Open main menu
首页
专栏
课程
分类
归档
Chat
Sci-Hub
谷歌学术
Libgen
GitHub镜像
登录/注册
搜索
关闭
Previous
Previous
Next
Next
ChatGPT使用学习(二):ChatPaper安装到测试详细教程(一文包会)
sockstack
/
255
/
2023-11-08 12:01:35
<p><span style="color: red; font-size: 18px">ChatGPT 可用网址,仅供交流学习使用,如对您有所帮助,请收藏并推荐给需要的朋友。</span><br><a href="https://ckai.xyz/?sockstack§ion=detail" target="__blank">https://ckai.xyz</a><br><br></p> <article class="baidu_pl"><div id="article_content" class="article_content clearfix"> <link rel="stylesheet" href="https://csdnimg.cn/release/blogv2/dist/mdeditor/css/editerView/kdoc_html_views-1a98987dfd.css"> <link rel="stylesheet" href="https://csdnimg.cn/release/blogv2/dist/mdeditor/css/editerView/ck_htmledit_views-25cebea3f9.css"> <div id="content_views" class="markdown_views prism-tomorrow-night-eighties"> <svg xmlns="http://www.w3.org/2000/svg" style="display: none;"><path stroke-linecap="round" d="M5,0 0,2.5 5,5z" id="raphael-marker-block" style="-webkit-tap-highlight-color: rgba(0, 0, 0, 0);"></path></svg><p></p> <div class="toc"> <h3>ChatPaper</h3> <ul> <li>1.简介及功能</li> <li>2.前置准备</li> <li>3.开始使用-命令行</li> <li>4.开始使用-网页</li> </ul> </div> <p></p> <h1> <a id="1_2"></a>1.简介及功能</h1> <p> ChatPaper是一种基于文本生成技术的研究论文,可以根据用户的输入进行智能回复和互动,具有类似于ChatGPT的功能。它可以根据关键字来获取相应的论文,并通过分析<mark>论文的标题、作者、单位、链接、研究背景、其它工作的问题、本文方法、本文方法具体步骤、总结本文的优缺点</mark>等内容,实现一分钟下载一篇最新arxiv论文,一个分钟速读主要信息。用户可以根据以上内容来判断是否需要更深入地了解该论文。</p> <h1> <a id="2_4"></a>2.前置准备</h1> <p>**第一步:**下载项目代码:https://github.com/kaixindelele/ChatPaper</p> <pre><code class="prism language-python">git clone https<span class="token punctuation">:</span><span class="token operator">//</span>github<span class="token punctuation">.</span>com<span class="token operator">/</span>kaixindelele<span class="token operator">/</span>ChatPaper<span class="token punctuation">.</span>git </code></pre> <p><strong>第二步</strong>:配置环境<br> 由于我已经安装了Anaconda和Pycharm,具体细节可以看这篇博客:点击</p> <pre><code class="prism language-python">conda create <span class="token operator">-</span>n chatgpt_pa python<span class="token operator">=</span><span class="token number">3.9</span> <span class="token comment"># 进入到项目目录</span> python <span class="token operator">-</span>m pip install <span class="token operator">-</span>r requirements<span class="token punctuation">.</span>txt <span class="token operator">-</span>i https<span class="token punctuation">:</span><span class="token operator">//</span>mirrors<span class="token punctuation">.</span>aliyun<span class="token punctuation">.</span>com<span class="token operator">/</span>pypi<span class="token operator">/</span>simple<span class="token operator">/</span> </code></pre> <p><strong>第三步</strong>:修改代码文件内容<br> 你需要修改的地方如下<br> <img referrerpolicy="no-referrer" src="https://img-blog.csdnimg.cn/b1b58a83bd604487b39d7cfa458211e3.png" alt="在这里插入图片描述"><br> 填入和这篇博客一样的Key即可(需要自己去官网获取):点击</p> <h1> <a id="3_20"></a>3.开始使用-命令行</h1> <p> 由于这里面太多功能,就不一一演示结果,可以根据自己的需求进行处理。<br> <strong>注意</strong>:key_word不重要,但是filter_keys非常重要! 一定要修改成你的关键词。</p> <p><mark>第一种</mark>:</p> <pre><code class="prism language-python">python chat_paper<span class="token punctuation">.