app.py

import gradio as gr
import random
import time

# Chatbot demo with multimodal input (text, markdown, LaTeX, code blocks, image, audio, & video). Plus shows support for streaming text.

def add_text(history, text):
    history = history + [(text, None)]
    return history, gr.update(value="", interactive=False)


def add_file(history, file):
    print(file.name)
    #if 'png' in file.name:
    #gr.Warning("testing warning")
    history = history + [((file.name,), None)]
    return history


def bot(history):
    response = "**That's cool!**"
    history[-1][1] = ""
    for character in response:
        history[-1][1] += character
        time.sleep(0.05)
        yield history


with gr.Blocks() as demo:
    chatbot = gr.Chatbot([], elem_id="chatbot").style(height=750)

    with gr.Row():
        with gr.Column(scale=0.85):
            txt = gr.Textbox(
                show_label=False,
                placeholder="Enter text and press enter, or upload an image",
            ).style(container=False)
        with gr.Column(scale=0.15, min_width=0):
            btn = gr.UploadButton("📁", file_types=["image"])

    txt_msg = txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(
        bot, chatbot, chatbot
    )
    txt_msg.then(lambda: gr.update(interactive=True), None, [txt], queue=False)
    file_msg = btn.upload(add_file, [chatbot, btn], [chatbot], queue=False).then(
        bot, chatbot, chatbot
    )
    btn.upload(lambda : gr.update(label='⬆️🖼️'), [], btn)
    txt_msg = txt.submit(lambda : gr.update(label="📁", interactive=True),[],btn)

demo.queue()
demo.launch(debug=True)