optional[Union[Tuple[str], str]], Optional[str]]]
 
 def user(text_prompt: str, chatbot: CHAT_HISTORY):
+    """
+    Maneja las entradas del usuario en el chatbot.
+    """
     if text_prompt:
         chatbot.append((text_prompt, None))
     return "", chatbot
@@ -36,10 +39,9 @@ def bot(
     system_instruction: Optional[str],
     chatbot: CHAT_HISTORY
 ):
-    if not GOOGLE_API_KEY:
-        raise ValueError("GOOGLE_API_KEY is not set.")
-
-    genai.configure(api_key=GOOGLE_API_KEY)
+    """
+    Maneja las respuestas del modelo generativo.
+    """
     generation_config = genai.types.GenerationConfig(
         temperature=0.7,
         max_output_tokens=8192,
@@ -47,90 +49,79 @@ def bot(
         top_p=0.9
     )
 
+    # Usar un valor predeterminado si system_instruction está vacío
     if not system_instruction:
-        system_instruction = "1"
+        system_instruction = "You are a helpful assistant."
+
+    # Obtener el prompt más reciente del usuario
+    text_prompt = [chatbot[-1][0]] if chatbot and chatbot[-1][0] else []
 
-    text_prompt = [chatbot[-1][0]] if chatbot and chatbot[-1][0] and isinstance(chatbot[-1][0], str) else []
-    
+    # Crear y configurar el modelo generativo
     model = genai.GenerativeModel(
         model_name=model_choice,
         generation_config=generation_config,
-        system_instruction=system_instruction
+        system_instruction=system_instruction,
     )
 
-    response = model.generate_content(text_prompt, stream=True, generation_config=generation_config)
+    # Generar contenido usando streaming
+    response = model.generate_content(text_prompt, stream=True)
 
-    chatbot[-1][1] = ""
+    # Preparar la respuesta para el chatbot
+    chatbot[-1] = (chatbot[-1][0], "")
     for chunk in response:
-        for i in range(0, len(chunk.text), 10):
-            section = chunk.text[i:i + 10]
-            chatbot[-1][1] += section
-            time.sleep(0.01)
-            yield chatbot
-
-def multimodal(file, chatbot: CHAT_HISTORY):
-    """
-    Procesa un archivo multimodal (imagen, PDF, texto) y genera resultados
-    utilizando Gemini Vision y Pro.
-    """
-    if not GOOGLE_API_KEY:
-        raise ValueError("GOOGLE_API_KEY is not set.")
-
-    genai.configure(api_key=GOOGLE_API_KEY)
-    file_type = file.name.split(".")[-1].lower()
-
-    if file_type in ["png", "jpg", "jpeg"]:
-        # Procesar imágenes
-        image = Image.open(file.name)
-        chatbot.append(("Image uploaded for analysis.", None))
-        result = genai.generate_images(
-            prompt="Analyze this image.",
-            image=image,
-            model="gemini-vision"
-        )
-        chatbot[-1] = ("Image uploaded for analysis.", result[0]["description"])
-
-    elif file_type == "txt":
-        # Procesar texto
-        content = file.read().decode("utf-8")
-        chatbot.append((content, None))
-        response = genai.generate_text(prompt=content, model="gemini-pro")
-        chatbot[-1] = (content, response.result)
-
-    elif file_type == "pdf":
-        # Procesar PDFs (extraer texto de la primera página)
-        import fitz  # PyMuPDF
-        doc = fitz.open(file.name)
-        page_text = doc[0].get_text() if len(doc) > 0 else "PDF vacío."
-        chatbot.append((page_text, None))
-        response = genai.generate_text(prompt=page_text, model="gemini-pro")
-        chatbot[-1] = (page_text, response.result)
-
-    else:
-        chatbot.append(("Unsupported file type.", "Please upload a valid file."))
-    
-    return chatbot
-
-# Componentes de interfaz actualizados
-chatbot_component = gr.Chatbot(label='Gemini', bubble_full_width=False, scale=2, height=300)
-file_upload_component = gr.File(label="Upload File (Image, PDF, or TXT)")
-run_button_component = gr.Button(value="Analyze File", variant="primary", scale=1)
-
-user_inputs = [file_upload_component, chatbot_component]
-
-# Interfaz actualizada
+        chatbot[-1] = (chatbot[-1][0], chatbot[-1][1] + chunk.text)
+        yield chatbot
+
+# Componentes de la interfaz de usuario
+system_instruction_component = gr.Textbox(
+    placeholder="Enter system instruction...",
+    label="System Instruction",
+    lines=2
+)
+chatbot_component = gr.Chatbot(label='Gemini', bubble_full_width=False, height=300)
+text_prompt_component = gr.Textbox(placeholder="Message...", show_label=False, autofocus=True)
+run_button_component = gr.Button(value="Run", variant="primary")
+model_choice_component = gr.Dropdown(
+    choices=["gemini-1.5-flash", "gemini-2.0-flash-exp", "gemini-1.5-pro"],
+    value="gemini-1.5-flash",
+    label="Select Model"
+)
+
+user_inputs = [text_prompt_component, chatbot_component]
+bot_inputs = [model_choice_component, system_instruction_component, chatbot_component]
+
+# Definir la interfaz de usuario
 with gr.Blocks() as demo:
     gr.HTML(TITLE)
     gr.HTML(SUBTITLE)
     with gr.Column():
+        # Campo de selección de modelo arriba
+        model_choice_component.render()
         chatbot_component.render()
-        file_upload_component.render()
-        run_button_component.render()
+        with gr.Row():
+            text_prompt_component.render()
+            run_button_component.render()
+
+        # Crear el acordeón para la instrucción del sistema al final
+        with gr.Accordion("System Instruction", open=False):
+            system_instruction_component.render()
 
     run_button_component.click(
-        fn=multimodal,
+        fn=user,
+        inputs=user_inputs,
+        outputs=[text_prompt_component, chatbot_component],
+        queue=False
+    ).then(
+        fn=bot, inputs=bot_inputs, outputs=[chatbot_component],
+    )
+
+    text_prompt_component.submit(
+        fn=user,
         inputs=user_inputs,
-        outputs=[chatbot_component],
+        outputs=[text_prompt_component, chatbot_component],
+        queue=False
+    ).then(
+        fn=bot, inputs=bot_inputs, outputs=[chatbot_component],
     )
 
 # Lanzar la aplicación