Update app.py

app.py

@@ -2,8 +2,7 @@ import os
 import gradio as gr
 from http import HTTPStatus
 import dashscope
-from dashscope import Generation
-from dashscope.api_entities.dashscope_response import Role
+from transformers import pipeline
 from typing import List, Optional, Tuple, Dict
 from urllib.error import HTTPError
 
@@ -46,23 +45,14 @@ def model_chat(query: Optional[str], history: Optional[History], system: str
         history = []
     messages = history_to_messages(history, system)
     messages.append({'role': Role.USER, 'content': query})
-    gen = Generation.call(
-        model='microsoft/Phi-3-mini-128k-instruct',  # Cambio de modelo aquí
-        messages=messages,
-        result_format='message',
-        stream=True
-    )
-    for response in gen:
-        if response.status_code == HTTPStatus.OK:
-            role = response.output.choices[0].message.role
-            response = response.output.choices[0].message.content
-            system, history = messages_to_history(messages + [{'role': role, 'content': response}])
-            yield '', history, system
-        else:
-            raise ValueError('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
-                response.request_id, response.status_code,
-                response.code, response.message
-            ))
+    
+    generator = pipeline('text-generation', model='microsoft/Phi-3-mini-128k-instruct')
+    response = generator(query, max_length=150)  # Ajusta la longitud máxima según necesidad
+    
+    role = Role.ASSISTANT
+    response_content = response[0]['generated_text']
+    system, history = messages_to_history(messages + [{'role': role, 'content': response_content}])
+    return '', history, system
 
 with gr.Blocks() as demo:
     with gr.TabBar():