Update app.py

app.py

@@ -1,47 +1,103 @@
-runtime error
-Exit code: 1. Reason: Error cargando modelo: A load persistent id instruction was encountered,
-but no persistent_load function was specified.
-Traceback (most recent call last):
-  File "/home/user/app/app.py", line 10, in <module>
-    model_data = pickle.load(f)
-_pickle.UnpicklingError: A load persistent id instruction was encountered,
-but no persistent_load function was specified.
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
-  File "/home/user/app/app.py", line 26, in <module>
-    model = torch.nn.LSTM(input_size=input_size, hidden_size=hidden_size, num_layers=2).float()
-NameError: name 'hidden_size' is not defined
-Container logs:
-
-===== Application Startup at 2025-05-19 22:20:24 =====
-
-Error cargando modelo: A load persistent id instruction was encountered,
-but no persistent_load function was specified.
-Traceback (most recent call last):
-  File "/home/user/app/app.py", line 10, in <module>
-    model_data = pickle.load(f)
-_pickle.UnpicklingError: A load persistent id instruction was encountered,
-but no persistent_load function was specified.
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
-  File "/home/user/app/app.py", line 26, in <module>
-    model = torch.nn.LSTM(input_size=input_size, hidden_size=hidden_size, num_layers=2).float()
-NameError: name 'hidden_size' is not defined
-Error cargando modelo: A load persistent id instruction was encountered,
-but no persistent_load function was specified.
-Traceback (most recent call last):
-  File "/home/user/app/app.py", line 10, in <module>
-    model_data = pickle.load(f)
-_pickle.UnpicklingError: A load persistent id instruction was encountered,
-but no persistent_load function was specified.
-
-During handling of the above exception, another exception occurred:
-
-Traceback (most recent call last):
-  File "/home/user/app/app.py", line 26, in <module>
-    model = torch.nn.LSTM(input_size=input_size, hidden_size=hidden_size, num_layers=2).float()
-NameError: name 'hidden_size' is not defined
+import gradio as gr
+import torch
+import pickle
+import numpy as np
+from collections import defaultdict
+
+# 1. Configuración segura
+DEFAULT_INPUT_SIZE = 4  # Basado en tu error anterior
+DEFAULT_HIDDEN_SIZE = 64  # Tamaño común para modelos pequeños
+
+# 2. Función segura para cargar modelos
+def safe_load_model(path):
+    try:
+        # Intentar cargar con pickle
+        with open(path, 'rb') as f:
+            data = pickle.load(f)
+        
+        # Verificar estructura
+        if not all(k in data for k in ['model', 'vocab', 'idx_to_word']):
+            raise ValueError("Estructura inválida del archivo .pkl")
+            
+        return data
+    
+    except Exception as e:
+        print(f"Error cargando modelo: {e}")
+        # Crear datos dummy seguros
+        vocab = defaultdict(lambda: 0, {"<unk>": 0, "hola": 1, "mundo": 2, "adiós": 3})
+        return {
+            'model': torch.nn.LSTM(
+                input_size=DEFAULT_INPUT_SIZE,
+                hidden_size=DEFAULT_HIDDEN_SIZE,
+                num_layers=2
+            ).float(),
+            'vocab': vocab,
+            'idx_to_word': {v: k for k, v in vocab.items()}
+        }
+
+# 3. Cargar modelo
+model_data = safe_load_model('model.pkl')
+model = model_data['model']
+vocab = model_data['vocab']
+idx_to_word = model_data['idx_to_word']
+
+print(f"Modelo cargado. Input size: {model.input_size}, Hidden size: {model.hidden_size}")
+
+# 4. Preprocesamiento seguro
+def preprocess(text, seq_length=5):
+    words = text.lower().split()[-seq_length:]
+    embeddings = []
+    
+    for word in words:
+        # Embedding básico con exactamente input_size características
+        embedding = [
+            len(word),
+            sum(ord(c) for c in word),
+            len(word) * sum(ord(c) for c in word),
+            1 if word.isalpha() else 0
+        ][:model.input_size]
+        
+        # Rellenar si es necesario
+        if len(embedding) < model.input_size:
+            embedding += [0] * (model.input_size - len(embedding))
+        
+        embeddings.append(embedding)
+    
+    # Rellenar secuencia
+    while len(embeddings) < seq_length:
+        embeddings.append([0] * model.input_size)
+    
+    return torch.tensor([embeddings], dtype=torch.float32)
+
+# 5. Función de predicción robusta
+def predict_next_word(text):
+    try:
+        inputs = preprocess(text)
+        print(f"Input shape: {inputs.shape}")
+        
+        with torch.no_grad():
+            outputs, _ = model(inputs)
+            
+            if outputs.shape[-1] != len(vocab):
+                proj = torch.nn.Linear(outputs.shape[-1], len(vocab)).float()
+                outputs = proj(outputs)
+            
+            probs = torch.softmax(outputs[:, -1, :], dim=1)
+            pred_idx = probs.argmax().item()
+            
+            return f"Predicción: {idx_to_word.get(pred_idx, '<unk>')} ({probs[0][pred_idx].item():.2%})"
+    
+    except Exception as e:
+        return f"Error en predicción: {str(e)}"
+
+# 6. Interfaz simplificada
+interface = gr.Interface(
+    fn=predict_next_word,
+    inputs=gr.Textbox(label="Contexto", placeholder="Escribe 3-5 palabras..."),
+    outputs="text",
+    examples=[["El cielo es"], ["Mi nombre es"], ["Qué hora es"]],
+    title="Predictor de Siguiente Palabra",
+    description="Escribe un contexto y predice la siguiente palabra"
+)
+
+interface.launch(share=True)