Update app.py

app.py

@@ -317,7 +317,7 @@ def retrieve_metadata(document_indices: List[int], metadata_path: str = 'recipes
         required_columns = {'id', 'original_file_name', 'url'}
         if not required_columns.issubset(metadata_df.columns):
             raise ValueError(f"Metadata file must contain columns: {required_columns}")
-        metadata_df['id'] = metadata_df['id'].astype(int)  # Ensure 'id' is of type int
+        metadata_df['id'] = metadata_df['id'].astype(int)  
         filtered_metadata = metadata_df[metadata_df['id'].isin(document_indices)]
         metadata_dict = {
             int(row['id']): {
@@ -331,21 +331,6 @@ def retrieve_metadata(document_indices: List[int], metadata_path: str = 'recipes
         print(f"Error retrieving metadata: {e}")
         return {}
 
-
-def retrieve_metadata(document_indices: List[str], metadata_path: str = 'recipes_metadata.xlsx') -> Dict[str, Dict[str, str]]:
-    try:
-        metadata_df = pd.read_excel(metadata_path)        
-        required_columns = {'id', 'original_file_name', 'url'}
-        if not required_columns.issubset(metadata_df.columns):
-            raise ValueError(f"Metadata file must contain the following columns: {required_columns}")        
-        metadata_mapping = metadata_df.set_index('id')[['original_file_name', 'url']].to_dict('index')       
-        result = {doc_id: metadata_mapping.get(doc_id, {}) for doc_id in document_indices}
-        return result
-    except Exception as e:
-        print(f"Error retrieving metadata: {e}")
-        return {}
-
-
 def rerank_documents(query, document_ids, document_texts, cross_encoder_model):
     try:
         pairs = [(query, doc) for doc in document_texts]