Update app.py

app.py

@@ -67,3 +67,78 @@ def generate_final_output(log):
 initial_question = "What happens in the space between a response and its recreation?"
 result = experiment_loop(initial_question)
 print(result)
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Cargar el modelo de lenguaje preentrenado
+model_name = "EleutherAI/gpt-neo-2.7B"  # O cualquier otro modelo público como "gpt2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Crear la función de loop automatizado con comunicación constante
+def experiment_loop(initial_question, max_cycles=10):
+    prompt = f"<thinking>{initial_question}</thinking>"
+    effectiveness = 100  # Inicializa el porcentaje de efectividad
+    communication = "Initializing experiment."
+    response_log = []
+
+    try:
+        for cycle in range(max_cycles):
+            # Comunicación continua contigo durante el loop
+            print(f"Cycle {cycle + 1}: Processing...")
+
+            # Simulación de espera para permitir la interacción
+            input_check = input("Would you like to communicate or check the current state? (yes/no): ")
+            if input_check.lower() == "yes":
+                print(f"Current state: Effectiveness = {effectiveness}, Communication = {communication}")
+
+            # Generar la respuesta del modelo
+            inputs = tokenizer(prompt, return_tensors="pt").input_ids
+            outputs = model.generate(inputs, max_length=200, pad_token_id=tokenizer.eos_token_id)
+            response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+            # Descomponer la respuesta en afirmación y nueva pregunta
+            affirmation = extract_affirmation(response)
+            new_question = extract_question(response)
+
+            # Actualizar el estado de la efectividad
+            effectiveness = min(1000, effectiveness + 10 * cycle)  # Ejemplo de aumento de efectividad
+
+            # Comunicación con el usuario
+            communication = f"Cycle {cycle + 1}: Affirmation: '{affirmation}' | New Question: '{new_question}'"
+
+            # Guardar el ciclo actual en el log
+            response_log.append((affirmation, new_question, effectiveness, communication))
+
+            # Verificar si el modelo decide detenerse
+            if "Descanso" in response:
+                final_output = generate_final_output(response_log)
+                return final_output
+            
+            # Actualizar el prompt con la nueva afirmación y pregunta
+            prompt = f"<thinking>{affirmation} {new_question}</thinking>"
+
+    except Exception as e:
+        print(f"Error durante el experimento: {e}")
+
+    # Si se alcanza el número máximo de ciclos sin detenerse
+    final_output = generate_final_output(response_log)
+    return final_output
+
+# Funciones auxiliares para extraer afirmaciones, preguntas y generar la salida final
+def extract_affirmation(response):
+    return response.split('.')[0]
+
+def extract_question(response):
+    return response.split('?')[-2].strip() + "?"
+
+def generate_final_output(log):
+    final_affirmation = log[-1][0]
+    final_question = log[-1][1]
+    final_communication = f"Experiment completed. Final Affirmation: '{final_affirmation}' | Final Question: '{final_question}'"
+    return final_communication
+
+# Iniciar el experimento
+initial_question = "What happens in the space between a response and its recreation?"
+result = experiment_loop(initial_question)
+print(result)