Laoda | 咕咕修改

十分钟搭建一个「万物皆可存」的智能书签应用——karakeep｜好玩儿的 Docker 项目

2025-11-13 09:55:12

1. 唠嗑

好久没更新了，这周来和大家分享一个好用的书签工具——Karakeep

2. karakeep 简介

Karakeep（前身为 Hoarder）是一款可自托管的「万物皆可存」书签应用，专为数据囤积爱好者打造，融入一丝 AI 魔法。

功能

• 🔗 书签链接、记录简单笔记，并存储图片和 PDF 文件。
• ⬇️ 自动抓取链接标题、描述和预览图。
• 📋 将书签整理到不同列表中。
• 🔎 全文本搜索所有存储内容。
• ✨ 基于 AI（类似 ChatGPT）自动打标签和生成摘要。支持使用 Ollama 运行本地模型！
• 🤖 规则引擎，实现自定义管理。
• 🎆 图像 OCR，提取图片中的文字。
• 🔖 Chrome 插件和 Firefox 扩展，快速添加书签。
• 📱 iOS 应用和 Android 应用。
• 📰 从 RSS 订阅源自动归档内容。
• 🔌 REST API 和多种客户端。
• 🌐 多语言支持。
• 🖍️ 标记并保存归档内容中的高亮片段。
• 🗄️ 完整页面归档（使用 monolith），防止链接失效。
• ▶️ 使用 yt-dlp 自动归档视频。
• ☑️ 支持批量操作。
• 🔐 支持 SSO 单点登录。
• 🌙 深色模式。
• 💾 优先支持自托管。
• ⬇️ 从 Chrome、Pocket、Linkwarden、Omnivore、Tab Session Manager 导入书签。
• 🔄 通过 floccus 与浏览器书签自动同步。
• [计划中] 移动端离线阅读、书签语义搜索，……

3. 相关地址

官方 GitHub 地址：https://github.com/karakeep-app/karakeep （目前 21.1k 个 star，欢迎大家去给项目点星星！）

Demo 地址：https://try.karakeep.app

默认账号密码：

Email: [email protected]

Password: demodemo

当然如果你体验完还想自己用 docker 搭建一个，那我们就继续往下！

4. 搭建环境

• 服务器：咕咕这边用的香港的 莱卡云服务器，建议服务器内存 1G 以上，当然你也可以选择其他 高性价比的服务器。
• 系统：Debian 11 （DD 脚本 非必需 DD，用原来的系统也 OK，之后教程都是用 Debian 或者 Ubuntu 搭建～）
• 安装好 Docker、Docker-compose（相关脚本）
• 【必需】域名一枚，并做好解析到服务器上（域名购买、域名解析 视频教程）
• 【非必需】提前安装好宝塔面板海外版本 aapanel，并安装好 Nginx（安装地址）
• 【非必需本教程选用】安装好 Nginx Proxy Manager（相关教程）

5. 搭建视频（过俩周补充 = =）

5.1 YouTube

视频地址：

5.2 哔哩哔哩

哔哩哔哩：

6. 搭建方式

6.1 安装 Docker 与 Nginx Proxy Manager

可以直接参考这篇内容：

https://blog.laoda.de/archives/nginxproxymanager/

6.2 创建安装目录

创建一下安装的目录：

sudo -i

mkdir -p /root/data/docker_data/karakeep

cd /root/data/docker_data/karakeep

接着我们来编辑下docker-compose.yml

vim docker-compose.yml

services:
  web:
    image: ghcr.io/karakeep-app/karakeep:latest
    restart: unless-stopped
    volumes:
      # By default, the data is stored in a docker volume called "data".
      # If you want to mount a custom directory, change the volume mapping to:
      # - /path/to/your/directory:/data
      - ./data:/data
    ports:
      - 3030:3000
    env_file:
      - .env
    environment:
      MEILI_ADDR: http://meilisearch:7700
      BROWSER_WEB_URL: http://chrome:9222
      # OPENAI_API_KEY: ...

      # You almost never want to change the value of the DATA_DIR variable.
      # If you want to mount a custom directory, change the volume mapping above instead.
      DATA_DIR: /data # DON'T CHANGE THIS
  chrome:
    image: gcr.io/zenika-hub/alpine-chrome:124
    restart: unless-stopped
    command:
      - --no-sandbox
      - --disable-gpu
      - --disable-dev-shm-usage
      - --remote-debugging-address=0.0.0.0
      - --remote-debugging-port=9222
      - --hide-scrollbars
  meilisearch:
    image: getmeili/meilisearch:v1.13.3
    restart: unless-stopped
    env_file:
      - .env
    environment:
      MEILI_NO_ANALYTICS: "true"
    volumes:
      - ./meilisearch:/meili_data

其中的左边的3030可以改成服务器上没有用过的端口，如果要用到AI功能的话，可以取消OPENAI_API_KEY的注释，填入自己的密钥。

修改完成之后，可以在英文输入法下，按 i 修改，完成之后，按一下 esc，然后 :wq 保存退出。

接着我们来编辑下.env

cd /root/data/docker_data/karakeep
vim .env

粘贴如下内容：

KARAKEEP_VERSION=release
NEXTAUTH_SECRET=super_random_string
MEILI_MASTER_KEY=another_random_string
NEXTAUTH_URL=http://localhost:3000

• 其中的http://localhost:3000这个改成你自己之后用域名访问的地址，比如我的https://karakeep.gugu.ovh
• 其中的super_random_string和another_random_string需要我们自己生成。

我们可以先在命令行里面输入

openssl rand -base64 36

生成随机的字符，然后替代它们。

我需要放在.env里的内容就是：

KARAKEEP_VERSION=release
NEXTAUTH_SECRET=Lu4YuG5pXji2/QB6blXaoWnfK2WdtKifPhEBt0UQCHqkxCAe
MEILI_MASTER_KEY=wJ222cTFWJ0/9Jnu38gU9Wb+AdCk2SBmQ687MdTbxT8c/V0b
NEXTAUTH_URL=https://karakeep.gugu.ovh

