app.py

import argparse
import os
import random

import numpy as np
import torch
import torch.backends.cudnn as cudnn
import gradio as gr
import argparse
import torch

from llava.constants import (
    IMAGE_TOKEN_INDEX,
    DEFAULT_IMAGE_TOKEN,
    DEFAULT_IM_START_TOKEN,
    DEFAULT_IM_END_TOKEN,
    IMAGE_PLACEHOLDER,
)
from llava.conversation import conv_templates, SeparatorStyle
from llava.model.builder import load_pretrained_model
from llava.utils import disable_torch_init
from llava.mm_utils import (
    process_images,
    tokenizer_image_token,
    get_model_name_from_path,
)

from PIL import Image
from huggingface_hub import snapshot_download
import requests
from PIL import Image
from io import BytesIO
import re

from llava.chat import Chat, conv_llava_v1

# imports modules for registration

def parse_args():
    parser = argparse.ArgumentParser(description="Demo")
    parser.add_argument("--model-path", type=str, default="gordonhu/MQT-LLaVA-7b")
    parser.add_argument("--model-base", type=str, default=None)
    # parser.add_argument("--image-file", type=str, required=True)
    # parser.add_argument("--query", type=str, required=True)
    parser.add_argument("--conv-mode", type=str, default='llava_v1')
    parser.add_argument("--sep", type=str, default=",")
    parser.add_argument("--temperature", type=float, default=0)
    parser.add_argument("--top_p", type=float, default=None)
    parser.add_argument("--num_beams", type=int, default=1)
    parser.add_argument("--max_new_tokens", type=int, default=512)
    parser.add_argument("--num-visual-tokens", type=int, default=256)
    parser.add_argument("--gpu-id", type=int, default=0)
    args = parser.parse_args()
    return args

# ========================================
#             Model Initialization
# ========================================

print('Initializing Chat')
args = parse_args()

if torch.cuda.is_available():
    device='cuda:{}'.format(args.gpu_id)
else:
    device=torch.device('cpu')

disable_torch_init()
snapshot_download(repo_id="gordonhu/MQT-LLaVA-7b")

model_name = get_model_name_from_path(args.model_path)
tokenizer, model, image_processor, context_len = load_pretrained_model(
    args.model_path, args.model_base, model_name, device_map=device, device=device
)

# vis_processor_cfg = cfg.datasets_cfg.cc_sbu_align.vis_processor.train
# vis_processor = registry.get_processor_class(vis_processor_cfg.name).from_config(vis_processor_cfg)
chat = Chat(model, tokenizer, image_processor, args, device=device)
print('Initialization Finished')

# ========================================
#             Gradio Setting
# ========================================

def gradio_reset(chat_state, img_list):
    if chat_state is not None:
        chat_state.messages = []
    if img_list is not None:
        img_list = []
    return None, gr.update(value=None, interactive=True), gr.update(placeholder='Please upload your image first', interactive=False),gr.update(value="Upload & Start Chat", interactive=True), chat_state, img_list

def upload_img(gr_img, text_input, chat_state):
    if gr_img is None:
        return None, None, gr.update(interactive=True), chat_state, None
    chat_state = conv_llava_v1.copy()   #CONV_VISION.copy()
    img_list = []
    llm_message = chat.upload_img(gr_img, chat_state, img_list)
    return gr.update(interactive=False), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Start Chatting", interactive=False), chat_state, img_list

def gradio_ask(user_message, chatbot, chat_state):
    if len(user_message) == 0:
        return gr.update(interactive=True, placeholder='Input should not be empty!'), chatbot, chat_state
    chat.ask(user_message, chat_state)
    chatbot = chatbot + [[user_message, None]]
    return '', chatbot, chat_state


def gradio_answer(chatbot, chat_state, img_list, num_beams, temperature, num_visual_tokens):
    llm_message = chat.answer(conv=chat_state,
                              img_list=img_list,
                              num_beams=num_beams,
                              temperature=temperature,
                              num_visual_tokens=num_visual_tokens,
                              )  #[0]
    chatbot[-1][1] = llm_message[0]
    return chatbot, chat_state, img_list

title = """<h1 align="center">Demo of MQT-LLaVA</h1>"""
description = """<h3>This is the demo of MQT-LLaVA. Upload your images and start chatting! <br> To use 
            example questions, click example image, hit upload & start chat, and press enter on your keyboard in the chatbox.
            <br> Due to limited memory constraint, we only support single turn conversation. To ask multiple questions, hit Restart and upload your image! </h3>"""
article = """<p><a href='https://gordonhu608.github.io/mqtllava/'><img src='https://img.shields.io/badge/Project-Page-Green'></a></p><p><a href='https://github.com/gordonhu608/MQT-LLaVA'><img src='https://img.shields.io/badge/Github-Code-blue'></a></p><p><a href='https://arxiv.org/abs/2405.19315'><img src='https://img.shields.io/badge/Paper-ArXiv-red'></a></p>
"""

#TODO show examples below

with gr.Blocks() as demo:
    gr.Markdown(title)
    gr.Markdown(description)
    gr.Markdown(article)

    with gr.Row():
        with gr.Column(scale=0.5):
            image = gr.Image(type="pil")
            upload_button = gr.Button(value="Upload & Start Chat", interactive=True, variant="primary")
            clear = gr.Button("Restart 🔄")
            
            num_visual_tokens = gr.Slider(
                minimum=1,
                maximum=256,
                value=256,
                step=1,
                interactive=True,
                label="Number of visual tokens",
            )
                                    
            temperature = gr.Slider(
                minimum=0.1,
                maximum=2.0,
                value=1.0,
                step=0.1,
                interactive=True,
                label="Temperature",
            )
            
            num_beams = gr.Slider(
                minimum=1,
                maximum=10,
                value=5,
                step=1,
                interactive=True,
                label="beam search numbers",
            )


        with gr.Column():
            chat_state = gr.State()
            img_list = gr.State()
            chatbot = gr.Chatbot(label='MQT-LLaVA')
            text_input = gr.Textbox(label='User', placeholder='Please upload your image first', interactive=False)
            
            gr.Examples(examples=[
                [f"images/extreme_ironing.jpg", "What is unusual about this image?"],
                [f"images/waterview.jpg", "What are the things I should be cautious about when I visit here?"],
            ], inputs=[image, text_input])          
            
    upload_button.click(upload_img, [image, text_input, chat_state], [image, text_input, upload_button, chat_state, img_list])
    
    text_input.submit(gradio_ask, [text_input, chatbot, chat_state], [text_input, chatbot, chat_state]).then(
        gradio_answer, [chatbot, chat_state, img_list, num_beams, temperature, num_visual_tokens], [chatbot, chat_state, img_list]
    )
    clear.click(gradio_reset, [chat_state, img_list], [chatbot, image, text_input, upload_button, chat_state, img_list], queue=False)

demo.launch()