Update app.py

app.py

@@ -1,4 +1,5 @@
 import os
+from huggingface_hub import Repository
 import streamlit.components.v1 as components
 from datasets import load_dataset
 import random
@@ -18,6 +19,19 @@ from my_component import my_component
 
 nltk.download('punkt')
 
+# Step 1: Clone the Dataset Repository
+repo = Repository(
+    local_dir="Private_Book",  # Local directory to clone the repository
+    repo_type="dataset",  # Specify that this is a dataset repository
+    
+    clone_from="Anne31415/Private_Book",  # Replace with your repository URL
+    
+    token=os.os.getenv["HUB_TOKEN"]  # Use the secret token to authenticate
+)
+repo.git_pull()  # Pull the latest changes (if any)
+
+# Step 2: Load the PDF File
+pdf_file_path = "Private_Book/Glossar_PDF_webscraping.pdf"  # Replace with your PDF file path
 
 
 # Sidebar contents