中秋卷王:蒲语书生InterLM大模型实战闯关-进阶岛-MindSearch 快速部署
MindSearch 部署到Github Codespace 和 Hugging Face Space
任务要求:随着硅基流动提供了免费的 InternLM2.5-7B-Chat 服务,MindSearch 的部署与使用也就迎来了纯 CPU 版本,进一步降低了部署门槛。那就让我们来一起看看如何使用硅基流动的 API 来部署 MindSearch 吧。
项目链接:https://huggingface.co/spaces/jeronimoyang/mindsearch
一、环境配置
1、创建开发机
打开codespace主页,选择blank template。
浏览器会自动在新的页面打开一个web版的vscode
2、环境安装
新建一个目录用于存放 MindSearch 的相关代码,并把 MindSearch 仓库 clone 下来
mkdir -p /workspaces/mindsearch
cd /workspaces/mindsearch
git clone https://github.com/InternLM/MindSearch.git
cd MindSearch && git checkout b832275 && cd ..
创建一个 conda 环境
# 创建环境
conda create -n mindsearch python=3.10 -y
安装相关依赖
# 激活环境
conda activate mindsearch
# 安装依赖
pip install -r /workspaces/mindsearch/MindSearch/requirements.txt
二、获取硅基流动 API Key
1、注册硅基流动账号
我们打开 https://account.siliconflow.cn/login 来注册硅基流动的账号
2、创建API密钥
在完成注册后,打开 https://cloud.siliconflow.cn/account/ak 来准备 API Key。首先创建新 API 密钥,然后点击密钥进行复制,以备后续使用
三、启动 MindSearch
1、启动后端
启动 MindSearch 的后端
export SILICON_API_KEY=第二步中复制的密钥
conda activate mindsearch
cd /workspaces/mindsearch/MindSearch
pip install class_registry
python -m mindsearch.app --lang cn --model_format internlm_silicon --search_engine DuckDuckGoSearch
浏览器访问http://0.0.0.0:8002
2、启动前端
打开新终端启动 MindSearch 的前端
conda activate mindsearch
cd /workspaces/mindsearch/MindSearch
python frontend/mindsearch_gradio.py
前后端同时运行
浏览器访问http://127.0.0.1:7882
四、部署到 HuggingFace Space
1、前期准备工作
打开 https://huggingface.co/spaces ,并点击 Create new Space
输入 Space name 并选择 License 后,选择配置
进入 Settings,配置硅基流动的 API Key
选择 New secrets,name 一栏输入 SILICON_API_KEY,value 一栏输入 API Key 的内容
2、准备文件
新建一个目录,准备提交到 HuggingFace Space 的全部文件
# 创建新目录
mkdir -p /workspaces/mindsearch/mindsearch_deploy
# 准备复制文件
cd /workspaces/mindsearch
cp -r /workspaces/mindsearch/MindSearch/mindsearch /workspaces/mindsearch/mindsearch_deploy
cp /workspaces/mindsearch/MindSearch/requirements.txt /workspaces/mindsearch/mindsearch_deploy
# 创建 app.py 作为程序入口
touch /workspaces/mindsearch/mindsearch_deploy/app.py
app.py 的内容如下
import json
import os
import gradio as gr
import requests
from lagent.schema import AgentStatusCode
os.system("python -m mindsearch.app --lang cn --model_format internlm_silicon &")
PLANNER_HISTORY = []
SEARCHER_HISTORY = []
def rst_mem(history_planner: list, history_searcher: list):
'''
Reset the chatbot memory.
