using gradio instead of streamlit

app.py

@@ -38,9 +38,15 @@ except Exception as e:
 # Function to process the image and extract text
 def process_image(image, keyword):
     try:
+        # Debugging: Check the type of the input image
+        print(f"Received image of type: {type(image)}")
+
         # Use the image-to-text pipeline to extract text from the image
         output_text_img_to_text = image_to_text_pipeline(image)
 
+        # Debugging: Check the output of the image-to-text model
+        print(f"Output from image-to-text pipeline: {output_text_img_to_text}")
+
         # Prepare input for Qwen model for image description
         conversation = [{"role": "user", "content": [{"type": "image"}, {"type": "text", "text": "Describe this image."}]}]
         text_prompt = processor_qwen.apply_chat_template(conversation, add_generation_prompt=True)
@@ -52,6 +58,9 @@ def process_image(image, keyword):
             generated_ids_qwen = [output_ids_qwen[len(input_ids):] for input_ids, output_ids_qwen in zip(inputs_qwen.input_ids, output_ids_qwen)]
             output_text_qwen = processor_qwen.batch_decode(generated_ids_qwen, skip_special_tokens=True, clean_up_tokenization_spaces=True)
 
+        # Debugging: Check the output from the Qwen model
+        print(f"Output from Qwen model: {output_text_qwen}")
+
         extracted_text = output_text_img_to_text[0]['generated_text']
 
         # Keyword search in the extracted text