</span>py <span class="token operator">-</span><span class="token operator">-</span>query <span class="token string">"chatgpt robot"</span> <span class="token operator">-</span><span class="token operator">-</span>filter_keys <span class="token string">"chatgpt robot"</span> <span class="token operator">-</span><span class="token operator">-</span>max_results <span class="token number">3</span> </code></pre> <p><strong>结果</strong>:</p> <p><mark>第二种</mark>:</p> <pre><code class="prism language-python">python chat_arxiv<span class="token punctuation">.</span>py <span class="token operator">-</span><span class="token operator">-</span>query <span class="token string">"chatgpt robot"</span> <span class="token operator">-</span><span class="token operator">-</span>page_num <span class="token number">2</span> <span class="token operator">-</span><span class="token operator">-</span>max_results <span class="token number">3</span> <span class="token operator">-</span><span class="token operator">-</span>days <span class="token number">10</span> </code></pre> <p>其中query是读者输入的搜索查询,filter_keys是用于在摘要中筛选的关键词,page_num是搜索的页面,每页和官网一样,最大是50篇,max_results是最终总结前N篇的文章,days是选最近几天的论文,严格筛选!<br> <strong>结果:</strong><br> <img referrerpolicy="no-referrer" src="https://img-blog.csdnimg.cn/72e3650ccfc74a019146794fbbe8e61a.png" alt="在这里插入图片描述"><br> <mark>第三种</mark>:<br> Arxiv在线批量搜索+下载+总结+高级搜索: 运行chat_paper.py, 比如:</p> <pre><code class="prism language-python">python chat_paper<span class="token punctuation">.</span>py <span class="token operator">-</span><span class="token operator">-</span>query <span class="token string">"all: reinforcement learning robot 2023"</span> <span class="token operator">-</span><span class="token operator">-</span>filter_keys <span class="token string">"reinforcement robot"</span> <span class="token operator">-</span><span class="token operator">-</span>max_results <span class="token number">3</span> </code></pre> <p><mark>第四种</mark>:<br> Arxiv在线批量搜索+下载+总结+高级搜索+指定作者: 运行chat_paper.py, 比如:</p> <pre><code class="prism language-python">python chat_paper<span class="token punctuation">.</span>py <span class="token operator">-</span><span class="token operator">-</span>query <span class="token string">"ti: Sergey Levine"</span> <span class="token operator">-</span><span class="token operator">-</span>filter_keys <span class="token string">"reinforcement robot"</span> <span class="token operator">-</span><span class="token operator">-</span>max_results <span class="token number">3</span> </code></pre> <p><mark>第五种</mark>:<br> 本地pdf总结: 运行chat_paper.py, 比如:</p> <pre><code class="prism language-python">python chat_paper<span class="token punctuation">.</span>py <span class="token operator">-</span><span class="token operator">-</span>pdf_path <span class="token string">"demo.pdf"</span> </code></pre> <p><mark>第六种</mark>:<br> 本地文件夹批量总结: 运行chat_paper.py, 比如:</p> <pre><code class="prism language-python">python chat_paper<span class="token punctuation">.</span>py <span class="token operator">-</span><span class="token operator">-</span>pdf_path <span class="token string">"your_absolute_path"</span> </code></pre> <p><mark>第七种</mark>:<br> 谷歌学术论文整理: 运行google_scholar_spider.py, 比如:</p> <pre><code class="prism language-python">python google_scholar_spider<span class="token punctuation">.