AutoGPT 是什么?它有哪些应用场景?

关注者
685
被浏览
439,259
登录后你可以
不限量看优质回答 私信答主深度交流 精彩内容一键收藏

大佬们对于自动化一切的追求是无止境的,在我们感叹 ChatGPT 的强大时,他们又推出了 Auto-GPT[1]

Auto-GPT 利用 OpenAI 的 GPT-3.5 和 GPT-4 模型能力与在线软件和服务进行交互,使其能够“自主”执行我们的任务。

但是它真的能实现完全的自动化,真正的能解放双手吗?我们拭目以待。

今天体验的版本是 0.3。可以看到新版本加入了 Plugins 功能,第三方开发人员可以通过编写插件来扩展 autogpt 的功能。这样我们可以为它添加更多的交互行为。

注意: 因为演示需要用到 OpenAI 的 API key,为避免账户被封禁,国内环境下使用还是要谨慎些。 这次我还是继续白嫖 Google-colab[2] 服务,来演示下 Auto-GPT 的能力。如果大家没有访问 colab 的方法的话,还可以使用 github 提供的 codespaces 去体验(国内慢了点但能用就行)。

安装

我们通过 git 直接 clone Auto-GPT 项目,选择 stable 分支。

!git clone -b stable https://github.com/Significant-Gravitas/Auto-GPT.git
%cd Auto-GPT

.env.template 文件名修改为 .env 。并正确填写自己的 OpenAI API key。

OPENAI_API_KEY=your-openai-api-key

启动

!sh run.sh

因为他会先安装依赖文件,所以第一次启动会慢些。大家在本地执行的时候,可能会出现各种依赖安装失败的问题,建议大家更换国内镜像源。

体验

我们的目标: 让 autogpt 写一篇 1000 字文章,介绍 autogpt 并写出使用教程

我们根据提示来,他需要输入回车继续,我们就在后面输入框输入。然后它问需要 autogpt 做什么,这里输入我们的目的。建议大家输入英文,因为 autogpt 很多情况会通过 google 搜索,对中文支持不是很友好。

我们输入目的后可以看到,新版本的 autogpt 已经可以自己设定自己的角色了,甚至连上一版本需要我们输入的目标步骤也可以自己定了。他似乎又进化了:

AUTOGPTGPT  has been created with the following details:
Name:  AUTOGPTGPT
Role:  an AI writing assistant that helps users create high-quality content by providing suggestions, generating ideas, and improving the overall writing process.
Goals:
-  Assist users in creating a 1000-word article introducing Autogpt and providing a tutorial on how to use it.
-  Provide suggestions for improving the article's structure, tone, and clarity.
-  Generate ideas for the article's content and help users expand on them.
-  Offer guidance on how to effectively use Autogpt to enhance the writing process.
-  Ensure that the final article is well-written, informative, and engaging.

大家可以自行翻译下,autogpt 给自己设定了角色并制定了每一步的目标。可以看到还是很合理的,至少比我自己输入的要好很多。接着 autogpt 开始列出它的想法:

THOUGHTS: To begin, let's create a file to store the article. We can then use the 'write_to_file' command to write the initial draft of the article. Once we have a draft, we can use the 'analyze_code' command to check for any grammatical errors or areas where we can improve the structure and clarity of the article. Additionally, we can use the 'google' command to research more information about Autogpt and gather ideas for the article's content.

THOUGHTS:

  • 想先创建文件,然后执行 write_to_file 命令编写文章的初稿
  • 一旦有了草稿,就可以使用 analyze_code 命令来检查是否有语法错误或可以改进文章结构和清晰度的地方
  • 此外,可以使用 google 命令来研究有关 autogpt 的更多信息

然后它根据想法开始进行推理,并列出计划:

REASONING:  Creating a file to store the article will allow us to easily edit and update the article as needed. Writing the initial draft will give us a starting point to work from, and using the 'analyze_code' command will help us improve the quality of the article. Researching more information about Autogpt will help us create a more informative and engaging article.
PLAN: