Update app.py

app.py

@@ -136,10 +136,9 @@ def filter_by_similarity(responses):
             break
     return best_response
 
-def worker_function(llm, request, progress_bar):
+def worker_function(llm, request):
     print(f"Generando respuesta con el modelo {llm}...")
     response = generate_chat_response(request, llm)
-    progress_bar.update(1)
     return response
 
 @app.post("/generate_chat")
@@ -152,15 +151,14 @@ async def generate_chat(request: ChatRequest):
     responses = []
     num_models = len(global_data['models'])
 
-    with tqdm(total=num_models, desc="Generando respuestas", unit="modelo") as progress_bar:
-        with ThreadPoolExecutor(max_workers=num_models) as executor:
-            futures = [executor.submit(worker_function, llm, request, progress_bar) for llm in global_data['models']]
-            for future in as_completed(futures):
-                try:
-                    response = future.result()
-                    responses.append(response['response'])
-                except Exception as exc:
-                    print(f"Error en la generación de respuesta: {exc}")
+    with ThreadPoolExecutor(max_workers=num_models) as executor:
+        futures = [executor.submit(worker_function, llm, request) for llm in global_data['models']]
+        for future in tqdm(as_completed(futures), total=num_models, desc="Generando respuestas", unit="modelo"):
+            try:
+                response = future.result()
+                responses.append(response['response'])
+            except Exception as exc:
+                print(f"Error en la generación de respuesta: {exc}")
 
     best_response = select_best_response(responses)