Add HF token support to embedding API

embedding_api.py

@@ -17,6 +17,11 @@ import uvicorn
 from colpali_engine.models import ColPali, ColPaliProcessor
 from colpali_engine.utils.torch_utils import get_torch_device
 
+# Set HF token if available
+hf_token = os.environ.get("HUGGING_FACE_TOKEN") or os.environ.get("HF_TOKEN")
+if hf_token:
+    os.environ["HF_TOKEN"] = hf_token
+
 # Setup logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -54,9 +59,10 @@ def load_model():
             model = ColPali.from_pretrained(
                 model_name,
                 torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
-                device_map=device
+                device_map=device,
+                token=hf_token
             ).eval()
-            processor = ColPaliProcessor.from_pretrained(model_name)
+            processor = ColPaliProcessor.from_pretrained(model_name, token=hf_token)
             logger.info("ColPali model loaded successfully")
         except Exception as e:
             logger.error(f"Error loading model: {e}")