'''
history_planner = []
history_searcher = []
if PLANNER_HISTORY:
PLANNER_HISTORY.clear()
return history_planner, history_searcher
def format_response(gr_history, agent_return):
if agent_return['state'] in [
AgentStatusCode.STREAM_ING, AgentStatusCode.ANSWER_ING
]:
gr_history[-1][1] = agent_return['response']
elif agent_return['state'] == AgentStatusCode.PLUGIN_START:
thought = gr_history[-1][1].split('```')[0]
if agent_return['response'].startswith('```'):
gr_history[-1][1] = thought + '\n' + agent_return['response']
elif agent_return['state'] == AgentStatusCode.PLUGIN_END:
thought = gr_history[-1][1].split('```')[0]
if isinstance(agent_return['response'], dict):
gr_history[-1][
1] = thought + '\n' + f'```json\n{json.dumps(agent_return["response"], ensure_ascii=False, indent=4)}\n```' # noqa: E501
elif agent_return['state'] == AgentStatusCode.PLUGIN_RETURN:
assert agent_return['inner_steps'][-1]['role'] == 'environment'
item = agent_return['inner_steps'][-1]
gr_history.append([
None,
f"```json\n{json.dumps(item['content'], ensure_ascii=False, indent=4)}\n```"
])
gr_history.append([None, ''])
return
def predict(history_planner, history_searcher):
def streaming(raw_response):
for chunk in raw_response.iter_lines(chunk_size=8192,
decode_unicode=False,
delimiter=b'\n'):
if chunk:
decoded = chunk.decode('utf-8')
if decoded == '\r':
continue
if decoded[:6] == 'data: ':
decoded = decoded[6:]
elif decoded.startswith(': ping - '):
continue
response = json.loads(decoded)
yield (response['response'], response['current_node'])
global PLANNER_HISTORY
PLANNER_HISTORY.append(dict(role='user', content=history_planner[-1][0]))
new_search_turn = True
url = 'http://localhost:8002/solve'
headers = {'Content-Type': 'application/json'}
data = {'inputs': PLANNER_HISTORY}
raw_response = requests.post(url,
headers=headers,
data=json.dumps(data),
timeout=20,
stream=True)
for resp in streaming(raw_response):
agent_return, node_name = resp
if node_name:
if node_name in ['root', 'response']:
continue
agent_return = agent_return['nodes'][node_name]['detail']
if new_search_turn:
history_searcher.append([agent_return['content'], ''])
new_search_turn = False
format_response(history_searcher, agent_return)
if agent_return['state'] == AgentStatusCode.END:
new_search_turn = True
yield history_planner, history_searcher
else:
new_search_turn = True
format_response(history_planner, agent_return)
if agent_return['state'] == AgentStatusCode.END:
PLANNER_HISTORY = agent_return['inner_steps']
yield history_planner, history_searcher
return history_planner, history_searcher
with gr.Blocks() as demo:
gr.HTML("""<h1 align="center">MindSearch Gradio Demo</h1>""")
gr.HTML("""<p style="text-align: center; font-family: Arial, sans-serif;">MindSearch is an open-source AI Search Engine Framework with Perplexity.ai Pro performance. You can deploy your own Perplexity.ai-style search engine using either closed-source LLMs (GPT, Claude) or open-source LLMs (InternLM2.5-7b-chat).</p>""")
gr.HTML("""
<div style="text-align: center; font-size: 16px;">
<a href="https://github.com/InternLM/MindSearch" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">🔗 GitHub</a>
<a href="https://arxiv.org/abs/2407.20183" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">📄 Arxiv</a>
<a href="https://huggingface.co/papers/2407.20183" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">📚 Hugging Face Papers</a>
<a href="https://huggingface.co/spaces/internlm/MindSearch" style="text-decoration: none; color: #4A90E2;">🤗 Hugging Face Demo</a>
</div>
""")
with gr.Row():
with gr.Column(scale=10):
with gr.Row():
with gr.Column():
planner = gr.Chatbot(label='planner',
height=700,
show_label=True,
show_copy_button=True,
bubble_full_width=False,
render_markdown=True)
with gr.Column():
searcher = gr.Chatbot(label='searcher',
height=700,
show_label=True,
show_copy_button=True,
bubble_full_width=False,
render_markdown=True)
with gr.Row():
user_input = gr.Textbox(show_label=False,
placeholder='帮我搜索一下 InternLM 开源体系',
lines=5,
container=False)
with gr.Row():
with gr.Column(scale=2):
submitBtn = gr.Button('Submit')
with gr.Column(scale=1, min_width=20):
emptyBtn = gr.Button('Clear History')
def user(query, history):
return '', history + [[query, '']]
submitBtn.click(user, [user_input, planner], [user_input, planner],
queue=False).then(predict, [planner, searcher],
[planner, searcher])
emptyBtn.click(rst_mem, [planner, searcher], [planner, searcher],
queue=False)
demo.queue()
demo.launch(server_name='0.0.0.0',
server_port=7860,
inbrowser=True,
share=True)
3、提交文件
创建一个有写权限的token
从huggingface把空的代码仓库clone到codespace
/workspaces/codespaces-blank
git clone https://huggingface.co/spaces/<你的名字>/<仓库名称>
把刚才准备的文件都copy进来
cd <仓库名称>
# 把刚才准备的文件都copy进来
cp -r /workspaces/mindsearch/mindsearch_deploy/* .
在requirements.txt文件中加入class_registry
把代码提交到huggingface space会自动启动项目
git add .
git commit -m "update"
# 把token挂到仓库上,让自己有写权限
git remote set-url orign https://<你的名字>:<上面创建的token>@huggingface.co/spaces/<你的名字>/<仓库名称>
git push
4、进行测试