修改完成之后，同样的，可以在英文输入法下，按 i 修改，完成之后，按一下 esc，然后 :wq 保存退出。

6.3 查看端口是否被占用

查看端口是否被占用（以 3030 为例），输入：

lsof -i:3030  #查看 3030 端口是否被占用，如果被占用，重新自定义一个端口

如果啥也没出现，表示端口未被占用，我们可以继续下面的操作了～

如果出现：

-bash: lsof: command not found

运行：

apt install lsof  #安装 lsof

如果端口没有被占用（被占用了就修改一下端口，比如改成 8381，注意 docker 命令行里和防火墙都要改）

6.4 启动 karakeep

cd /root/data/docker_data/karakeep

docker compose up -d   # 注意，老版本用户用 docker-compose up -d

耐心等待拉取好镜像，出现 done的字样之后，

理论上我们就可以输入 http://ip:3030 访问了。

但是这边这个服务必须先搞一下反向代理！既然是加密的项目，不能用 http 使用明文传输，我们部署在公网一定要考虑使用反向代理工具配置 SSL！

做反向代理前，你需要一个域名！

namesilo 上面 xyz 后缀的域名一年就 7 块钱，可以年抛。（冷知识，namesilo 上 6 位数字的 xyz 续费永远都是 0.99 美元 = =）

如果想要长期使用，还是建议买 com 后缀的域名，更加正规一些，可以输入 laodade 来获得 1 美元的优惠（不知道现在还有没有）

namesilo 自带隐私保护，咕咕一直在用这家，价格也是这些注册商里面比较低的，关键是他家不像其他家域名注册商，没有七七八八的套路！（就是后台界面有些 丑 古老 = =）

【域名购买】Namesilo 优惠码和域名解析教程（附带服务器购买推荐和注意事项）

我们接着往下看！

7. 反向代理

7.1 利用 Nginx Proxy Manager

在添加反向代理之前，确保你已经完成了域名解析，不会的可以看这个：域名一枚，并做好解析到服务器上（域名购买、域名解析 视频教程） （名称改成你自己想要的域名前缀即可）

之后，登陆 Nginx Proxy Manager（不会的看这个：安装 Nginx Proxy Manager（相关教程））

注意：

Nginx Proxy Manager（以下简称 NPM）会用到 80、443 端口，所以本机不能占用（比如原来就有 Nginx）

直接丢几张图：

注意填写对应的 域名、IP 和 端口，按文章来的话，应该是 3030

IP 填写：

如果 Nginx Proxy Manager 和 karakeep 在同一台服务器上，可以在终端输入：

ip addr show docker0

查看对应的 Docker 容器内部 IP。

否则直接填 karakeep 所在的服务器 IP 就行。

然后访问域名就可以访问了！

7.2 利用宝塔面板

发现还是有不少小伙伴习惯用宝塔面板，这边也贴一个宝塔面板的反代配置：

直接新建一个站点，不要数据库，不要 php，纯静态即可。

然后打开下面的配置，修改 Nginx 的配置。

代码如下：

location / {
      proxy_pass http://127.0.0.1:3030/;       # 注意改成你实际使用的端口
      rewrite ^/(.*)$ /$1 break;
      proxy_redirect off;
      proxy_set_header Host $host;
      proxy_set_header X-Forwarded-Proto $scheme;
      proxy_set_header X-Real-IP $remote_addr;
      proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
      proxy_set_header Upgrade-Insecure-Requests 1;
      proxy_set_header X-Forwarded-Proto https;
    }

此方法对 90% 的反向代理都能生效，然后就可以用域名来安装访问了。

有同学可能会问，为什么不直接用宝塔自带的反向代理功能。

也可以，不过咕咕自己之前遇到过当有多个网站需要反代的时候，在这边设置会报错的情况 = =

所以后来就不用了，直接用上面的方法来操作了。

8. 使用教程

非常简单，所见即所得。

登录，

首先注册一个账号，

后台页面，

用户设置，

如果觉得英文不习惯，也可以改成中文，

输入一个网址，测试一下，

支持给你存下来的网页打标签，

服务器统计情况，

Karakeep是支持浏览器插件的，这边可以直接下载浏览器插件，方便浏览网页的时候使用，

输入你搭建好的域名，然后登录即可，

使用

也支持下载完整页面，

还有一些AI功能，大家可以自行探索。或者查看Karakeep的官方文档

8.1 更新 karakeep

这个项目后续会持续有更新，所以提供一个更新的方式。

cd /root/data/docker_data/karakeep

docker compose pull

docker compose up -d    # 请不要使用 docker compose stop 来停止容器，因为这么做需要额外的时间等待容器停止；docker compose up -d 直接升级容器时会自动停止并立刻重建新的容器，完全没有必要浪费那些时间。

docker image prune  # prune 命令用来删除不再使用的 docker 对象。删除所有未被 tag 标记和未被容器使用的镜像

提示：

WARNING! This will remove all dangling images.
Are you sure you want to continue? [y/N]

输入 y

利用 Docker 搭建的应用，更新非常容易～

8.2 卸载 karakeep

同样进入安装页面，先停止所有容器。

cd /root/data/docker_data/karakeep

docker compose down

cd ..

