app.py

import string
import gradio as gr
import requests
def inference_caption():
    return 
def inference_chat():
    return "hello"
    
with gr.Blocks(
    css="""
    .message.svelte-w6rprc.svelte-w6rprc.svelte-w6rprc {font-size: 20px; margin-top: 20px}
    #component-21 > div.wrap.svelte-w6rprc {height: 600px;}
    """
) as iface:
    state = gr.State([])
    #caption_output = state
    #gr.Markdown(title)
    #gr.Markdown(description)
    #gr.Markdown(article)

    with gr.Row():
        with gr.Column(scale=1):
            image_input = gr.Image(type="pil")

          

        with gr.Column(scale=1.8):
            
            with gr.Row():
                with gr.Column():
                    caption_output = gr.Textbox(lines=1, label="VQA Output")
                with gr.Column(scale=1):
                    chat_input = gr.Textbox(lines=1, label="VQA Input")
                    chat_input.submit(
                        inference_chat,
                        [
                            image_input,
                            chat_input,
                        ],
                        [ caption_output],
                    )

                    with gr.Row():
                        clear_button = gr.Button(value="Clear", interactive=True)
                        clear_button.click(
                            lambda: ("", [], []),
                            [],
                            [chat_input,  state],
                            queue=False,
                        )

                        submit_button = gr.Button(
                            value="Submit", interactive=True, variant="primary"
                        )
                        submit_button.click(
                            inference_chat,
                            [
                                image_input,
                                chat_input,
                            ],
                            [caption_output],
                        )
            

            image_input.change(
                lambda: ("", "", []),
                [],
                [ caption_output, state],
                queue=False,
            )

   # examples = gr.Examples(
   #     examples=examples,
   #     inputs=[image_input, chat_input],
  #  )

iface.queue(concurrency_count=1, api_open=False, max_size=10)
iface.launch(enable_queue=True)