Coder Social home page Coder Social logo

connectai-e / autogpt-next-web Goto Github PK

View Code? Open in Web Editor NEW
2.8K 35.0 1.4K 20 MB

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.一键免费部署你的私人AutoGPT 网页应用

Home Page: https://auto-agentgpt.com

License: GNU General Public License v3.0

Shell 4.53% Dockerfile 3.31% TypeScript 89.56% JavaScript 1.51% CSS 1.09%
auto-gpt openai llm nextjs react vercel langchangjs docker docker-compose connect-ai

autogpt-next-web's People

Contributors

afcppe avatar ddmeaqua avatar dependabot[bot] avatar dogtiti avatar eltociear avatar hhz-saner avatar kaichii avatar kalinote avatar leizhenpeng avatar liuelric avatar lloydzhou avatar louyongjiu avatar natecc0902 avatar wddxg avatar yaway avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

autogpt-next-web's Issues

[FEAT]增加docker镜像支持

能否加一个actions的build_docker文件,可以自动编译git项目push到dockerhub。
这样做的好处是更新项目方便。我自己尝试,会报如下错误:

[linux/amd64 6/6] RUN npm run build
#16 0.925 
#16 0.925 > [email protected] build
#16 0.925 > next build --no-lint
#16 0.925 
#16 1.480 warn  - Linting is disabled
#16 1.915 ❌ Invalid environment variables:
#16 1.915  OPENAI_API_KEY: Required
#16 1.915 
#16 1.918 error - Failed to load next.config.mjs, see more info here https://nextjs.org/docs/messages/next-config-error
#16 1.926 
#16 1.926 > Build error occurred
#16 1.929 Error: Invalid environment variables
#16 1.929     at file:///app/src/env/server.mjs:16:9
#16 1.929     at ModuleJob.run (node:internal/modules/esm/module_job:193:25)
#16 ERROR: process "/bin/sh -c npm run build" did not complete successfully: exit code: 1
#13 [linux/arm64 4/6] RUN npm ci
#13 CANCELED
------
 > [linux/amd64 6/6] RUN npm run build:
#16 1.480 warn  - Linting is disabled
#16 1.915 ❌ Invalid environment variables:
#16 1.915  OPENAI_API_KEY: Required
#16 1.915 
#16 1.918 error - Failed to load next.config.mjs, see more info here https://nextjs.org/docs/messages/next-config-error
#16 1.926 
#16 1.926 > Build error occurred
#16 1.929 Error: Invalid environment variables
#16 1.929     at file:///app/src/env/server.mjs:16:9
#16 1.929     at ModuleJob.run (node:internal/modules/esm/module_job:193:25)
------
Dockerfile:21
--------------------
  19 |     
  20 |     # Build the Next.js app
  21 | >>> RUN npm run build
  22 |     
  23 |     # Expose the port the app will run on
--------------------
ERROR: failed to solve: process "/bin/sh -c npm run build" did not complete successfully: exit code: 1
Error: buildx failed with: ERROR: failed to solve: process "/bin/sh -c npm run build" did not complete successfully: exit code: 1

使用的build_docker.yml文件内容如下:

name: build_docker

on:
  push:
    branches: [main]
  release:
    types: [created] # 表示在创建新的 Release 时触发

jobs:
  build_docker:
    name: Build docker
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v3

      - run: |
          echo "本次构建的版本为:${GITHUB_REF_NAME} (但是这个变量目前上下文中无法获取到)"
          echo 本次构建的版本为:${{ github.ref_name }}
          env
      - name: Set up QEMU
        uses: docker/setup-qemu-action@v2
      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v2
      - name: Login to DockerHub
        uses: docker/login-action@v2
        with:
          username: ${{ secrets.DOCKERHUB_USERNAME }}
          password: ${{ secrets.DOCKERHUB_TOKEN }}
      - name: Build and push
        id: docker_build
        uses: docker/build-push-action@v4
        with:
          context: .
          push: true
          labels: ${{ steps.meta.outputs.labels }}
          platforms: linux/amd64,linux/arm64
          tags: |
            ${{ secrets.DOCKERHUB_USERNAME }}/agent-gpt:${{ github.ref_name }}
            ${{ secrets.DOCKERHUB_USERNAME }}/agent-gpt:latest

