Update app.py

app.py

@@ -89,25 +89,31 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
     # Agregar la nueva pregunta del usuario
     messages.append({"role": "user", "content": message})
 
-    # Llamar a la API de OpenAI con streaming
-    stream = client.chat.completions.create(
+
+    # Llamar a la API con streaming usando `responses`
+    stream = client.responses.stream(
         model="gpt-5-mini",
-        messages=messages,
-        #max_tokens=max_tokens,
-        stream=True,
-        #temperature=temperature,
-        #top_p=top_p,
+        input=messages,
         tools=[{"type": "web_search", "search_context_size": "high"}],
     )
-
+    
     response = ""
-    for chunk in stream:
-        if chunk.choices and chunk.choices[0].delta.content:
-            response += chunk.choices[0].delta.content
+    
+    # Recibir los fragmentos del stream
+    for event in stream:
+        if event.type == "response.output_text.delta":
+            response += event.delta
             yield response
+        elif event.type == "response.completed":
+            break  # 🚨 Importante: terminar cuando el modelo indique fin del stream
+    
+    # Cerrar el stream correctamente
+    stream.close()
     
+    # Procesar el texto final
     citations = extract_unique_citations(response)
-    response = response + "\n Fuentes:" + citations
+    response = response + "\nFuentes: " + citations
+    yield response
 
 # Configuración de la interfaz Gradio
 demo = gr.ChatInterface(