任务拆解,悠然自得,自动版本的ChatGPT,AutoGPT自动人工智能AI任务实践(Python3.10)

简介: 当我们使用ChatGPT完成某些工作的时候,往往需要多轮对话,比如让ChatGPT分析、翻译、总结一篇网上的文章或者文档,再将总结的结果以文本的形式存储在本地。过程中免不了要和ChatGPT“折冲樽俎”一番,事实上,这个“交涉”的过程也可以自动化,AutoGPT可以帮助我们自动拆解任务,没错,程序能做到的事情,人类绝不亲力亲为。我们唯一需要做的,就是告诉AutoGPT一个任务目标,AutoGPT会自动根据任务目标将任务拆解成一个个的小任务,并且逐个完成,简单且高效。

当我们使用ChatGPT完成某些工作的时候,往往需要多轮对话,比如让ChatGPT分析、翻译、总结一篇网上的文章或者文档,再将总结的结果以文本的形式存储在本地。过程中免不了要和ChatGPT“折冲樽俎”一番,事实上,这个“交涉”的过程也可以自动化,AutoGPT可以帮助我们自动拆解任务,没错,程序能做到的事情,人类绝不亲力亲为。

我们唯一需要做的,就是告诉AutoGPT一个任务目标,AutoGPT会自动根据任务目标将任务拆解成一个个的小任务,并且逐个完成,简单且高效。

配置AutoGPT

先确保本地环境安装好了Python3.10.9

接着运行Git命令拉取项目:

git clone https://github.com/Significant-Gravitas/Auto-GPT.git

随后进入项目的目录:

cd Auto-GPT

安装相关的依赖库:

pip3 install -r requirements.txt

安装成功后,复制一下项目的配置文件:

cp .env.template .env

这里通过cp命令将配置文件模版.env.template复制成为一个新的配置文件.env。

随后将Openai的秘钥填入配置文件:

### OPENAI  
# OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key)  
# TEMPERATURE - Sets temperature in OpenAI (Default: 0)  
# USE_AZURE - Use Azure OpenAI or not (Default: False)  
OPENAI_API_KEY=您的秘钥  
TEMPERATURE=0  
USE_AZURE=False

除了Openai官方的接口秘钥,AutoGPT也支持微软Azure的接口。

如果希望使用微软Azure的接口,需要将配置中的USE\_AZURE设置为True,随后复制azure.yaml.template配置模版为新的azure.yaml配置文件。

接着将微软Azure服务的秘钥填入azure.yaml即可。

由于微软Azure接入Openai接口需要极其复杂的申请流程,这里还是直接使用OpenAI官方的接口。

当然了,如果不想在本地装那么多依赖,也可以通过Docker来构建Auto-GPT的容器:

docker build -t autogpt .  
docker run -it --env-file=./.env -v $PWD/auto_gpt_workspace:/app/auto_gpt_workspace autogpt

这里Docker会自动读取项目中的Dockerfile配置文件进行构建,相当方便。

至此,Auto-GPT就配置好了。

运行Auto-GPT

在项目根目录运行命令:

python3 -m autogpt --debug

即可启动AutoGPT:

➜  Auto-GPT git:(master) python -m autogpt --debug         
Warning: The file 'AutoGpt.json' does not exist. Local memory would not be saved to a file.  
Debug Mode:  ENABLED  
Welcome to Auto-GPT!  Enter the name of your AI and its role below. Entering nothing will load defaults.  
Name your AI:  For example, 'Entrepreneur-GPT'  
AI Name:

首先创建AutoGPT机器人的名字:

AI Name: v3u.cn  
v3u.cn here!  I am at your service.  
Describe your AI's role:  For example, 'an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.'  
v3u.cn is:

创建好名字以后,Auto-GPT就可以随时为您效劳了。

首先为AutoGPT设置目标:

v3u.cn is: Analyze the contents of this article,the url is https://v3u.cn/a_id_303,and write the result to goal.txt

这里我们要求AutoGPT分析并且总结v3u.cn/a\_id\_303这篇文章,并且将分析结果写入本地的goal.txt文件。

程序返回:

Enter up to 5 goals for your AI:  For example: Increase net worth, Grow Twitter Account, Develop and manage multiple businesses autonomously'  
Enter nothing to load defaults, enter nothing when finished.  
Goal 1:   
Using memory of type:  LocalCache

AutoGPT会告诉你可以最多拆解为五个任务,我们可以自己拆解,也可以让机器人帮助我们拆解,直接按回车,让AutoGPT自动拆解任务即可。

接着程序会自动爬取这篇文章的内容,然后使用gpt-3.5-turbo模型来进行分析:

Goal 1:   
Using memory of type:  LocalCache  
Using Browser:  chrome  
  Token limit: 4000  
  Memory Stats: (0, (0, 1536))  
  Token limit: 4000  
  Send Token Count: 936  
  Tokens remaining for response: 3064  
  ------------ CONTEXT SENT TO AI ---------------  
  System: The current time and date is Mon Apr 17 20:29:37 2023  
    
  System: This reminds you of these events from your past:  
  
  
  
    
  User: Determine which next command to use, and respond using the format specified above:  
    
