Update app.py

app.py

@@ -77,34 +77,39 @@ def text_to_txt_bytes(text):
     except Exception as e:
         raise RuntimeError(f"Error during TXT conversion: {e}")
 
-def on_extract(pdf_file):
+def on_extract(pdf_file_path):
     """
     Callback function to extract text from PDF and return CSV and TXT data.
 
     Args:
-        pdf_file (gr.File): Dictionary containing file information.
+        pdf_file_path (str): The file path to the uploaded PDF.
 
     Returns:
-        tuple: CSV bytes and filename, TXT bytes and filename.
+        tuple: CSV download object, TXT download object, Status message.
     """
-    if pdf_file is None:
-        return gr.update(), gr.update(), "No file uploaded.", "No file uploaded."
+    if not pdf_file_path:
+        return None, None, "No file uploaded."
 
     try:
         # Extract text and create DataFrame
-        df, full_text = extract_text_with_langchain_pdf(pdf_file.name)
+        df, full_text = extract_text_with_langchain_pdf(pdf_file_path)
         
         # Convert DataFrame to CSV bytes
         csv_bytes = df_to_csv_bytes(df)
-        csv_filename = f"{pdf_file.name.rsplit('.', 1)[0]}_extracted.csv"
+        csv_filename = f"{pdf_file_path.rsplit('/', 1)[-1].rsplit('.', 1)[0]}_extracted.csv"
         
         # Convert full text to TXT bytes
         txt_bytes = text_to_txt_bytes(full_text)
-        txt_filename = f"{pdf_file.name.rsplit('.', 1)[0]}_full_text.txt"
+        txt_filename = f"{pdf_file_path.rsplit('/', 1)[-1].rsplit('.', 1)[0]}_full_text.txt"
         
-        return csv_bytes, csv_filename, txt_bytes, txt_filename
+        # Return CSV and TXT files along with a success message
+        return (
+            (csv_bytes, csv_filename),
+            (txt_bytes, txt_filename),
+            "Extraction successful!"
+        )
     except Exception as e:
-        return gr.update(), gr.update(), f"Extraction failed: {e}", f"Extraction failed: {e}"
+        return None, None, f"Extraction failed: {e}"
 
 with gr.Blocks() as demo:
     gr.Markdown("# 📄 PDF Text Extractor with Metadata and Multiple Exports")
@@ -113,7 +118,7 @@ with gr.Blocks() as demo:
         pdf_input = gr.File(
             label="Upload PDF",
             file_types=[".pdf"],
-            type="filepath",
+            type="filepath",  # Using "filepath" as per Gradio's valid options
             interactive=True
         )
     
@@ -121,15 +126,17 @@ with gr.Blocks() as demo:
         extract_button = gr.Button("Extract and Download")
     
     with gr.Row():
-        csv_download = gr.Download(
-            label="Download Extracted CSV"
+        csv_download = gr.File(
+            label="Download Extracted CSV",
+            interactive=False
         )
-        txt_download = gr.Download(
-            label="Download Full Text"
+        txt_download = gr.File(
+            label="Download Full Text",
+            interactive=False
         )
     
     with gr.Row():
-        error_output = gr.Textbox(
+        status_output = gr.Textbox(
             label="Status",
             interactive=False,
             lines=2
@@ -138,12 +145,12 @@ with gr.Blocks() as demo:
     extract_button.click(
         fn=on_extract,
         inputs=pdf_input,
-        outputs=[csv_download, txt_download, error_output, error_output]
+        outputs=[csv_download, txt_download, status_output]
     )
     
     gr.Markdown("""
     ---
-    Developed Gradio and LangChain.
+    Developed with ❤️ using Gradio and LangChain.
     """)
 
 # Launch the Gradio app