Update app.py

app.py

@@ -1210,10 +1210,13 @@ def handle_large_dataset(df, create_document,isDataFrame):
                 # Create a PDF for each row
                 create_pdf(row['COMPANY'], row['EMPLOYEE NAME'], row['ACCOUNT NUMBER'],directory)
             create_document = False
-            zip_name = 'output_files.zip'
-            print(zip_name)
-            zip_files_in_folder(directory, zip_name)
-            create_file_HF(zip_name,directory, False)
+            # Directory containing PDF files
+            pdf_dir = "/home/user/app"
+            # Output ZIP file name
+            zip_file_name = "/home/user/app/pdf_files.zip"
+            print(zip_file_name)
+            zip_files_in_folder(directory, zip_file_name)
+            create_file_HF(zip_file_name,directory, False)
             docstatus = f"Please download the complete dataset here: <a href='https://redmindtechnologies.com/RedMindGPT/output.zip' download>Download</a>. {total_rows} documents are created successfully."
         print(sample_table)
         # 5. Return the summary and downloadable link
@@ -1271,25 +1274,22 @@ def create_pdf(cname,ename,account_number, directory):
     # Get the absolute path
     file_path = os.path.abspath(output_file_name)
     print(f"The file was created at: {file_path}")
-    create_file_HF(output_file_name, directory,document_created)
+    #create_file_HF(output_file_name, directory,document_created)
 
     
     return f"{output_file_name} is created successfully."
 
 def zip_files_in_folder(folder_path, zip_name):
-    # Create a Zip file
-    #folder_path="./"
-    print(folder_path)
-    with zipfile.ZipFile(zip_name, 'w', zipfile.ZIP_DEFLATED) as zipf:
-        # Walk through the folder
-        for root, dirs, files in os.walk(folder_path):
+    # Initialize the ZIP file
+    with zipfile.ZipFile(output_zip, 'w', zipfile.ZIP_DEFLATED) as zipf:
+        # Walk through the directory and add PDF files to the ZIP
+        for root, _, files in os.walk(directory):
             for file in files:
-                file_path = os.path.join(root, file)
-                # Add each file to the zip file
-                zipf.write(file_path, os.path.relpath(file_path, folder_path))
-
-    print(f"Zip file '{zip_name}' created successfully!")
-
+                if file.endswith(".pdf"):  # Only include PDF files
+                    file_path = os.path.join(root, file)
+                    # Add file to the ZIP archive
+                    zipf.write(file_path, os.path.relpath(file_path, directory))
+    print(f"ZIP file created: {output_zip}")
 
 def directory_exists(repo_id, directory, token):
     try: