Update prepare_vector_dp.py

prepare_vector_dp.py

@@ -68,11 +68,16 @@ def create_db_from_text():
 
 def create_dp_from_files():
     
+    print("Files in directory:", os.listdir(pdf_data_path))
     
     # Khai bao loader de quet toan bo thu muc data
     loader = DirectoryLoader(pdf_data_path, glob="*.pdf",loader_cls=PyPDFLoader)
     documents = loader.load()
 
+    print(f"Loaded {len(documents)} documents")
+    for doc in documents:
+        print("Preview:", doc.page_content[:300])
+
     text_splitter = CharacterTextSplitter(chunk_size = 512, chunk_overlap = 50)
     chunks = text_splitter.split_documents(documents)