  ----------- END OF CONTEXT ----------------  
Creating chat completion with model gpt-3.5-turbo, temperature 0.0, max_tokens 3064  
The JSON object is valid.  
 THOUGHTS:  Let's start by browsing the article at https://v3u.cn/a_id_303 to get a better understanding of its contents.  
REASONING:  Browsing the article will allow us to analyze its contents and determine the appropriate next steps.  
PLAN:   
-  Browse the article  
-  Analyze its contents  
-  Determine the appropriate next steps  
CRITICISM:  None  
NEXT ACTION:  COMMAND = browse_website ARGUMENTS = {'url': 'https://v3u.cn/a_id_303', 'question': 'analyze the contents of the article'}  
Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ...  
Input:y  
-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=   
[WDM] - Downloading: 100%|████████████████████████████████████████████| 8.04M/8.04M [00:03<00:00, 2.42MB/s]  
Text length: 6977 characters  
Adding chunk 1 / 1 to memory  
Summarizing chunk 1 / 1  
Creating chat completion with model gpt-3.5-turbo, temperature 0.0, max_tokens 300  
SYSTEM:  Command browse_website returned: Error: This model's maximum context length is 4097 tokens. However, you requested 4339 tokens (4039 in the messages, 300 in the completion). Please reduce the length of the messages or completion.  
  Token limit: 4000  
  Memory Stats: (2, (2, 1536))  
  Token limit: 4000  
  Send Token Count: 1472  
  Tokens remaining for response: 2528  
  ------------ CONTEXT SENT TO AI ---------------  
  System: The current time and date is Mon Apr 17 20:30:19 2023  
    
  System: This reminds you of these events from your past:  
['Assistant Reply: {\n    "thoughts": {\n        "text": "Let\'s start by browsing the article at https://v3u.cn/a_id_303 to get a better understanding of its contents.",\n        "reasoning": "Browsing the article will allow us to analyze its contents and determine the appropriate next steps.",\n        "plan": "- Browse the article\\n- Analyze its contents\\n- Determine the appropriate next steps",\n        "criticism": "None",\n        "speak": "I suggest we start by browsing the article at the given URL to analyze its contents and determine the appropriate next steps."\n    },\n    "command": {\n        "name": "browse_website",\n        "args": {\n            "url": "https://v3u.cn/a_id_303",\n            "question": "analyze the contents of the article"\n        }\n    }\n} \nResult: Command browse_website returned: Error: This model\'s maximum context length is 4097 tokens. However, you requested 4339 tokens (4039 in the messages, 300 in the completion). Please reduce the length of the messages or completion. \nHuman Feedback: GENERATE NEXT COMMAND JSON ']  
  
  
    
  User: Determine which next command to use, and respond using the format specified above:  
    
  Assistant: {  
    "thoughts": {  
        "text": "Let's start by browsing the article at https://v3u.cn/a_id_303 to get a better understanding of its contents.",  
        "reasoning": "Browsing the article will allow us to analyze its contents and determine the appropriate next steps.",  
        "plan": "- Browse the article\n- Analyze its contents\n- Determine the appropriate next steps",  
        "criticism": "None",  
        "speak": "I suggest we start by browsing the article at the given URL to analyze its contents and determine the appropriate next steps."  
    },  
    "command": {  
        "name": "browse_website",  
        "args": {  
            "url": "https://v3u.cn/a_id_303",  
            "question": "analyze the contents of the article"  
        }  
    }  
}  
    
    
  User: Determine which next command to use, and respond using the format specified above:  
    
  ----------- END OF CONTEXT ----------------  
Creating chat completion with model gpt-3.5-turbo, temperature 0.0, max_tokens 2528

最后将分析结果写入goal.txt文件:

这篇文章主要阐释了苹果Mac电脑可以完成机器学习和深度学习任务,并且通过深度学习框架Tensorflow的安装和运行进行了佐证,同时也对Tensorflow的CPU和GPU的两种模型训练模式进行了深度对比和测试。

一气呵成,流畅丝滑。

结语

AutoGPT和其他 AI 程序的不同之处在于,它专门专注于在无需人工干预的情况下生成提示和自动执行多步骤任务。它还具有扫描互联网或在用户计算机上执行命令以获取信息的能力,这使其有别于可能仅依赖于预先存在的数据集的其他人工智能程序。

AutoGPT的底层逻辑并不复杂:先通过搜索引擎检索任务,然后把结果和目标丢给gpt让它给出序列化方案json,再把方案分段丢给gpt,最后用shell去创建Python文件+json.load并且执行,是一个反复递归的过程。

