Changes based on @hysts suggestions

Hoping that I got

@hysts
suggestions correct and this works!

https://huggingface.co/spaces/hysts/BLIP2-with-transformers/discussions/2#64298547f1884027c2a6a7c3

app.py

@@ -40,17 +40,22 @@ def blip2_interface(image, prompted_caption_text, vqa_question, chat_context):
 
 # Define Gradio input and output components
 image_input = gr.Image(type="numpy")
-text_input = gr.Text()
-output_text = gr.outputs.Textbox()
+prompted_caption_input = gr.Textbox()
+vqa_question_input = gr.Textbox()
+chat_context = gr.Textbox()
+image_caption_result = gr.Textbox()
+prompted_caption_result = gr.Textbox()
+vqa_answer = gr.Textbox()
+chat_response = gr.Textbox()
 
 # Create Gradio interface
 iface = gr.Interface(
     fn=blip2_interface,
-    inputs=[image_input, text_input, text_input, text_input],
-    outputs=[output_text, output_text, output_text, output_text],
+    inputs=[image_input, prompted_caption_input, vqa_question_input, chat_context],
+    outputs=[image_caption_result, prompted_caption_result, vqa_answer, chat_response],
     title="BLIP-2 Image Captioning and VQA",
     description="Interact with the BLIP-2 model for image captioning, prompted image captioning, visual question answering, and chat-based prompting.",
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()