metadata v12

app.py

@@ -40,15 +40,18 @@ def build_database():
     database = []
     batch_size = 10
 
+    # Get the train split
+    train_dataset = dataset["train"]
+    
     # Debug: Print dataset structure
-    print("Dataset structure:", dataset.features)
-    print("First item structure:", dataset["train"][0])
-    print("Dataset type:", type(dataset))
-    print("Dataset item type:", type(dataset["train"][0]))
+    print("Dataset structure:", train_dataset.features)
+    print("First item structure:", train_dataset[0])
+    print("Dataset type:", type(train_dataset))
+    print("Dataset item type:", type(train_dataset[0]))
 
-    for i in range(0, len(dataset["train"]), batch_size):
-        batch = dataset["train"][i:i + batch_size]
-        print(f"📦 Procesando lote {i // batch_size + 1}/{(len(dataset['train']) + batch_size - 1) // batch_size}")
+    for i in range(0, len(train_dataset), batch_size):
+        batch = train_dataset[i:i + batch_size]
+        print(f"📦 Procesando lote {i // batch_size + 1}/{(len(train_dataset) + batch_size - 1) // batch_size}")
 
         for j, item in enumerate(batch):
             try:
@@ -77,7 +80,7 @@ def build_database():
                 )[0]["embedding"]
 
                 database.append((f"image_{i+j}", img, embedding))
-                print(f"✅ Procesada imagen {i+j+1}/{len(dataset['train'])}")
+                print(f"✅ Procesada imagen {i+j+1}/{len(train_dataset)}")
 
                 del img_processed
                 gc.collect()