不能否认的是,虽然实现逻辑简单,但这无疑是一种“自我进化”的过程,相信随着时间的推移,AutoGPT可以更好地处理愈加复杂的任务。

相关文章
|
13天前
|
机器学习/深度学习 人工智能 计算机视觉
MILS:无需对LLM进行额外训练就能处理多模态任务,Meta AI提出零样本生成多模态描述方法
MILS 是 Meta AI 推出的零样本生成高质量多模态描述方法,支持图像、视频和音频的描述生成,无需额外训练。
102 34
MILS:无需对LLM进行额外训练就能处理多模态任务,Meta AI提出零样本生成多模态描述方法
|
19天前
|
人工智能 算法 计算机视觉
【01】opencv项目实践第一步opencv是什么-opencv项目实践-opencv完整入门以及项目实践介绍-opencv以土壤和水滴分离的项目实践-人工智能AI项目优雅草卓伊凡
【01】opencv项目实践第一步opencv是什么-opencv项目实践-opencv完整入门以及项目实践介绍-opencv以土壤和水滴分离的项目实践-人工智能AI项目优雅草卓伊凡
115 62
【01】opencv项目实践第一步opencv是什么-opencv项目实践-opencv完整入门以及项目实践介绍-opencv以土壤和水滴分离的项目实践-人工智能AI项目优雅草卓伊凡
|
23天前
|
机器学习/深度学习 人工智能 弹性计算
阿里云AI服务器价格表_GPU服务器租赁费用_AI人工智能高性能计算推理
阿里云AI服务器提供多种配置,包括CPU+GPU、FPGA等,适用于人工智能、机器学习和深度学习等计算密集型任务。本文整理了阿里云GPU服务器的优惠价格,涵盖NVIDIA A10、V100、T4等型号,提供1个月、1年和1小时的收费明细。具体规格如A10卡GN7i、V100-16G卡GN6v等,适用于不同业务场景,详情见官方页面。
118 11
|
1月前
|
数据采集 人工智能 自然语言处理
Riona-AI-Agent:自媒体 AI 代理!自动点赞、评论、个性化内容生成和发布等交互任务
Riona-AI-Agent 是一款基于 Node.js 和 TypeScript 的 AI 自动化工具,支持 Instagram、Twitter 等平台的自动化交互,生成高质量内容,提升社交媒体管理效率。
151 13
Riona-AI-Agent:自媒体 AI 代理!自动点赞、评论、个性化内容生成和发布等交互任务
|
1月前
|
人工智能 开发框架 自然语言处理
Eko:一句话就能快速构建复杂工作流的 AI 代理开发框架!快速实现自动操作电脑和浏览器完成任务
Eko 是 Fellou AI 推出的开源 AI 代理开发框架,支持自然语言驱动,帮助开发者快速构建从简单指令到复杂工作流的智能代理。
305 12
Eko:一句话就能快速构建复杂工作流的 AI 代理开发框架!快速实现自动操作电脑和浏览器完成任务
|
1月前
|
数据采集 人工智能 算法
Seer:上海 AI Lab 与北大联合开源端到端操作模型,结合视觉预测与动作执行信息,使机器人任务提升成功率43%
Seer是由上海AI实验室与北大等机构联合推出的端到端操作模型,结合视觉预测与动作执行,显著提升机器人任务成功率。
72 20
Seer:上海 AI Lab 与北大联合开源端到端操作模型,结合视觉预测与动作执行信息,使机器人任务提升成功率43%
|
1月前
|
人工智能 前端开发 程序员
通义灵码 AI 程序员全面上线,能和人类协作完成复杂开发任务
1 月 8 日消息,阿里云通义灵码 AI 程序员已全面上线,成为全球首个同时支持 VS Code、JetBrains IDEs 开发工具的 AI 程序员产品。此次上线的 AI 程序员相比传统 AI 辅助编程工具,能力更全面,可以让开发者以更高效、更沉浸的方式完成编码任务,通过全程对话协作的方式,就能完成从 0 到 1 的业务需求开发、问题修复、单元测试批量生成等复杂编码任务。
357 65
|
1月前
|
消息中间件 机器学习/深度学习 人工智能
AI赋能运维:实现运维任务的智能化自动分配
AI赋能运维:实现运维任务的智能化自动分配
164 24
|
1月前
|
人工智能 API
MMedAgent:专为医疗领域设计的多模态 AI 智能体,支持医学影像处理、报告生成等多种医疗任务
MMedAgent 是专为医疗领域设计的多模态AI智能体,支持多种医疗任务,包括医学影像处理、报告生成等,性能优于现有开源方法。
151 19
MMedAgent:专为医疗领域设计的多模态 AI 智能体,支持医学影像处理、报告生成等多种医疗任务
|
Java Linux Shell
centos7内网离线安装face_recognition、python、pip、CMake、dlib,离线升级gcc/切换gcc,文末有face_recognition的docker版本
公司项目需要人脸识别,本来app自带人脸识别,结果api支持的设备试了一圈就一个同事的华为Mate40Pro可以,所以使用无望。接着找了一下免费的java离线人脸识别sdk,发现虹软的确实简单好用,一会就在linux上弄好并测试通过了,然而在准备集成进去开写代码时,不小心看到了一眼首次激活需联网,后续方可离线使用,好吧,我们内网机器首次都不可能的,接着看了下离线激活方法,首先需要企业认证,这一步我们肯定没法做的,毕竟不是之前的小公司了,营业执照啥的随便给我肯定不行,直接放弃了。后来在同事推荐下看了下face_recognition这个项目,之前基本没用过python,于是有了漫长的踩坑之旅。
796 1

推荐镜像

更多