基础任务
按照教程,将 MindSearch 部署到 HuggingFace,提供截图和 Hugging Face 的Space的链接。
过程记录
0. 简介
MindSearch是由上海人工智能实验室开发的一个基于大语言模型(LLM)和搜索引擎相结合的系统,继 OpenAI 发布 SearchGPT 之后,国内也涌现出一批优秀的AI搜索引擎,其中,由中科大和上海人工智能实验室联合研发的 MindSearch(思·索)尤为引人注目。这款开源AI搜索引擎,不仅性能媲美Perplexity.ai Pro,更重要的是,它跳脱了传统搜索引擎的窠臼,不再仅仅依赖关键词匹配,而是模拟人类的思维过程,深度理解用户的搜索意图,并提供更精准、更全面的搜索结果。这款开源AI搜索引擎的出现,无疑为我们打开了一扇通往未来搜索引擎的大门。
我们模仿人类思维引出深度人工智能搜索,MindSearch 是一个开源的 AI 搜索引擎框架,具有 Perplexity.ai Pro 的性能。您可以使用闭源 LLM(GPT、Claude)或开源 LLM(InternLM2.5-7b-chat)将其与您自己的 perplexity.ai 风格的搜索引擎一起部署。它具有以下特点:
🤔询问您想知道的一切:MindSearch 旨在解决您生活中的任何问题并使用网络知识。
📚深入的知识发现:MindSearch 浏览数百个网页来回答您的问题,提供更深入、更广泛的知识库答案。
🔍详细的解决方案路径:MindSearch 公开所有细节,让用户可以检查他们想要的一切。这大大提高了其最终响应的可信度和可用性。
💻优化的 UI 体验:为用户提供各种类型的界面,包括 React、Gradio、Streamlit 和 Terminal。根据需要选择任意类型。
🧠动态图构建过程:MindSearch 将用户查询分解为原子子问题作为图中的节点,并根据 WebSearcher 的搜索结果逐步扩展图。
1. 仓库准备
mkdir -p /workspaces/mindsearch
cd /workspaces/mindsearch
git clone https://github.com/InternLM/MindSearch.git
cd MindSearch && git checkout b832275 && cd ..
2. 环境准备
conda create -n mindsearch python=3.10 -y
# 激活环境
conda activate mindsearch
# 安装依赖
pip install -r /workspaces/mindsearch/MindSearch/requirements.txt
3. 获取InternLM2模型的api-key(基于硅基流动)
site: https://cloud.siliconflow.cn/
4. 本地启动 MindSearch
4.1 启动后端
由于硅基流动 API 的相关配置已经集成在了 MindSearch 中,所以我们可以直接执行下面的代码来启动 MindSearch 的后端。
export SILICON_API_KEY=xxx
conda activate mindsearch
cd /workspaces/mindsearch/MindSearch
python -m mindsearch.app --lang cn --model_format internlm_silicon --search_engine DuckDuckGoSearch
4.2 启动前端
conda activate mindsearch
cd /workspaces/mindsearch/MindSearch
python frontend/mindsearch_gradio.py
结果截图
6. 部署到 HuggingFace Space
首先需要在huggingface创建一个app(详情参考huggingface文档),然后我们在本地创建好对应的项目仓库。
# 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
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)
然后上传到huggingface上即可。
结果截图:
7. MindSearch体验
体验链接:https://huggingface.co/spaces/Alannikos768/MindSearch_App
欢迎使用,不要忘记点个like哦~