metadata v12

app.py

@@ -60,17 +60,21 @@ def build_database():
         batch = dataset[i:i + batch_size]
         print(f"📦 Procesando lote {i // batch_size + 1}/{(len(dataset) + batch_size - 1) // batch_size}")
 
-        for j, item in enumerate(batch):
+        for j in range(len(batch["image"])):
             try:
-                if not isinstance(item, dict) or "image" not in item:
-                    print(f"⚠️ Saltando item {i + j} - estructura inválida: {item}")
-                    continue
+                item = {"image": batch["image"][j]}
 
                 image_url = item["image"]
                 if not isinstance(image_url, str) or not image_url.startswith("http") or image_url.strip().lower() == "image":
                     print(f"⚠️ Saltando item {i + j} - URL inválida: {image_url}")
                     continue
 
+                # Autenticación para datasets privados
+                headers = {}
+                HF_TOKEN = os.getenv("HF_TOKEN")
+                if HF_TOKEN:
+                    headers["Authorization"] = f"Bearer {HF_TOKEN}"
+
                 response = requests.get(image_url, headers=headers, timeout=10)
                 response.raise_for_status()
                 img = Image.open(BytesIO(response.content)).convert("RGB")