rm -rf /root/data/docker_data/karakeep  # 完全删除

可以卸载得很干净。

9. 使用简介

大家有问题欢迎评论区交流。

10. 结尾

祝大家用得开心，有问题可以去 GitHub 提 Issues，也可以在评论区互相交流探讨。

同时，有能力给项目做贡献的同学，也欢迎积极加入到 项目 中来，贡献自己的一份力量！

最后，感谢作者 @civilblur 的辛苦付出，让我们能用到这么优秀的项目！欢迎大家都去给这个项目点个 star。

参考资料

官方 GitHub：https://github.com/karakeep-app/karakeep

十分钟搭建一次性私密信息共享平台——OTS｜好玩儿的Docker项目

2025-10-22 11:04:21

1. 唠嗑

好久没更新了，这周来和大家分享一个阅后即焚工具，安全高效的一次性私密信息共享平台——OTS（One-Time-Secret）

2. OTS 简介

OTS 是一个一次性私密信息分享平台。私密信息在发送到服务器之前，会在浏览器中使用对称的 256 位 AES 加密进行加密。之后会生成一个包含私密信息的 ID 和密码的 URL。密码永远不会发送到服务器，因此服务器无法以合理的方式解密它所传递的私密信息。此外，私密信息在第一次读取后会立即被删除。

功能

• 私密信息在浏览器中通过 AES 256 位加密进行加密
• 服务器永远不会接收到明文私密信息
• 私密信息在第一次读取后即被删除

3. 相关地址

官方 GitHub 地址：https://github.com/Luzifer/ots （目前 638 个 star，欢迎大家去给项目点星星！）

Demo 地址：https://ots.fyi/

当然如果你看到这边还想自己用 docker 搭建一个，那我们就继续往下！

4. 搭建环境

• 服务器：咕咕这边用的香港的 莱卡云服务器，建议服务器内存 1G 以上，当然你也可以选择其他 高性价比的服务器。
• 系统：Debian 11 （DD 脚本 非必需 DD，用原来的系统也 OK，之后教程都是用 Debian 或者 Ubuntu 搭建～）
• 安装好 Docker、Docker-compose（相关脚本）
• 【必需】域名一枚，并做好解析到服务器上（域名购买、域名解析 视频教程）
• 【非必需】提前安装好宝塔面板海外版本 aapanel，并安装好 Nginx（安装地址）
• 【非必需本教程选用】安装好 Nginx Proxy Manager（相关教程）

5. 搭建视频（过俩天补充 = =）

5.1 YouTube

视频地址：

5.2 哔哩哔哩

哔哩哔哩：

6. 搭建方式

6.1 安装 Docker 与 Nginx Proxy Manager

可以直接参考这篇内容：

https://blog.laoda.de/archives/nginxproxymanager/

6.2 创建安装目录

创建一下安装的目录：

sudo -i

mkdir -p /root/data/docker_data/OTS

cd /root/data/docker_data/OTS

接着我们来编辑下docker-compose.yml

vim docker-compose.yml

services:
  app:
    image: ghcr.io/luzifer/ots:latest
    container_name: ots-app
    restart: always
    ports:
      - 3003:3000
    environment:
      # Optional, see "Customization" in README
      #CUSTOMIZE: '/etc/ots/customize.yaml'
      # See README for details
      REDIS_URL: redis://redis:6379/0
      # 168h = 1w
      SECRET_EXPIRY: "604800"
      # "mem" or "redis" (See README)
      STORAGE_TYPE: redis
    depends_on:
      - redis

  redis:
    image: redis:latest
    container_name: ots-redis
    restart: always
    volumes:
      - ./data:/data

环境变量的说明如下：

环境变量	描述
REDIS_URL	Redis 数据库的连接字符串，格式为 redis：//USR：PWD@HOST：PORT/DB。用于指定 OTS 应用连接的 Redis 实例
SECRET_EXPIRY	秘密的过期时间，单位为秒（默认 0 = 无过期）。此示例中设置为 604800（168 小时 = 1 周）
STORAGE_TYPE	用于指定存储类型，可以是 mem（内存存储）或 redis（使用 Redis 存储秘密）

最后，在 ots 目录下执行以下命令一键启动：

其中的左边的3003可以改成服务器上没有用过的端口，记得修改自己的用户名和密码，修改完成之后，可以在英文输入法下，按 i 修改，完成之后，按一下 esc，然后 :wq 保存退出。

6.3 查看端口是否被占用

查看端口是否被占用（以 3003 为例），输入：

lsof -i:3003  #查看 3003 端口是否被占用，如果被占用，重新自定义一个端口

如果啥也没出现，表示端口未被占用，我们可以继续下面的操作了～

如果出现：

-bash: lsof: command not found

运行：

apt install lsof  #安装 lsof

如果端口没有被占用（被占用了就修改一下端口，比如改成 8381，注意 docker 命令行里和防火墙都要改）

6.4 启动 OTS

cd /root/data/docker_data/OTS

docker compose up -d   # 注意，老版本用户用 docker-compose up -d

耐心等待拉取好镜像，出现 done的字样之后，

理论上我们就可以输入 http://ip:3003 访问了。

但是这边这个服务必须先搞一下反向代理！既然是加密的项目，不能用 http 使用明文传输，我们部署在公网一定要考虑使用反向代理工具配置 SSL！

做反向代理前，你需要一个域名！

namesilo 上面 xyz 后缀的域名一年就 7 块钱，可以年抛。（冷知识，namesilo 上 6 位数字的 xyz 续费永远都是 0.99 美元 = =）

如果想要长期使用，还是建议买 com 后缀的域名，更加正规一些，可以输入 laodade 来获得 1 美元的优惠（不知道现在还有没有）

namesilo 自带隐私保护，咕咕一直在用这家，价格也是这些注册商里面比较低的，关键是他家不像其他家域名注册商，没有七七八八的套路！（就是后台界面有些 丑 古老 = =）

【域名购买】Namesilo 优惠码和域名解析教程（附带服务器购买推荐和注意事项）

我们接着往下看！

7. 反向代理

7.1 利用 Nginx Proxy Manager

在添加反向代理之前，确保你已经完成了域名解析，不会的可以看这个：域名一枚，并做好解析到服务器上（域名购买、域名解析 视频教程） （名称改成你自己想要的域名前缀即可）

