一個多智能體元編程框架，給定一行需求，它可以返回產(chǎn)品文檔、架構(gòu)設(shè)計、任務(wù)列表和代碼。這個項目提供了一種創(chuàng)新的方式來管理和執(zhí)行項目，將需求轉(zhuǎn)化為具體的文檔和任務(wù)列表，使項目管理變得高效而智能。對于需要進(jìn)行規(guī)劃和協(xié)調(diào)的項目，這個框架提供了強(qiáng)大的支持.
MetaGPT’s 能力展示
https://github.com/geekan/MetaGPT/assets/34952977/34345016-5d13-489d-b9f9-b82ace413419
例如，如果你輸入’ python startup.py ’ ’ Design a RecSys like今日頭條’ '，你會得到很多輸出，其中之一是data & api Design
生成一個分析和設(shè)計示例的成本約為0.2美元(在GPT-4 API費(fèi)用中)，而生成一個完整項目的成本約為2.0美元。
1.安裝
1.1 安裝視頻指南
- Matthew Berman: How To Install MetaGPT - Build A Startup With One Prompt!!
- 常規(guī)安裝
#Step 1: Ensure that NPM is installed on your system. Then install mermaid-js. (If you don't have npm in your computer, please go to the Node.js offical website to install Node.js https://nodejs.org/ and then you will have npm tool in your computer.)
npm --version
sudo npm install -g @mermaid-js/mermaid-cli
#Step 2: Ensure that Python 3.9+ is installed on your system. You can check this by using:
python --version
#Step 3: Clone the repository to your local machine, and install it.
git clone https://github.com/geekan/metagpt
cd metagpt
pip install -e.
Note:
-
If already have Chrome, Chromium, or MS Edge installed, you can skip downloading Chromium by setting the environment variable
PUPPETEER_SKIP_CHROMIUM_DOWNLOADtotrue. -
Some people are having issues installing this tool globally. Installing it locally is an alternative solution,
npm install @mermaid-js/mermaid-cli -
don’t forget to the configuration for mmdc in config.yml
PUPPETEER_CONFIG: "./config/puppeteer-config.json" MMDC: "./node_modules/.bin/mmdc" -
if
pip install -e.fails with error[Errno 13] Permission denied: '/usr/local/lib/python3.11/dist-packages/test-easy-install-13129.write-test', try instead runningpip install -e. --user -
將Mermaid圖表轉(zhuǎn)換為SVG、PNG和PDF格式。除了Node.js版本的mermaid - cli之外，你現(xiàn)在還可以選擇使用Python版本的劇作家、pyppeteer或mermaid。
-
Playwright
- Install Playwright
pip install playwright- Install the Required Browsers
to support PDF conversion, please install Chrominum.
playwright install --with-deps chromium- modify
config.yaml
uncomment MERMAID_ENGINE from config.yaml and change it to
playwrightMERMAID_ENGINE: playwright -
pyppeteer
- Install pyppeteer
pip install pyppeteer- Use your own Browsers
pyppeteer alow you use installed browsers, please set the following envirment
export PUPPETEER_EXECUTABLE_PATH = /path/to/your/chromium or edge or chromeplease do not use this command to install browser, it is too old
pyppeteer-install- modify
config.yaml
uncomment MERMAID_ENGINE from config.yaml and change it to
pyppeteerMERMAID_ENGINE: pyppeteer -
mermaid.ink
- modify
config.yaml
uncomment MERMAID_ENGINE from config.yaml and change it to
inkMERMAID_ENGINE: inkNote: this method does not support pdf export.
- modify
-
1.2 Docker安裝指南
#Step 1: Download metagpt official image and prepare config.yaml
docker pull metagpt/metagpt:latest
mkdir -p /opt/metagpt/{config,workspace}
docker run --rm metagpt/metagpt:latest cat /app/metagpt/config/config.yaml > /opt/metagpt/config/key.yaml
vim /opt/metagpt/config/key.yaml # Change the config
#Step 2: Run metagpt demo with container
docker run --rm \
--privileged \
-v /opt/metagpt/config/key.yaml:/app/metagpt/config/key.yaml \
-v /opt/metagpt/workspace:/app/metagpt/workspace \
metagpt/metagpt:latest \
python startup.py "Write a cli snake game"
#You can also start a container and execute commands in it
docker run --name metagpt -d \
--privileged \
-v /opt/metagpt/config/key.yaml:/app/metagpt/config/key.yaml \
-v /opt/metagpt/workspace:/app/metagpt/workspace \
metagpt/metagpt:latest
docker exec -it metagpt /bin/bash
$ python startup.py "Write a cli snake game"
The command docker run ... do the following things:
- Run in privileged mode to have permission to run the browser
- Map host directory
/opt/metagpt/configto container directory/app/metagpt/config - Map host directory
/opt/metagpt/workspaceto container directory/app/metagpt/workspace - Execute the demo command
python startup.py "Write a cli snake game"
1.3 構(gòu)造自定義
#You can also build metagpt image by yourself.
