Update file_loader.py

file_loader.py

@@ -29,20 +29,20 @@ def get_vectorstore():
     # ['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")):
-    #     output_json_path = f"output_{i}.json"
-    #     splits = get_splits(file_path, output_json_path)
-    #     all_splits += splits
+    print('Feeding .docx files')
+    for i, file_path in enumerate(tqdm(docx_files, desc="Đang xử lý", unit="file")):
+        output_json_path = f"output_{i}.json"
+        splits = get_splits(file_path, output_json_path)
+        all_splits += splits
         
-    # print('Feeding .json files')
-    # # Xử lý FAQ
-    # FAQ_path = "syllabus_nct_word_format/FAQ.json"
-    # FAQ_splits = get_json_splits_only(FAQ_path)
-    # all_splits += FAQ_splits
+    print('Feeding .json files')
+    # Xử lý FAQ
+    FAQ_path = "syllabus_nct_word_format/FAQ.json"
+    FAQ_splits = get_json_splits_only(FAQ_path)
+    all_splits += FAQ_splits
 
     FAQ_path = "syllabus_nct_word_format/FAQ2.json"
     FAQ_splits = get_json_splits_only(FAQ_path)