之后，登陆 Nginx Proxy Manager（不会的看这个：安装 Nginx Proxy Manager（相关教程））

注意：

Nginx Proxy Manager（以下简称 NPM）会用到 80、443 端口，所以本机不能占用（比如原来就有 Nginx）

直接丢几张图：

注意填写对应的 域名、IP 和 端口，按文章来的话，应该是 3003

IP 填写：

如果 Nginx Proxy Manager 和 OTS 在同一台服务器上，可以在终端输入：

ip addr show docker0

查看对应的 Docker 容器内部 IP。

否则直接填 OTS 所在的服务器 IP 就行。

然后访问域名就可以访问了！

7.2 利用宝塔面板

发现还是有不少小伙伴习惯用宝塔面板，这边也贴一个宝塔面板的反代配置：

直接新建一个站点，不要数据库，不要 php，纯静态即可。

然后打开下面的配置，修改 Nginx 的配置。

代码如下：

location / {
      proxy_pass http://127.0.0.1:3003/;       # 注意改成你实际使用的端口
      rewrite ^/(.*)$ /$1 break;
      proxy_redirect off;
      proxy_set_header Host $host;
      proxy_set_header X-Forwarded-Proto $scheme;
      proxy_set_header X-Real-IP $remote_addr;
      proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
      proxy_set_header Upgrade-Insecure-Requests 1;
      proxy_set_header X-Forwarded-Proto https;
    }

此方法对 90% 的反向代理都能生效，然后就可以用域名来安装访问了。

有同学可能会问，为什么不直接用宝塔自带的反向代理功能。

也可以，不过咕咕自己之前遇到过当有多个网站需要反代的时候，在这边设置会报错的情况 = =

所以后来就不用了，直接用上面的方法来操作了。

8. 使用教程

非常简单，所见即所得。

8.1 更新 OTS

这个项目后续会持续有更新，所以提供一个更新的方式。

cd /root/data/docker_data/OTS

docker compose pull

docker compose up -d    # 请不要使用 docker compose stop 来停止容器，因为这么做需要额外的时间等待容器停止；docker compose up -d 直接升级容器时会自动停止并立刻重建新的容器，完全没有必要浪费那些时间。

docker image prune  # prune 命令用来删除不再使用的 docker 对象。删除所有未被 tag 标记和未被容器使用的镜像

提示：

WARNING! This will remove all dangling images.
Are you sure you want to continue? [y/N]

输入 y

利用 Docker 搭建的应用，更新非常容易～

8.2 卸载 OTS

同样进入安装页面，先停止所有容器。

cd /root/data/docker_data/OTS

docker compose down

cd ..

rm -rf /root/data/docker_data/OTS  # 完全删除

可以卸载得很干净。

9. 常见问题及注意点

大家有问题欢迎评论区交流。

10. 结尾

祝大家用得开心，有问题可以去 GitHub 提 Issues，也可以在评论区互相交流探讨。

同时，有能力给项目做贡献的同学，也欢迎积极加入到 项目 中来，贡献自己的一份力量！

最后，感谢作者 @civilblur 的辛苦付出，让我们能用到这么优秀的项目！欢迎大家都去给这个项目点个 star。

参考资料

官方 GitHub：https://github.com/Luzifer/ots

3分钟利用 Paypal 领取免费一年 Perplexity 会员！ 解锁AI搜索神器！网页点点就行！

2025-09-04 18:31:06

简介

Perplexity是什么？

Perplexity 是一个结合了 AI 聊天机器人和搜索引擎功能的工具，旨在快速提供准确、简洁的答案，并附上可靠的来源引用。它通过理解用户问题，从网络上实时抓取信息，整理成清晰的回答，特别适合需要快速查资料或做研究的用户。

Pro版本的功能：

Perplexity Pro 提供更高级的功能，收费20美元/月，功能包括：

• 多模型选择：用户可切换使用 GPT-4o、Claude 3.7、Gemini Flash 等不同语言模型，灵活应对不同需求。
• Pages报告生成：可根据用户需求生成定制化的精美简报，适合研究或商务用途。
• 高级搜索功能：如学术论文模式，专注搜索学术资源（如 Arxiv、SemanticScholar），提升研究效率。
• 更高使用额度：相比免费版，Pro 版支持更多查询次数和更复杂的任务。

如果你需要快速查资料、做研究或验证信息，Perplexity 是最佳选择，尤其适合学术和专业场景。

领取条件

• 1个PayPal账号（我用的是美区，据网友测试国区也可以）
• 能访问真正的互联网
• Perplexity 账号（可以现场注册）

领取方式

领取地址：https://www.perplexity.ai/join/p/paypal-subscription

链接PayPal，

我这边登录的是美区的PayPal，

选择接受优惠，

成功领取！

已经可以正常使用了！

如果担心被反薅，记得取消 Perplexity 自动续费订阅，

访问：https://www.perplexity.ai/account/details

取消订阅即可，不影响使用

同样的，Perplexity 还支持Mac桌面端，也可以用起来了！

注意点

• 这次似乎国区的PayPal也可以领取。
• 有不少网友评价Perplexity玩不起，之前三星的泄漏的一年优惠码，没用几天被收回了。
• 也有网友表示现在这次打开会提示开通过了。 You are already subscribed or have previously subscribed to Perplexity Pro.
• 还有一些一注册上就风控，即使美区也是，原先注册好的死活都不让领说领过了，换无数个邮箱尝试依旧如此，这个时候可以考虑换一个干净的IP再试试。