git clone https://github.com/geekan/MetaGPT.git
cd MetaGPT && docker build -t metagpt:custom .
1.4 相關(guān)配置
- Configure your
OPENAI_API_KEYin any ofconfig/key.yaml / config/config.yaml / env - Priority order:
config/key.yaml > config/config.yaml > env
#Copy the configuration file and make the necessary modifications.
cp config/config.yaml config/key.yaml
| Variable Name | config/key.yaml | env |
|---|---|---|
| OPENAI_API_KEY # Replace with your own key | OPENAI_API_KEY: “sk-…” | export OPENAI_API_KEY=“sk-…” |
| OPENAI_API_BASE # Optional | OPENAI_API_BASE: “https://<YOUR_SITE>/v1” | export OPENAI_API_BASE=“https://<YOUR_SITE>/v1” |
2.相關(guān)教程
#Run the script
python startup.py "Write a cli snake game"
#Do not hire an engineer to implement the project
python startup.py "Write a cli snake game" --implement False
#Hire an engineer and perform code reviews
python startup.py "Write a cli snake game" --code_review True
After running the script, you can find your new project in the workspace/ directory.
- Preference of Platform or Tool
You can tell which platform or tool you want to use when stating your requirements.
python startup.py "Write a cli snake game based on pygame"
- 使用指南
NAME
startup.py - We are a software startup comprised of AI. By investing in us, you are empowering a future filled with limitless possibilities.
SYNOPSIS
startup.py IDEA <flags>
DESCRIPTION
We are a software startup comprised of AI. By investing in us, you are empowering a future filled with limitless possibilities.
POSITIONAL ARGUMENTS
IDEA
Type: str
Your innovative idea, such as "Creating a snake game."
FLAGS
--investment=INVESTMENT
Type: float
Default: 3.0
As an investor, you have the opportunity to contribute a certain dollar amount to this AI company.
--n_round=N_ROUND
Type: int
Default: 5
NOTES
You can also use flags syntax for POSITIONAL ARGUMENTS
2.1 快速開始
It is difficult to install and configure the local environment for some users. The following tutorials will allow you to quickly experience the charm of MetaGPT.
- MetaGPT quickstart
Try it on Huggingface Space
- https://huggingface.co/spaces/deepwisdom/MetaGPT
- 相關(guān)鏈接
https://github.com/geekan/MetaGPT/assets/2707039/5e8c1062-8c35-440f-bb20-2b0320f8d27d
