Update file_loader.py

file_loader.py

@@ -19,11 +19,18 @@ def get_vectorstore():
     docx_files = list_docx_files(folder_path)
     
     all_splits = []  # Khởi tạo danh sách lưu kết quả
+    print("Feeding relevent websites' contents")
+    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 = scrape_website(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 .json files')
     # Xử lý FAQ
     FAQ_path = "syllabus_nct_word_format/FAQ.json"
@@ -33,11 +40,6 @@ def get_vectorstore():
     FAQ_path = "syllabus_nct_word_format/FAQ2.json"
     FAQ_splits = get_json_splits_only(FAQ_path)
     all_splits += FAQ_splits
-    print("Feeding relevent websites' contents")
-    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 = scrape_website(base_urls='base_urls')
-    all_splits += website_contents
     
     # Lưu vào vectorstore với nhúng từ Google GenAI
     # embedding = GoogleGenerativeAIEmbeddings(model="models/text-embedding-004")