给你的Docker应用加一层保险！10分钟搭建一个简单好用的认证中间件—— Tinyauth

2025-09-03 16:30:34

1. 唠嗑

这两三年来，我们搭建了不少好玩的Docker应用，其实一直陆陆续续有小伙伴在视频评论区和博客的评论区询问，怎么样才能让我的Docker应用更安全一点？

这一期，我们就来介绍这样一个工具，用最简单的方式来给我们的Docker应用加一层保险！

效果展示：

保存之后。

再次打开简历这个网页。

提示需要登录了。

输入账号密码，继续

进来了。

2. Tinyauth简介

Tinyauth 是个简单好用的认证中间件，能给你的 Docker 应用加个简洁的登录页面，或者支持 Google、GitHub 以及其他平台的 OAuth 认证。它跟主流代理比如 Nginx Proxy Manager、Traefik、Nginx 和 Caddy 都能无缝配合。

3. 相关地址

官方GitHub地址：https://github.com/steveiliop56/tinyauth (目前5.3K个star，欢迎大家去给项目点星星！）

文档地址：https://tinyauth.app/docs/guides/nginx-proxy-manager

Demo地址：https://tinyauth.app/

下面我们就用 Tinyauth配合 Nginx Proxy Manager，简单分享一下是怎么搭建这个中间件从而来保护我们的Docker应用的。

4. 搭建环境

• 服务器：这边强烈建议用非大陆的服务器，咕咕这边用的香港的莱卡云轻量应用服务器，建议服务器内存1G以上，当然你也可以选择其他高性价比的服务器。
• 系统：Debian 11 （DD 脚本 非必需 DD，用原来的系统也 OK，之后教程都是用 Debian 或者 Ubuntu 搭建～）
• 安装好 Docker、Docker-compose（相关脚本）
• 【必需】域名一枚，并做好解析到服务器上（域名购买、域名解析 视频教程）
• 【非必需】提前安装好宝塔面板海外版本 aapanel，并安装好 Nginx（安装地址）
• 【非必需本教程选用】安装好 Nginx Proxy Manager（相关教程）

5. 搭建视频（过俩天补充 = =）

5.1 YouTube

视频地址：

5.2 哔哩哔哩

哔哩哔哩：

6. 搭建方式

6.1 安装 Docker 与 Nginx Proxy Manager

可以直接参考这篇内容：

https://blog.laoda.de/archives/nginxproxymanager/

我们这边假设大家都装好了Nginx Proxy Manger，

假设Nginx Proxy Manger在服务器上的路径是~/data/docker_data/npm

这边的话就只需要修改一下即可。

官方文档给的参考如下：

services:
  npm:
    container_name: npm
    image: jc21/nginx-proxy-manager:2
    restart: unless-stopped
    ports:
      - 80:80
      - 443:443
      - 81:81
    volumes:
      - npm-data:/data
      - npm-letsencrypt:/etc/letsencrypt

  nginx:
    container_name: nginx
    image: nginx:latest
    restart: unless-stopped

  tinyauth:
    container_name: tinyauth
    image: ghcr.io/steveiliop56/tinyauth:v3
    restart: unless-stopped
    environment:
      - SECRET_FILE=/secret.txt
      - APP_URL=http://tinyauth.example.com
      - USERS=user:$$2a$$10$$UdLYoJ5lgPsC0RKqYH/jMua7zIn0g9kPqWmhYayJYLaZQ/FTmH2/u # user:password

volumes:
  npm-data:
  npm-letsencrypt:

如果直接使用，你一定会遇到很多问题。

我不会告诉你我用官方的这个配置文件，折腾了大半小时 = =

这边直接用咕咕修改过的这个：

重新编辑你的NPM的docker-compose.yaml文件，改成下面这个：

services:
  npm:
    container_name: npm
    image: jc21/nginx-proxy-manager:2
    restart: unless-stopped
    ports:
      - 80:80
      - 443:443
      - 81:81
    volumes:
      - ./data:/data         # 冒号左边的 ./data改成你自己实际的路径
      - ./letsencrypt:/etc/letsencrypt  # 冒号左边的 ./letsencrypt改成你自己实际的路径

  tinyauth:
    container_name: tinyauth
    image: ghcr.io/steveiliop56/tinyauth:v3
    restart: unless-stopped
    environment:
      - SECRET=kX9mPqW3zT7rY2vN8bL4jF6hD1cA5eK2  # 这个也要修改
      - APP_URL=https://auth.gugu.ovh  #这个也要修改
      - USERS=roy:$$2a$$10$$oXMqgLV/S1hrknYQht.WYu7YfWxkI4VriQn/y # user:password 这边要修改

然后我们来看需要修改的部分。

SECRET，这个的话，直接在命令行操作：

生成secret:

openssl rand -base64 32 | tr -dc 'a-zA-Z0-9' | head -c 32 && echo

输出类似：kX9mPqW3zT7rY2vN8bL4jF6hD1cA5eK2 填入yaml即可。

APP_URL 这里改成你的tinyauth将来想要使用的域名，比如我这边https://auth.gugu.ovh

USERS ，这个官方也提供了方法，生成用户名和密码。

docker run -i -t --rm ghcr.io/steveiliop56/tinyauth:v3 user create --interactive

为docker格式化输出这个，记得选yes（按住shift再按小键盘方向键就可以选）

原因是USERS这边在yaml文件里要做哈希转换（比如哈希中的 $ 需要正确转义为 $$，命令行的 Docker 格式会自动处理。），如果不格式化输出会有问题。

当然也支持多个用户，可以再打一遍代码，设置第二个用户，

如果是一个用户，我们直接贴到yaml文件里即可，但是如果像我们现在这样，有三个用户，直接放进yaml文件会有点长，而且也不好维护。

所以，我们可以把用户配置放入 .env 文件，可以这样做：

编辑 ~/data/docker_data/npm/.env：

SECRET=kX9mPqW3zT7rY2vN8bL4jF6hD1cA5eK2
APP_URL=https://auth.gugu.ovh
USERS=roy:$$2a$$10$$oXMqgLV/S1hrknYQht.WYu7YfEjBdSB5rIicj23O8WxkI4VriQn/y,gugu:$$2a$$10$$s.nq/KZLBlFwUiSUNyRUGe0j2pp.A9/.tecuX7QsCBq242baKgKJ.,xixi:$$2a$$10$$6smj5Y/PD.jB1a2Z2gDAxOVnlcv8HfINtLrzCmmTjMZLObBwV8DoW