</span>py <span class="token operator">-</span><span class="token operator">-</span>kw <span class="token string">"deep learning"</span> <span class="token operator">-</span><span class="token operator">-</span>nresults <span class="token number">30</span> <span class="token operator">-</span><span class="token operator">-</span>csvpath <span class="token string">"./data"</span> <span class="token operator">-</span><span class="token operator">-</span>sortby <span class="token string">"cit/year"</span> <span class="token operator">-</span><span class="token operator">-</span>plotresults <span class="token number">1</span> </code></pre> <p>此命令在Google Scholar上搜索与“deep learning”相关的文章,检索30个结果,将结果保存到“./data”文件夹中的CSV文件中,按每年引用次数排序数据,并绘制结果。</p> <p>最后会在export下生成对应的报告,默认为md文档。</p> <h1> <a id="4_68"></a>4.开始使用-网页</h1> <p><mark>感觉没有命令行好用</mark><br> <img referrerpolicy="no-referrer" src="https://img-blog.csdnimg.cn/c2c71f8cfc4249f08c4f7ac4a40594c1.png" alt="在这里插入图片描述"></p> <p> 除了用命令行的方式,还可以用网页的形式来操作。启动服务</p> <pre><code class="prism language-python">python3 app<span class="token punctuation">.</span>py </code></pre> <p> 启动 Flask 服务。运行此命令后,Flask 服务将在本地的 5000 端口上启动并等待用户请求。在浏览器中访问以下地址之一以访问 Flask 服务的主页:</p> <pre><code class="prism language-python">http<span class="token punctuation">:</span><span class="token operator">//</span><span class="token number">127.0</span><span class="token number">.0</span><span class="token number">.1</span><span class="token punctuation">:</span><span class="token number">5000</span><span class="token operator">/</span> 或 http<span class="token punctuation">:</span><span class="token operator">//</span><span class="token number">127.0</span><span class="token number">.0</span><span class="token number">.1</span><span class="token punctuation">:</span><span class="token number">5000</span><span class="token operator">/</span>index </code></pre> <p> 访问 http://127.0.0.1:5000/ 后,您将看到主页。在主页上,您可以点击不同的链接来调用各种服务。您可以通过修改链接中的参数值来实现不同的效果。有关参数详细信息,请参阅上一步骤中的详细介绍主界面:</p> <p> 特别的,这四个接口实际是封装了根目录下四个脚本的 web 界面。参数可以通过链接来修改。例如要运行“arxiv?query=GPT-4&key_word=GPT+robot&page_num=1&max_results=1&days=1&sort=web&save_image=False&file_format=md&language=zh”的话,相当于在根目录下调用 chat_arxiv.py 并返回结果。这个显示的结果和在命令行中调用的结果是一样的(即:python chat_arxiv.py --query “GPT-4” --key_word “GPT robot” --page_num 1 --max_results 1 --days 1 --sort “web” --save_image False --file_format “md” --language “zh”)。您可以通过修改参数来获得其他搜索结果。</p> <p> 如果以这种方式部署的话,结果会保存在同级目录下新生成的export、pdf_files 和response_file三个文件夹里</p> </div> <link href="https://csdnimg.cn/release/blogv2/dist/mdeditor/css/editerView/markdown_views-0407448025.css" rel="stylesheet"> <link href="https://csdnimg.cn/release/blogv2/dist/mdeditor/css/style-c216769e99.css" rel="stylesheet"> </div> <div id="treeSkill"></div> </article>
ChatGPT使用学习(二):ChatPaper安装到测试详细教程(一文包会)
作者
sockstack
许可协议
CC BY 4.0
发布于
2023-11-08
修改于
2024-12-23
上一篇:软件:常用 Linux 软件汇总,值得收藏
下一篇:全网最详细中英文ChatGPT接口文档(五)30分钟快速入门ChatGPT——手把手示例教程:如何建立一个人工智能回答关于您的网站问题,小白也可学
尚未登录
登录 / 注册
文章分类
博客重构之路
5
Spring Boot简单入门
4
k8s 入门教程
0
MySQL 知识
1
NSQ 消息队列
0
ThinkPHP5 源码分析
5
使用 Docker 从零开始搭建私人代码仓库
3
日常开发汇总
4
标签列表
springboot
hyperf
swoole
webman
php
多线程
数据结构
docker
k8s
thinkphp
mysql
tailwindcss
flowbite
css
前端