浦語·靈筆的圖文理解及創作部署

浦語·靈筆是基于書生·浦語大語言模型研發的視覺-語言大模型，提供出色的圖文理解和創作能力，結合了視覺和語言的先進技術，能夠實現圖像到文本、文本到圖像的雙向轉換。使用浦語·靈筆大模型可以輕松的創作一篇圖文推文，也能夠輕松識別一張圖片中的物體，并生成對應的文本描述。

使用 InternStudio 中的 A100(1/4) * 2 機器和 internlm-xcomposer-7b 模型部署一個圖文理解創作 Demo

克隆環境

/root/share/install_conda_env_internlm_base.sh xcomposer-demo

激活環境

conda activate xcomposer-demo

安裝依賴

pip install transformers==4.33.1 timm==0.4.12 sentencepiece==0.1.99 gradio==3.44.4 markdown2==2.4.10 xlsxwriter==3.1.2 einops accelerate

模型下載

mkdir -p /root/model/Shanghai_AI_Laboratory
cp -r /root/share/temp/model_repos/internlm-xcomposer-7b /root/model/Shanghai_AI_Laboratory

代碼準備

cd /root/code
git clone https://gitee.com/internlm/InternLM-XComposer.git
cd /root/code/InternLM-XComposer
git checkout 3e8c79051a1356b9c388a6447867355c0634932d

demo運行

cd /root/code/InternLM-XComposer
python examples/web_demo.py  \--folder /root/model/Shanghai_AI_Laboratory/internlm-xcomposer-7b \--num_gpus 1 \--port 6006

運行效果

完成 Lagent 工具調用 Demo 創作部署

環境準備.

python -m pip install --upgrade pippip install modelscope==1.9.5
pip install transformers==4.35.2
pip install streamlit==1.24.0
pip install sentencepiece==0.1.99
pip install accelerate==0.24.1

模型下載

mkdir -p /root/model/Shanghai_AI_Laboratory
cp -r /root/share/temp/model_repos/internlm-chat-7b /root/model/Shanghai_AI_Laboratory

Lagent 安裝

cd /root/code
git clone https://gitee.com/internlm/lagent.git
cd /root/code/lagent
git checkout 511b03889010c4811b1701abb153e02b8e94fb5e # 盡量保證和教程commit版本一致
pip install -e . # 源碼安裝

