try new functing

rag/scraper/Scrape_pdf/Scrape_pdf.py

@@ -4,6 +4,26 @@
 from rag.scraper.Scrape_pdf.pdf_helper import missing_page_fill
 import os
 
+def create_folder_from_filename(filename: str) -> str:
+    """Create a folder using the given filename.
+    
+    Args:
+        filename (str): The filename to be used for creating the folder.
+    
+    Returns:
+        str: The path to the created or existing folder.
+    """
+    # Extract the folder name from the filename (remove extension if any)
+    folder_name = os.path.splitext(filename)[0]
+
+    # Ensure the folder exists
+    if not os.path.exists(folder_name):
+        os.makedirs(folder_name)
+        print(f"Created folder: {folder_name}")
+    else:
+        print(f"Folder already exists: {folder_name}")
+
+    return folder_name
 
 def add_remove_image_suffix(pdf_path: str) -> str:
     """Add '_remove_image' suffix to a PDF file path while keeping the .pdf extension."""
@@ -12,7 +32,7 @@ def add_remove_image_suffix(pdf_path: str) -> str:
         raise ValueError("The input file must be a PDF.")
 
     # Add the suffix before the file extension
-    new_path = input_path.with_stem(input_path.stem + "_remove_image")
+    new_path = input_path.with_stem(input_path.stem)
 
     return str(new_path)
 
@@ -36,24 +56,30 @@ def remove_images(input_pdf, output_pdf):
     doc.save(output_pdf)
     doc.close()
 
-def process_pdf(input_pdf: str) -> str:
-    """Process the PDF by removing images and saving to a new file with '_remove_image' suffix."""
-    output_pdf = add_remove_image_suffix(input_pdf)
+def process_pdf(input_pdf: str, output_folder: str) -> str:
+    """Process the PDF by removing images and saving to a new file in the specified folder."""
+    # Ensure the output folder exists
+    if not os.path.exists(output_folder):
+        os.makedirs(output_folder)
+
+    output_pdf_name = add_remove_image_suffix(os.path.basename(input_pdf))
+    output_pdf = os.path.join(output_folder, output_pdf_name)
     remove_images(input_pdf, output_pdf)
     return output_pdf
 
 def generate_mmd_file_path(folder_path):
     folder_name = os.path.basename(folder_path)
-    mmd_file_path = os.path.join(folder_path, f"{folder_name}_remove_image.mmd")
+    mmd_file_path = os.path.join(folder_path, f"{folder_name}.mmd")
     return mmd_file_path
 
 
 input_pdf = "rag\scraper\Scrape_pdf\example_pdf.pdf"
-folder_name = "rag\scraper\Scrape_pdf\example_pdf"
+
 
 
 if __name__ == '__main__':
-    output_pdf = process_pdf(input_pdf)
+    folder_name = create_folder_from_filename(input_pdf)
+    output_pdf = process_pdf(input_pdf, folder_name)
     pdf_to_md(output_pdf, folder_name)
     md_file_path = generate_mmd_file_path(folder_name)
     missing_page_fill(output_pdf, folder_name, md_file_path)

test.py

@@ -1,3 +1,10 @@
-import nougat
-print(dir(nougat))
+import tensorflow as tf
 
+print("TensorFlow version:", tf.__version__)
+print("Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU')))
+
+if len(tf.config.experimental.list_physical_devices('GPU')) == 0:
+    print("No GPU found. Please check your installation.")
+else:
+    for device in tf.config.experimental.list_physical_devices('GPU'):
+        print("GPU Device:", device)