demos/chatbot_multimodal/run.py

import gradio as gr
import time

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

def print_like_dislike(x: gr.LikeData):
    print(x.index, x.value, x.liked)

def add_message(history, message):
    for x in message["files"]:
        history.append({"role": "user", "content": {"path": x}})
    if message["text"] is not None:
        history.append({"role": "user", "content": message["text"]})
    return history, gr.MultimodalTextbox(value=None, interactive=False)

def bot(history: list):
    response = "**That's cool!**"
    history.append({"role": "assistant", "content": ""})
    for character in response:
        history[-1]['content'] += character
        time.sleep(0.05)
        yield history

with gr.Blocks() as demo:
    chatbot = gr.Chatbot(
        elem_id="chatbot",
        bubble_full_width=False,
        type="messages"
    )

    chat_input = gr.MultimodalTextbox(interactive=True,
                                      file_count="multiple",
                                      placeholder="Enter message or upload file...", show_label=False)

    chat_msg = chat_input.submit(add_message, [chatbot, chat_input], [chatbot, chat_input])
    bot_msg = chat_msg.then(bot, chatbot, chatbot, api_name="bot_response")
    bot_msg.then(lambda: gr.MultimodalTextbox(interactive=True), None, [chat_input])

    chatbot.like(print_like_dislike, None, None)

if __name__ == "__main__":
    demo.launch()