app.py

import gradio as gr
from gradio_multimodalchatbot import MultimodalChatbot
from gradio.data_classes import FileData

user_msg1 = {"text": "Hello, what is in this image?",
             "files": [{"file": FileData(path="https://gradio-builds.s3.amazonaws.com/diffusion_image/cute_dog.jpg")}]
             }
bot_msg1 = {"text": "It is a very cute dog",
            "files": []}

user_msg2 = {"text": "Describe this audio clip please.",
             "files": [{"file": FileData(path="cantina.wav")}]}
bot_msg2 = {"text": "It is the cantina song from Star Wars",
            "files": []}

user_msg3 = {"text": "Give me a video clip please.",
             "files": []}
bot_msg3 = {"text": "Here is a video clip of the world",
            "files": [{"file": FileData(path="world.mp4")},
                      {"file": FileData(path="cantina.wav")}]}

conversation = [[user_msg1, bot_msg1], [user_msg2, bot_msg2], [user_msg3, bot_msg3]]

with gr.Blocks() as demo:
    MultimodalChatbot(value=conversation, height=800)


demo.launch()