应该是dockerfile或者哪里,强制读取环境变量的原因吧。

[BUG] 样式错误

Describe the bug / 描述bug
任务到一定层级右侧列表出现样式错误

To Reproduce / 复现方式
image

建议可以最大化界面

因为电脑是高清屏,对话框边上还有不少有空间,建议把对话框可以最大化,方便查看思考的对话框及当前任务的更多的内容
image

[FEAT] 集成登录功能

⚠️ Please check that this feature request hasn't been suggested before.请检查之前是否没有建议过此功能请求。

  • I searched previous Ideas in issue didn't find any similar feature requests.我搜索了之前的 Ideas in issue 没有找到任何类似的功能请求。

🔖 Feature description 功能说明

  • 新增登录相关教程,包括数据库和变量配置说明
  • 调整auth providers

✔️ Solution 解决方案

  • 在本地运行脚本生成必须的环境变量参数
  • 通过vercel面板设置

❓ Alternatives 备选方案

一键部署的可能性研究,通过vercel实现所有过程,免去本地操作

📝 Additional Context 附加上下文

No response

Acknowledgements 致谢

  • My issue title is concise, descriptive, and in title casing.我的问题标题简明扼要,具有描述性,并且使用标题框。
  • I have searched the existing issues to make sure this feature has not been requested yet.我已经搜索了现有问题以确保尚未请求此功能。
  • I have provided enough information for the maintainers to understand and evaluate this request.我已经为维护者提供了足够的信息来理解和评估这个请求。

OPENAI_API_BASE支持

发现gpt类相关的开源工具基本上都没有第一时间支持OPENAI_API_BASE这个配置,但在国内这个基本上是刚需

可否支持Azure Openai API?

AutoGPT本身是支持azure openai的,如下图:
CleanShot 2023-04-21 at 19 52 43@2x
但是目前本项目仅支持配置openai 的apikey,无法使用azure openai。或者能够添加配置修改openai的endpoint也可以,因为已有项目可以做azure [openai到官方openai的proxy azure-openai-proxy

本地部署docker容器运行时使用本地代理,无法进入http://0.0.0.0:3000/

为了使用本地代理,尝试了以下修改:

ENV="NODE_ENV=development\n\
NEXTAUTH_SECRET=$NEXTAUTH_SECRET\n\
NEXTAUTH_URL=http://localhost:3000\n\
OPENAI_API_KEY=$OPENAI_API_KEY\n\
DATABASE_URL=file:../db/db.sqlite\n\
HTTP_PROXY=http://127.0.0.1:8887\n\
HTTPS_PROXY=http://127.0.0.1:8887\n"

printf $ENV > .env

if [ "$1" = "--docker" ]; then
  printf $ENV > .env.docker
  source .env.docker
  docker build --build-arg NODE_ENV=$NODE_ENV -t agentgpt .
  #docker run -d --name agentgpt -p 3000:3000 -v $(pwd)/db:/app/db agentgpt
  docker run -d --name agentgpt -v $(pwd)/db:/app/db agentgpt --network host
else
  printf $ENV > .env
  ./prisma/useSqlite.sh
  npm install
  npm run dev
fi

但是http://0.0.0.0:3000/ http error 503,npm需要配置代理?如何使得autogpt next web使用本地代理服务器?

[BUG] Looping creates repeating steps and answers

Describe the bug
Looping set to max creates repeating steps and answers which make no sense

To Reproduce

  1. Set looping to 100
  2. Start new agent

Expected behavior
It should not show always show the same steps and answers. I want that it acts like an AutoGPT bot not like a repeating machine.

Device information

  • Device: Xiaomi Mi 9T Pro
  • Browser: Kiwi Beta

[BUG] 问答无法中文化的问题

我通过./setup.sh --docker的方式在自己的服务器上部署了AutoGPT-Next-Web,服务运行正常,但是在使用中文提问的时候回答依然是英文,测试过程截图:
QQ图片20230504095525

[BUG]在输入名称/目标的时候 回车键 会错误触发“停止代理程序”

Describe the bug / 描述bug
在输入名称的时候 会错误触发“停止代理程序”

名称和目标的输入框中,在输入法中敲击回车的时候 会直接触发“停止代理程序” 但是本意只是想直接输入某个英文字符。

To Reproduce / 复现方式
首页 在名称/目标输入框中,简单输入“成为AI工程师”,其中“AI”使用中文输入法输入,并且通过回车键直接录入

Expected behavior / 期望的行为
焦点在输入框的时候 回车不会触发按钮
Screenshots / 截屏

Device information / 设备信息
M1 芯片 macbook pro 13寸

  • Device: [e.g. iPhone6]
    设备,比如:iphone6
  • OS: [e.g. iOS8.1]
    macos 12 5 1
  • Browser [e.g. safari]
    chrome
  • Version [e.g. 22]
    最新