修改 docker-compose.yaml 以引用 .env：

services:
  npm:
    container_name: npm
    image: jc21/nginx-proxy-manager:2
    restart: unless-stopped
    ports:
      - 80:80
      - 443:443
      - 81:81
    volumes:
      - ./data:/data
      - ./letsencrypt:/etc/letsencrypt

  nginx:
    container_name: nginx
    image: nginx:latest
    restart: unless-stopped

  tinyauth:
    container_name: tinyauth
    image: ghcr.io/steveiliop56/tinyauth:v3
    restart: unless-stopped
	env_file:
      - .env
#    environment:
#      - SECRET=kX9mPqW3zT7rY2vN8bL4jF6hD1cA5eK2
#      - APP_URL=https://auth.gugu.ovh
#      - USERS=roy:$$2a$$10$$oXMqgLV/S1hrknYQht.WYu7YfEjBdSB5rIicj23O8WxkI4VriQn/y # user:password

这样基本上就OK啦。

重新启动NPM

cd ~/data/docker_data/npm

docker compose down 

docker compose up -d 

docker compose logs tinyauth

出现类似，代表成功。

这边我们先搞一下反向代理！

做反向代理前，你需要一个域名！

namesilo 上面 xyz 后缀的域名一年就 7 块钱，可以年抛。（冷知识，namesilo上 6位数字的xyz续费永远都是0.99美元 = =）

如果想要长期使用，还是建议买 com 后缀的域名，更加正规一些，可以输入 laodade 来获得 1 美元的优惠（不知道现在还有没有）

namesilo 自带隐私保护，咕咕一直在用这家，价格也是这些注册商里面比较低的，关键是他家不像其他家域名注册商，没有七七八八的套路！（就是后台界面有些 丑 古老 = =）

【域名购买】Namesilo 优惠码和域名解析教程（附带服务器购买推荐和注意事项）

我们接着往下看！

7. 反向代理

7.1 配置Tinyauth的反向代理

在添加反向代理之前，确保你已经完成了域名解析，不会的可以看这个：域名一枚，并做好解析到服务器上（域名购买、域名解析 视频教程） （名称改成你自己想要的域名前缀即可）

之后，登陆 Nginx Proxy Manager（不会的看这个：安装 Nginx Proxy Manager（相关教程））

注意：

Nginx Proxy Manager（以下简称 NPM）会用到 80、443 端口，所以本机不能占用（比如原来就有 Nginx）

直接丢几张图：

确保“阻止常见漏洞”(Bolck Common Exploits)选项是关掉的。如果这选项开了，Nginx 会把 URL 里的查询参数给拦下来，而 Tinyauth 得靠这些参数才能正常工作。

tinyauth这个是容器的名字，因为它和NPM在一个网络下，所以可以用容器名字来代替域名，3000是内部的端口，保持即可不要更改。

然后访问域名就可以访问了！

7.2 配置需要保护的应用的反向代理

我这边以之前介绍的简历应用（让写简历变得简单且智能！十分钟搭建一个在线简历编辑器——Magic Resume｜好玩儿的Docker项目）为例子，

找到你需要添加登录页的应用的对应的NPM配置，在Advance里面添加：

# Root location
location / {
  # Pass the request to the app
  proxy_pass          $forward_scheme://$server:$port;

  # Add other app specific config here

  # Tinyauth auth request
  auth_request /tinyauth;
  error_page 401 = @tinyauth_login;
}

# Tinyauth auth request
location /tinyauth {
  # Pass request to Tinyauth
  proxy_pass http://tinyauth:3000/api/auth/nginx;

  # Pass the request headers
  proxy_set_header x-forwarded-proto $scheme;
  proxy_set_header x-forwarded-host $http_host;
  proxy_set_header x-forwarded-uri $request_uri;
}

# Tinyauth login redirect
location @tinyauth_login {
  return 302 https://auth.gugu.ovh/login?redirect_uri=$scheme://$http_host$request_uri; # Make sure to replace the https://auth.gugu.ovh with your own app URL
}

其他地方都不用管，只要把https://auth.gugu.ovh 替换成你自己的tinyauth的域名即可。

保存之后。

再次打开简历这个网页。

提示需要登录了。

输入账号密码，继续

进来了。

8. 使用教程

其他的也类似，只需要在对应应用的NPM的Advance里面加：

# Root location
location / {
  # Pass the request to the app
  proxy_pass          $forward_scheme://$server:$port;

  # Add other app specific config here

  # Tinyauth auth request
  auth_request /tinyauth;
  error_page 401 = @tinyauth_login;
}

# Tinyauth auth request
location /tinyauth {
  # Pass request to Tinyauth
  proxy_pass http://tinyauth:3000/api/auth/nginx;

  # Pass the request headers
  proxy_set_header x-forwarded-proto $scheme;
  proxy_set_header x-forwarded-host $http_host;
  proxy_set_header x-forwarded-uri $request_uri;
}

# Tinyauth login redirect
location @tinyauth_login {
  return 302 https://auth.gugu.ovh/login?redirect_uri=$scheme://$http_host$request_uri; # Make sure to replace the https://auth.gugu.ovh with your own app URL
}

