Update app.py

app.py

@@ -1,64 +1,67 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import requests
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
+# Configura tu cliente de modelo de Hugging Face
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# Tu clave de API de Google Custom Search
+GOOGLE_API_KEY = "AIzaSyDI48Q_Ez8-KXQ6Dfe_r7JyOkk-dloER0I"
+# Tu ID de motor de búsqueda
+SEARCH_ENGINE_ID = "030a88810b398467c"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def web_search(query):
+    # Realiza la búsqueda en Google
+    url = f"https://www.googleapis.com/customsearch/v1?q={query}&key={GOOGLE_API_KEY}&cx={SEARCH_ENGINE_ID}"
+    response = requests.get(url)
+    results = response.json()
+    
+    # Devuelve un resumen de los primeros resultados
+    search_results = []
+    for item in results.get("items", []):
+        title = item.get("title", "No title")
+        link = item.get("link", "")
+        snippet = item.get("snippet", "")
+        search_results.append(f"{title}: {snippet} ({link})")
+    return "\n".join(search_results)  # Devuelve los resultados como texto
 
+# Define la función del chatbot con navegación web
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # Prepara el contexto de la conversación para el modelo
+    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})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    # Realiza la búsqueda en la web
+    search_summary = web_search(message)
+    
+    # Incluye los resultados de la búsqueda en el contexto para el modelo
+    messages.append({"role": "system", "content": f"Search results:\n{search_summary}"})
+    
+    # Genera la respuesta del modelo
+    response = client.text_completion(
+        prompt=message, max_tokens=max_tokens, temperature=temperature, top_p=top_p
+    )
 
-        response += token
-        yield response
+    return response
 
+# Interfaz de Gradio
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.Button("Clear")
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", 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)",
-        ),
-    ],
-)
+    def chat_interface(user_message, history=[]):
+        output = respond(
+            user_message, history, "You are a helpful assistant.", 200, 0.7, 0.9
+        )
+        history.append((user_message, output))
+        return history, chatbot.update(history)
 
+    msg.submit(chat_interface, inputs=[msg, chatbot], outputs=[chatbot, chatbot])
+    clear.click(lambda: [], None, chatbot)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()