按下enter可以做成換行嗎

如題
每次輸入 打完注音 按下enter 會變成直接執行 而不是完成輸入

如果覺得可以改成換行的話 可以assigne 給我

1.0.4版本长时间处于"运行中"状态[BUG]

1
部署环境:
自有CentOS 7独立服务器

部署方式:
./setup.sh --docker

部署完成后访问:3000可以正常打开,但是进行任何提问都会卡住,一直处于"运行中"状态。
降级为1.0.3,使用同样的操作方式则是正常的,但是1.0.3存在回答无法汉化的问题

能否添加一个zeabur的部署方案。

目前安装AutoGPT-Next-Web安装教程点击deploy可以安装,手动去vercel官网部署就不能正常安装,收到安装zeabur也不行,希望出一个方案,隔壁chatGPT-next-web以皆可以正常安装。辛苦大佬。

汇总结果

描述 / Description

  1. 如果遇到复杂的任务,子任务会被递归拆分成更细的子任务。
  2. 然后结果会散落在很长的消息列表里面。这个时候需要慢慢的找到消息,手动合并,挺麻烦的

期望的结果 / Expected Result

希望能在任务完成的时候给出一个按照任务层级归纳查看结果的地方

可行性 / Feasibility

  1. 更改AutonomousAgent队列,使用一个树形结构来做队列
  2. 每次的loop循环总是(广度)递归遍历数结构找到需要被执行的任务
  3. 每执行完一个任务,更新任务状态,记录任务结果。开启下一次loop循环
  4. 执行完成的时候增加一条合并结果后的消息?

关于Docker部署

Docker部署有问题的统一在这里回复
带上详细信息,检查环境变量是否正确传入

[BUG] 设置页面输入API key反而不能用

Describe the bug / 描述bug

设置页面不输入密钥还能使用,输入密钥提示

访问OpenAI API出错。请检查您的API密钥或稍后重试

To Reproduce / 复现方式

使用vercel部署,全程跟着教程

Expected behavior / 期望的行为

期望填api key也能用

Screenshots / 截屏

image

这里的密钥我也填了
image

Device information / 设备信息

使用的最新版本

baada12

image

image

请问能不能开放调整高级设置

现在既然已经有NEXT_PUBLIC_GUEST_KEY可以控制访问了,能否在填写NEXT_PUBLIC_GUEST_KEY正确之后就可以更改高级设置,总是有那样的限制用的不够开心。

[BUG]docker-compose启动错误

Describe the bug / 描述bug

使用./setup.sh --docker-compose命令启动容器时报如下错误:
Error response from daemon: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error mounting "/root/AutoGPT-Next-Web/.env.docker" to rootfs at "/app/.env": mount /root/AutoGPT-Next-Web/.env.docker:/app/.env (via /proc/self/fd/6), flags: 0x5000: not a directory: unknown: Are you trying to mount a directory onto a file (or vice-versa)? Check if the specified host path exists and is the expected type

并且在项目目录下生成了一个.env.docker文件夹

To Reproduce / 复现方式

clone项目后执行./setup.sh --docker-compose命令

手动在setup.sh中添加了printf "$ENV" > .env.docker后解决

elif [ "$1" = "--docker-compose" ]; then
  # printf "$ENV" > .env.docker
  docker-compose up -d --remove-orphans

Cant trust this

I asked to create a scrape of google for information and it made up nearly 95% of sources. Cann;t be trusted for accuracy of finds, also makes up statistics and references. Found it to easily fall off at 50 loops. I asked it to produce documents of all info found, it didn't

Over all, nice interface but doesn't work well in the auto sense.

[FEAT] sync script

描述 / Description

定时任务

期望的结果 / Expected Result

定时的去通过github actions执行同步任务

I don't see any difference

请在这里描述您的意见、建议、吐槽、鼓励或其他任何想法。我们非常重视您的反馈和意见,感谢您的支持和贡献!
Please describe your opinion, suggestion, complaint, encouragement or any other idea here. We value your feedback and opinions, and appreciate your support and contributions!

期望的结果/Expected result

请在这里描述您期望看到的结果或变化。
Please describe the results or changes you would like to see here.

声明/statement

请注意,您的问题可能会被公开回复,因此请勿包含任何敏感信息。
Note that your question may be answered publicly, so please do not include any sensitive information.

[FEAT] version notification

描述 / Description

版本通知

期望的结果 / Expected Result

当上游更新时,能通知下游更新版本

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.