deal with samples properly

app.py

@@ -136,14 +136,31 @@ def process_pdfs(
         progress(0, desc="Starting PDF processing")
         images, message = pdf_to_images(pdf_files, sample_size, images_dir)
 
+        # Create a new directory for sampled images
+        sampled_images_dir = os.path.join(temp_dir, "sampled_images")
+        os.makedirs(sampled_images_dir)
+
+        # Move sampled images to the new directory and update paths
+        updated_images = []
+        for image in images:
+            new_path = os.path.join(sampled_images_dir, os.path.basename(image))
+            shutil.move(image, new_path)
+            updated_images.append(new_path)
+
+        # Update the images list with new paths
+        images = updated_images
+
         zip_path = None
         if create_zip:
-            # Create a zip file of the images
+            # Create a zip file of the sampled images
             zip_path = os.path.join(temp_dir, "converted_images.zip")
             with zipfile.ZipFile(zip_path, "w") as zipf:
                 progress(0, desc="Zipping images")
                 for image in progress.tqdm(images, desc="Zipping images"):
-                    zipf.write(image, os.path.basename(image))
+                    zipf.write(
+                        os.path.join(sampled_images_dir, os.path.basename(image)),
+                        os.path.basename(image),
+                    )
             message += f"\nCreated zip file with {len(images)} images"
 
         if hf_repo:
@@ -154,11 +171,12 @@ def process_pdfs(
                     repo_type="dataset",
                     private=private_repo,
                 )
-                hf_api.upload_large_folder(
-                    folder_path=temp_dir,
+                # Upload only the sampled images directory
+                hf_api.upload_folder(
+                    folder_path=sampled_images_dir,
                     repo_id=hf_repo,
                     repo_type="dataset",
-                    # path_in_repo="images",
+                    path_in_repo="images",
                 )
 
                 # Determine size category