Update app.py

app.py

@@ -73,8 +73,11 @@ def save_dataframe_to_csv(df):
     return temp_file_path
 
 # Main function to perform image captioning and image-text matching
-def process_images_and_statements(image, filename):
+def process_images_and_statements(image, file):
     logging.info('Starting process_images_and_statements')
+    
+    # Extract the filename from the file object
+    filename = file.name
 
     # Generate image caption for the uploaded image using git-large-r-textcaps
     caption = generate_caption(git_processor_large_textcaps, git_model_large_textcaps, image)
@@ -119,19 +122,14 @@ def process_images_and_statements(image, filename):
     # Return both the DataFrame and the CSV data for the Gradio interface
     return results_df, csv_results # <--- Return results_df and csv_results
 
-# Define a function to handle the user's input
-def handle_input(image, filename):
-    # Call the process_images_and_statements function with the image and filename
-    return process_images_and_statements(image, filename.name)
 # Gradio interface
-image_input = gr.inputs.Image()
-file_input = gr.inputs.File()  # Add an input element to allow users to provide the image filename
+image_input = gr.inputs.Image()  # Create default image input element
 output_df = gr.outputs.Dataframe(type="pandas", label="Results")
 output_csv = gr.outputs.File(label="Download CSV")
 
 iface = gr.Interface(
-    fn=handle_input,  # Use the handle_input function to handle user input
-    inputs=[image_input, file_input],  # Include both the image and filename inputs
+    fn=process_images_and_statements,
+    inputs=image_input,
     outputs=[output_df, output_csv],
     title="Image Captioning and Image-Text Matching",
     theme='sudeepshouche/minimalist',