3.更多推薦：終端LLM AI模型:mlc-llm
大型語言模型的機(jī)器學(xué)習(xí)編譯(MLC LLM)是一種高性能的通用部署解決方案，允許使用帶有編譯器加速的本機(jī)api來本地部署任何大型語言模型。這個項目的使命是讓每個人都能使用ML編譯技術(shù)在每個人的設(shè)備上開發(fā)、優(yōu)化和部署人工智能模型。
項目鏈接：https://github.com/mlc-ai/mlc-llm
最后
為了幫助大家更好的學(xué)習(xí)人工智能，這里給大家準(zhǔn)備了一份人工智能入門/進(jìn)階學(xué)習(xí)資料，里面的內(nèi)容都是適合學(xué)習(xí)的筆記和資料，不懂編程也能聽懂、看懂，所有資料朋友們?nèi)绻行枰兹斯ぶ悄苋腴T+進(jìn)階學(xué)習(xí)資源包，可以在評論區(qū)或掃.碼領(lǐng)取哦）~
在線教程
- 麻省理工學(xué)院人工智能視頻教程 – 麻省理工人工智能課程
- 人工智能入門 – 人工智能基礎(chǔ)學(xué)習(xí)。Peter Norvig舉辦的課程
- EdX 人工智能 – 此課程講授人工智能計算機(jī)系統(tǒng)設(shè)計的基本概念和技術(shù)。
- 人工智能中的計劃 – 計劃是人工智能系統(tǒng)的基礎(chǔ)部分之一。在這個課程中，你將會學(xué)習(xí)到讓機(jī)器人執(zhí)行一系列動作所需要的基本算法。
- 機(jī)器人人工智能 – 這個課程將會教授你實現(xiàn)人工智能的基本方法，包括：概率推算，計劃和搜索，本地化，跟蹤和控制，全部都是圍繞有關(guān)機(jī)器人設(shè)計。
- 機(jī)器學(xué)習(xí) – 有指導(dǎo)和無指導(dǎo)情況下的基本機(jī)器學(xué)習(xí)算法
- 機(jī)器學(xué)習(xí)中的神經(jīng)網(wǎng)絡(luò) – 智能神經(jīng)網(wǎng)絡(luò)上的算法和實踐經(jīng)驗
- 斯坦福統(tǒng)計學(xué)習(xí)
??有需要的小伙伴，可以點擊下方鏈接免費(fèi)領(lǐng)取或者V掃描下方二維碼免費(fèi)領(lǐng)取??
?
人工智能書籍
- OpenCV（中文版）.(布拉德斯基等)
- OpenCV+3計算機(jī)視覺++Python語言實現(xiàn)+第二版
- OpenCV3編程入門 毛星云編著
- 數(shù)字圖像處理_第三版
- 人工智能:一種現(xiàn)代的方法
- 深度學(xué)習(xí)面試寶典
- 深度學(xué)習(xí)之PyTorch物體檢測實戰(zhàn)
- 吳恩達(dá)DeepLearning.ai中文版筆記
- 計算機(jī)視覺中的多視圖幾何
- PyTorch-官方推薦教程-英文版
- 《神經(jīng)網(wǎng)絡(luò)與深度學(xué)習(xí)》(邱錫鵬-20191121)
- …
??有需要的小伙伴，可以點擊下方鏈接免費(fèi)領(lǐng)取或者V掃描下方二維碼免費(fèi)領(lǐng)取??
?
第一階段：零基礎(chǔ)入門（3-6個月）
新手應(yīng)首先通過少而精的學(xué)習(xí)，看到全景圖，建立大局觀。 通過完成小實驗，建立信心，才能避免“從入門到放棄”的尷尬。因此，第一階段只推薦4本最必要的書（而且這些書到了第二、三階段也能繼續(xù)用），入門以后，在后續(xù)學(xué)習(xí)中再“哪里不會補(bǔ)哪里”即可。
第二階段：基礎(chǔ)進(jìn)階（3-6個月）
熟讀《機(jī)器學(xué)習(xí)算法的數(shù)學(xué)解析與Python實現(xiàn)》并動手實踐后，你已經(jīng)對機(jī)器學(xué)習(xí)有了基本的了解，不再是小白了。這時可以開始觸類旁通，學(xué)習(xí)熱門技術(shù)，加強(qiáng)實踐水平。在深入學(xué)習(xí)的同時，也可以探索自己感興趣的方向，為求職面試打好基礎(chǔ)。
第三階段：工作應(yīng)用
這一階段你已經(jīng)不再需要引導(dǎo)，只需要一些推薦書目。如果你從入門時就確認(rèn)了未來的工作方向，可以在第二階段就提前閱讀相關(guān)入門書籍（對應(yīng)“商業(yè)落地五大方向”中的前兩本），然后再“哪里不會補(bǔ)哪里”。
文章來源：http://www.zghlxwxcb.cn/news/detail-808800.html
??有需要的小伙伴，可以點擊下方鏈接免費(fèi)領(lǐng)取或者V掃描下方二維碼免費(fèi)領(lǐng)取??
?文章來源地址http://www.zghlxwxcb.cn/news/detail-808800.html
到了這里，關(guān)于MetaGPT( The Multi-Agent Framework)：顛覆AI開發(fā)的革命性多智能體元編程框架的文章就介紹完了。如果您還想了解更多內(nèi)容，請在右上角搜索TOY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！