即可。

PS: /tinyauth 这个路径可以随便改，指南里用这个名字只是为了方便。

9. 常见问题及注意点

大家有问题欢迎评论区交流。

10. 结尾

祝大家用得开心，有问题可以去 GitHub 提 Issues，也可以在评论区互相交流探讨。

同时，有能力给项目做贡献的同学，也欢迎积极加入到 项目 中来，贡献自己的一份力量！

最后，感谢作者@steveiliop56的辛苦付出，让我们能用到这么优秀的项目！欢迎大家都去给这个项目点个 star ⭐️

参考资料

官方GitHub：https://github.com/steveiliop56/tinyauth

Dify本地部署上手攻略：轻松打造你的专属AI神器｜好玩儿的Docker项目

2025-08-28 16:50:27

前言

Dify是一个开源的AI应用开发平台，简单来说，它能让普通人也能轻松创建智能聊天机器人或AI助手。

它通过拖拽式的界面，整合了各种大语言模型和工具，比如可以连接企业知识库或外部API，让AI能回答专业问题或完成复杂任务。无论是程序员还是非技术人员，都能用它快速搭建AI应用，省时省力。Dify还支持本地部署，数据安全有保障，特别适合想快速上手AI的团队或个人。

其实Dify已经火了有很长时间了，之前嫌麻烦，我一直没怎么用。最近，公司里的一批小伙伴都换了配置更高的新电脑，纷纷在本地部署起了Dify，这一期就来一个小白级别的教程，和大家简单分享一下Dify的本地部署。

准备工作

Dify本身官方对电脑硬件的建议要求是：

• CPU >= 2 Core
• RAM >= 4 GiB

如果你打算做完全本地的部署，即不用云端的大模型，

如果你是windows电脑，建议配置如下：

内存：至少 16GB 系统内存（推荐 24GB 以上，留 8GB 给操作系统和其他软件）。

GPU（可选但推荐）：至少 16GB VRAM 的 GPU（如 AMD Radeon RX 9070 XT 或 NVIDIA RTX 3090），支持 MXFP4 量化。GPU 内存带宽需高（如 GDDR6X/GDDR7，1000+ GB/s）。

CPU：支持 CPU 推理，但速度较慢。推荐高性能 CPU（如 AMD Ryzen 9 5900X 或 Intel Core i9）。

如果是Mac的话，

硬件：Apple Silicon（M1/M2/M3/M4），至少 16GB 统一内存（推荐 32GB）。

我自己这边用的是Mac，部署起来相对简单一些，用Windows的小伙伴可能会稍微复杂一丢丢。

Windows安装Docker可以参考这个：https://docs.docker.com/desktop/windows/install/#wsl-2-backend

本质都是先在本地电脑安装好Docker，然后通过Docker来部署Dify。

安装Docker

本地装docker，可以去docker官网直接下载一个安装包。

官方地址：https://www.docker.com/products/docker-desktop/

下载之后，就像安装普通软件一样，安装一下。

然后打开docker。

打开Mac的终端，输入docker -v，有版本号说明安装好了。

这边还会涉及docker换源，由于防火墙的原因，我们大陆可能无法访问docker的镜像仓库，建议大家换成中科大的源:https://docker.mirrors.ustc.edu.cn/

改成这个：

{
  "builder": {
    "gc": {
      "defaultKeepStorage": "20GB",
      "enabled": true
    }
  },
  "experimental": false,
  "features": {
    "buildkit": true
  },
  "registry-mirrors": [
    "https://docker.mirrors.ustc.edu.cn"
  ]
}

然后记得点击应用并重启。

使用如下命令查看Docker配置，

docker info

就可以了。

安装Dify

Docker安装好之后，接下来安装我们今天的主角——Dify。

文档地址：https://docs.dify.ai/en/introduction

这边一直关注咕咕的小伙伴可以很轻松的安装好。

Mac和Linux其实差不多，我们直接像操作VPS一样来就行。

mkdir ./data/docker_data
cd data/docker_data

git clone --branch "$(curl -s https://api.github.com/repos/langgenius/dify/releases/latest | jq -r .tag_name)" https://github.com/langgenius/dify.git      # 从GitHub下载dify源码

cd dify/docker    # 进入文件夹

cp .env.example .env    # 拷贝一份配置文件

这里如果后续有需求，可以自行修改这个配置文件，一起来看一下

# ------------------------------
# Environment Variables for API service & worker
# ------------------------------

# ------------------------------
# Common Variables
# ------------------------------

# The backend URL of the console API,
# used to concatenate the authorization callback.
# If empty, it is the same domain.
# Example: https://api.console.dify.ai
CONSOLE_API_URL=

# The front-end URL of the console web,
# used to concatenate some front-end addresses and for CORS configuration use.
# If empty, it is the same domain.
# Example: https://console.dify.ai
CONSOLE_WEB_URL=

# Service API Url,
# used to display Service API Base Url to the front-end.
# If empty, it is the same domain.
# Example: https://api.dify.ai
SERVICE_API_URL=

# WebApp API backend Url,
# used to declare the back-end URL for the front-end API.
# If empty, it is the same domain.
# Example: https://api.app.dify.ai
APP_API_URL=

# WebApp Url,
# used to display WebAPP API Base Url to the front-end.
# If empty, it is the same domain.
# Example: https://app.dify.ai
APP_WEB_URL=

# File preview or download Url prefix.
# used to display File preview or download Url to the front-end or as Multi-model inputs;
# Url is signed and has expiration time.
# Setting FILES_URL is required for file processing plugins.
#   - For https://example.com, use FILES_URL=https://example.com
#   - For http://example.com, use FILES_URL=http://example.com
#   Recommendation: use a dedicated domain (e.g., https://upload.example.com).
#   Alternatively, use http://<your-ip>:5001 or http://api:5001,
#   ensuring port 5001 is externally accessible (see docker-compose.yaml).
FILES_URL=

# INTERNAL_FILES_URL is used for plugin daemon communication within Docker network.
# Set this to the internal Docker service URL for proper plugin file access.
# Example: INTERNAL_FILES_URL=http://api:5001
INTERNAL_FILES_URL=

