Update search_utils.py

search_utils.py

@@ -38,17 +38,19 @@ class MetadataManager:
         try:
             # Load the parquet file
             self.df = pd.read_parquet(self.metadata_path)
+            
             # Clean and format the data
             self.df['source'] = self.df['source'].apply(
                 lambda x: [
                     url.strip()
                     for url in str(x).split(';') 
-                    if url.strip()
+                    if url.strip() and url.startswith('http')
                 ]
             )
-            # Convert list of sources to a single string
+            # Convert list of sources to a single string, separate by ' | '
             self.df['source'] = self.df['source'].apply(lambda x: ' | '.join(x) if isinstance(x, list) else x)
             
+
             self.total_docs = len(self.df)