修改代碼
由于代碼修改的地方比較多，大家直接將 /root/code/lagent/examples/react_web_demo.py 內容替換為以下代碼

import copy
import osimport streamlit as st
from streamlit.logger import get_loggerfrom lagent.actions import ActionExecutor, GoogleSearch, PythonInterpreter
from lagent.agents.react import ReAct
from lagent.llms import GPTAPI
from lagent.llms.huggingface import HFTransformerCasualLMclass SessionState:def init_state(self):"""Initialize session state variables."""st.session_state['assistant'] = []st.session_state['user'] = []#action_list = [PythonInterpreter(), GoogleSearch()]action_list = [PythonInterpreter()]st.session_state['plugin_map'] = {action.name: actionfor action in action_list}st.session_state['model_map'] = {}st.session_state['model_selected'] = Nonest.session_state['plugin_actions'] = set()def clear_state(self):"""Clear the existing session state."""st.session_state['assistant'] = []st.session_state['user'] = []st.session_state['model_selected'] = Noneif 'chatbot' in st.session_state:st.session_state['chatbot']._session_history = []class StreamlitUI:def __init__(self, session_state: SessionState):self.init_streamlit()self.session_state = session_statedef init_streamlit(self):"""Initialize Streamlit's UI settings."""st.set_page_config(layout='wide',page_title='lagent-web',page_icon='./docs/imgs/lagent_icon.png')# st.header(':robot_face: :blue[Lagent] Web Demo ', divider='rainbow')st.sidebar.title('模型控制')def setup_sidebar(self):"""Setup the sidebar for model and plugin selection."""model_name = st.sidebar.selectbox('模型選擇：', options=['gpt-3.5-turbo','internlm'])if model_name != st.session_state['model_selected']:model = self.init_model(model_name)self.session_state.clear_state()st.session_state['model_selected'] = model_nameif 'chatbot' in st.session_state:del st.session_state['chatbot']else:model = st.session_state['model_map'][model_name]plugin_name = st.sidebar.multiselect('插件選擇',options=list(st.session_state['plugin_map'].keys()),default=[list(st.session_state['plugin_map'].keys())[0]],)plugin_action = [st.session_state['plugin_map'][name] for name in plugin_name]if 'chatbot' in st.session_state:st.session_state['chatbot']._action_executor = ActionExecutor(actions=plugin_action)if st.sidebar.button('清空對話', key='clear'):self.session_state.clear_state()uploaded_file = st.sidebar.file_uploader('上傳文件', type=['png', 'jpg', 'jpeg', 'mp4', 'mp3', 'wav'])return model_name, model, plugin_action, uploaded_filedef init_model(self, option):"""Initialize the model based on the selected option."""if option not in st.session_state['model_map']:if option.startswith('gpt'):st.session_state['model_map'][option] = GPTAPI(model_type=option)else:st.session_state['model_map'][option] = HFTransformerCasualLM('/root/model/Shanghai_AI_Laboratory/internlm-chat-7b')return st.session_state['model_map'][option]def initialize_chatbot(self, model, plugin_action):"""Initialize the chatbot with the given model and plugin actions."""return ReAct(llm=model, action_executor=ActionExecutor(actions=plugin_action))def render_user(self, prompt: str):with st.chat_message('user'):st.markdown(prompt)def render_assistant(self, agent_return):with st.chat_message('assistant'):for action in agent_return.actions:if (action):self.render_action(action)st.markdown(agent_return.response)def render_action(self, action):with st.expander(action.type, expanded=True):st.markdown("<p style='text-align: left;display:flex;'> <span style='font-size:14px;font-weight:600;width:70px;text-align-last: justify;'>插    件</span><span style='width:14px;text-align:left;display:block;'>:</span><span style='flex:1;'>"  # noqa E501+ action.type + '</span></p>',unsafe_allow_html=True)st.markdown("<p style='text-align: left;display:flex;'> <span style='font-size:14px;font-weight:600;width:70px;text-align-last: justify;'>思考步驟</span><span style='width:14px;text-align:left;display:block;'>:</span><span style='flex:1;'>"  # noqa E501+ action.thought + '</span></p>',unsafe_allow_html=True)if (isinstance(action.args, dict) and 'text' in action.args):st.markdown("<p style='text-align: left;display:flex;'><span style='font-size:14px;font-weight:600;width:70px;text-align-last: justify;'> 執行內容</span><span style='width:14px;text-align:left;display:block;'>:</span></p>",  # noqa E501unsafe_allow_html=True)st.markdown(action.args['text'])self.render_action_results(action)def render_action_results(self, action):"""Render the results of action, including text, images, videos, andaudios."""if (isinstance(action.result, dict)):st.markdown("<p style='text-align: left;display:flex;'><span style='font-size:14px;font-weight:600;width:70px;text-align-last: justify;'> 執行結果</span><span style='width:14px;text-align:left;display:block;'>:</span></p>",  # noqa E501unsafe_allow_html=True)if 'text' in action.result:st.markdown("<p style='text-align: left;'>" + action.result['text'] +'</p>',unsafe_allow_html=True)if 'image' in action.result:image_path = action.result['image']image_data = open(image_path, 'rb').read()st.image(image_data, caption='Generated Image')if 'video' in action.result:video_data = action.result['video']video_data = open(video_data, 'rb').read()st.video(video_data)if 'audio' in action.result:audio_data = action.result['audio']audio_data = open(audio_data, 'rb').read()st.audio(audio_data)def main():logger = get_logger(__name__)# Initialize Streamlit UI and setup sidebarif 'ui' not in st.session_state:session_state = SessionState()session_state.init_state()st.session_state['ui'] = StreamlitUI(session_state)else:st.set_page_config(layout='wide',page_title='lagent-web',page_icon='./docs/imgs/lagent_icon.png')# st.header(':robot_face: :blue[Lagent] Web Demo ', divider='rainbow')model_name, model, plugin_action, uploaded_file = st.session_state['ui'].setup_sidebar()# Initialize chatbot if it is not already initialized# or if the model has changedif 'chatbot' not in st.session_state or model != st.session_state['chatbot']._llm:st.session_state['chatbot'] = st.session_state['ui'].initialize_chatbot(model, plugin_action)for prompt, agent_return in zip(st.session_state['user'],st.session_state['assistant']):st.session_state['ui'].render_user(prompt)st.session_state['ui'].render_assistant(agent_return)# User input form at the bottom (this part will be at the bottom)# with st.form(key='my_form', clear_on_submit=True):if user_input := st.chat_input(''):st.session_state['ui'].render_user(user_input)st.session_state['user'].append(user_input)# Add file uploader to sidebarif uploaded_file:file_bytes = uploaded_file.read()file_type = uploaded_file.typeif 'image' in file_type:st.image(file_bytes, caption='Uploaded Image')elif 'video' in file_type:st.video(file_bytes, caption='Uploaded Video')elif 'audio' in file_type:st.audio(file_bytes, caption='Uploaded Audio')# Save the file to a temporary location and get the pathfile_path = os.path.join(root_dir, uploaded_file.name)with open(file_path, 'wb') as tmpfile:tmpfile.write(file_bytes)st.write(f'File saved at: {file_path}')user_input = '我上傳了一個圖像，路徑為: {file_path}. {user_input}'.format(file_path=file_path, user_input=user_input)agent_return = st.session_state['chatbot'].chat(user_input)st.session_state['assistant'].append(copy.deepcopy(agent_return))logger.info(agent_return.inner_steps)st.session_state['ui'].render_assistant(agent_return)if __name__ == '__main__':root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))root_dir = os.path.join(root_dir, 'tmp_dir')os.makedirs(root_dir, exist_ok=True)main()

Demo運行

streamlit run /root/code/lagent/examples/react_web_demo.py --server.address 127.0.0.1 --server.port 6006

運行效果：