updated for error correction

app.py

@@ -1,7 +1,7 @@
 # app.py
 
 import os
-from utils.data_loader import download_dataset
+from utils.data_loader import download_dataset, save_metadata
 from utils.vector_utils import create_vector_db
 from config import v_auth_token, v_vector_folder, v_metadata_file
 
@@ -9,6 +9,12 @@ if __name__ == "__main__":
     if not v_auth_token:
         raise ValueError("Authentication token not found. Ensure 'hkey' is set as a secret in Hugging Face Spaces.")
 
+    # Ensure vector folder and metadata file are initialized
+    os.makedirs(v_vector_folder, exist_ok=True)
+    if not os.path.exists(v_metadata_file):
+        print("Metadata file not found. Creating a new one.")
+        save_metadata(v_metadata_file, {})
+
     print("Starting Vector Database Creation...")
 
     v_dataset_path = download_dataset(v_auth_token, v_metadata_file, v_vector_folder)
@@ -16,3 +22,4 @@ if __name__ == "__main__":
         print("Vector database is up-to-date.")
     else:
         create_vector_db(v_dataset_path, v_vector_folder)
+

utils/data_loader.py

@@ -28,12 +28,22 @@ def fetch_metadata():
     return {"dataset_version": "v1.0"}
 
 def load_metadata(v_metadata_file):
+    """
+    Load metadata from the file. If the file doesn't exist or is empty, return an empty dictionary.
+    """
     if os.path.exists(v_metadata_file):
         with open(v_metadata_file, "r") as file:
-            return json.load(file)
+            try:
+                return json.load(file)
+            except json.JSONDecodeError:
+                print(f"Metadata file {v_metadata_file} is empty or invalid. Initializing new metadata.")
+                return {}
     return {}
 
 def save_metadata(v_metadata_file, v_metadata):
+    """
+    Save metadata to the file. Creates the file if it doesn't exist.
+    """
     os.makedirs(os.path.dirname(v_metadata_file), exist_ok=True)
     with open(v_metadata_file, "w") as file:
-        json.dump(v_metadata, file)
+        json.dump(v_metadata, file, indent=4)