Update file_loader.py

file_loader.py

@@ -63,13 +63,27 @@ def get_vectorstore():
     folder_path = "syllabus_nct_docx_format_K66/" #'/content/chatbot4nct_test2/syllabus_nct_word_format'
     docx_files = list_docx_files(folder_path)
     all_splits = []  # Khởi tạo danh sách lưu kết quả
+    error_files = []  # List to store files that caused errors
     for i, file_path in enumerate(tqdm(docx_files, desc="Đang xử lý", unit="file")):
+        # print(f'Reading {file_path}')
         output_json_path = f"output_{i}.json"
-        metadata = define_metadata(file_path)
-        splits = get_splits(file_path, output_json_path)
-        splits_with_metadata = update_documents_metadata(splits, metadata)
-        all_splits += splits_with_metadata
-        # if i == 1: break
+        
+        try:
+            metadata = define_metadata(file_path)
+            splits = get_splits(file_path, output_json_path)
+            splits_with_metadata = update_documents_metadata(splits, metadata)
+            all_splits += splits_with_metadata    
+        except Exception as e:
+            print(f"Error processing {file_path}: {e}")
+            error_files.append(file_path)  # Store the problematic file
+    
+    # Print all files that caused errors
+    if error_files:
+        print("\nFiles that caused errors:")
+        for file in error_files:
+            print(file)
+    else:
+        print("\nAll files processed successfully!")
 
     FAQ_path = "syllabus_nct_word_format/FAQ.json"
     FAQ_splits = get_json_splits_only(FAQ_path)