Update file_loader.py

file_loader.py

@@ -20,17 +20,17 @@ def get_vectorstore():
     docx_files = list_docx_files(folder_path)
     
     all_splits = []  # Khởi tạo danh sách lưu kết quả
-    print("Feeding relevent websites' contents")
-    # 
-    with open('syllabus_nct_word_format/urls.txt', 'r') as f:
-        base_urls = [line.strip() for line in f]
-    # urls_list
-    # base_urls =['https://fda.neu.edu.vn/hoi-nghi-khoa-hoc-cong-nghe-dai-hoc-kinh-te-quoc-dan-nam-2025/']
-    # ['https://nct.neu.edu.vn/', 'https://fsf.neu.edu.vn/', 'https://mfe.neu.edu.vn/', 'https://mis.neu.edu.vn/', 'https://fda.neu.edu.vn/', 'https://khoathongke.neu.edu.vn/', 'https://fit.neu.edu.vn/']
+    # print("Feeding relevent websites' contents")
+    # # 
+    # with open('syllabus_nct_word_format/urls.txt', 'r') as f:
+    #     base_urls = [line.strip() for line in f]
+    # # urls_list
+    # # base_urls =['https://fda.neu.edu.vn/hoi-nghi-khoa-hoc-cong-nghe-dai-hoc-kinh-te-quoc-dan-nam-2025/']
+    # # ['https://nct.neu.edu.vn/', 'https://fsf.neu.edu.vn/', 'https://mfe.neu.edu.vn/', 'https://mis.neu.edu.vn/', 'https://fda.neu.edu.vn/', 'https://khoathongke.neu.edu.vn/', 'https://fit.neu.edu.vn/']
     
     
-    website_contents = get_web_documents(base_urls=base_urls)
-    all_splits += website_contents
+    # website_contents = get_web_documents(base_urls=base_urls)
+    # all_splits += website_contents
     
     print('Feeding .docx files')
     for i, file_path in enumerate(tqdm(docx_files, desc="Đang xử lý", unit="file")):