# Ensure UTF-8 encoding
LANG=en_US.UTF-8
LC_ALL=en_US.UTF-8
PYTHONIOENCODING=utf-8

# ------------------------------
# Server Configuration
# ------------------------------

# The log level for the application.
# Supported values are `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL`
LOG_LEVEL=INFO
# Log file path
LOG_FILE=/app/logs/server.log
# Log file max size, the unit is MB
LOG_FILE_MAX_SIZE=20
# Log file max backup count
LOG_FILE_BACKUP_COUNT=5
# Log dateformat
LOG_DATEFORMAT=%Y-%m-%d %H:%M:%S
# Log Timezone
LOG_TZ=UTC

# Debug mode, default is false.
# It is recommended to turn on this configuration for local development
# to prevent some problems caused by monkey patch.
DEBUG=false

# Flask debug mode, it can output trace information at the interface when turned on,
# which is convenient for debugging.
FLASK_DEBUG=false

# Enable request logging, which will log the request and response information.
# And the log level is DEBUG
ENABLE_REQUEST_LOGGING=False

# A secret key that is used for securely signing the session cookie
# and encrypting sensitive information on the database.
# You can generate a strong key using `openssl rand -base64 42`.
SECRET_KEY=sk-9f73s3ljTXVcMT3Blb3ljTqtsKiGHXVcMT3BlbkFJLK7U

# Password for admin user initialization.
# If left unset, admin user will not be prompted for a password
# when creating the initial admin account.
# The length of the password cannot exceed 30 characters.
INIT_PASSWORD=

# Deployment environment.
# Supported values are `PRODUCTION`, `TESTING`. Default is `PRODUCTION`.
# Testing environment. There will be a distinct color label on the front-end page,
# indicating that this environment is a testing environment.
DEPLOY_ENV=PRODUCTION

# Whether to enable the version check policy.
# If set to empty, https://updates.dify.ai will be called for version check.
CHECK_UPDATE_URL=https://updates.dify.ai

# Used to change the OpenAI base address, default is https://api.openai.com/v1.
# When OpenAI cannot be accessed in China, replace it with a domestic mirror address,
# or when a local model provides OpenAI compatible API, it can be replaced.
OPENAI_API_BASE=https://api.openai.com/v1

# When enabled, migrations will be executed prior to application startup
# and the application will start after the migrations have completed.
MIGRATION_ENABLED=true

# File Access Time specifies a time interval in seconds for the file to be accessed.
# The default value is 300 seconds.
FILES_ACCESS_TIMEOUT=300

# Access token expiration time in minutes
ACCESS_TOKEN_EXPIRE_MINUTES=60

# Refresh token expiration time in days
REFRESH_TOKEN_EXPIRE_DAYS=30

# The maximum number of active requests for the application, where 0 means unlimited, should be a non-negative integer.
APP_MAX_ACTIVE_REQUESTS=0
APP_MAX_EXECUTION_TIME=1200

# ------------------------------
# Container Startup Related Configuration
# Only effective when starting with docker image or docker-compose.
# ------------------------------

# API service binding address, default: 0.0.0.0, i.e., all addresses can be accessed.
DIFY_BIND_ADDRESS=0.0.0.0

# API service binding port number, default 5001.
DIFY_PORT=5001

# The number of API server workers, i.e., the number of workers.
# Formula: number of cpu cores x 2 + 1 for sync, 1 for Gevent
# Reference: https://docs.gunicorn.org/en/stable/design.html#how-many-workers
SERVER_WORKER_AMOUNT=1

# Defaults to gevent. If using windows, it can be switched to sync or solo.
SERVER_WORKER_CLASS=gevent

# Default number of worker connections, the default is 10.
SERVER_WORKER_CONNECTIONS=10

# Similar to SERVER_WORKER_CLASS.
# If using windows, it can be switched to sync or solo.
CELERY_WORKER_CLASS=

# Request handling timeout. The default is 200,
# it is recommended to set it to 360 to support a longer sse connection time.
GUNICORN_TIMEOUT=360

# The number of Celery workers. The default is 1, and can be set as needed.
CELERY_WORKER_AMOUNT=

# Flag indicating whether to enable autoscaling of Celery workers.
#
# Autoscaling is useful when tasks are CPU intensive and can be dynamically
# allocated and deallocated based on the workload.
#
# When autoscaling is enabled, the maximum and minimum number of workers can
# be specified. The autoscaling algorithm will dynamically adjust the number
# of workers within the specified range.
#
# Default is false (i.e., autoscaling is disabled).
#
# Example:
# CELERY_AUTO_SCALE=true
CELERY_AUTO_SCALE=false

# The maximum number of Celery workers that can be autoscaled.
# This is optional and only used when autoscaling is enabled.
# Default is not set.
CELERY_MAX_WORKERS=

# The minimum number of Celery workers that can be autoscaled.
# This is optional and only used when autoscaling is enabled.
# Default is not set.
CELERY_MIN_WORKERS=

# API Tool configuration
API_TOOL_DEFAULT_CONNECT_TIMEOUT=10
API_TOOL_DEFAULT_READ_TIMEOUT=60

# -------------------------------
# Datasource Configuration
# --------------------------------
ENABLE_WEBSITE_JINAREADER=true
ENABLE_WEBSITE_FIRECRAWL=true
ENABLE_WEBSITE_WATERCRAWL=true

# ------------------------------
# Database Configuration
# The database uses PostgreSQL. Please use the public schema.
# It is consistent with the configuration in the 'db' service below.
# ------------------------------

DB_USERNAME=postgres
DB_PASSWORD=difyai123456
DB_HOST=db
DB_PORT=5432
DB_DATABASE=dify
# The size of the database connection pool.
# The default is 30 connections, which can be appropriately increased.
SQLALCHEMY_POOL_SIZE=30
# The default is 10 connections, which allows temporary overflow beyond the pool size.
SQLALCHEMY_MAX_OVERFLOW=10
# Database connection pool recycling time, the default is 3600 seconds.
SQLALCHEMY_POOL_RECYCLE=3600
# Whether to print SQL, default is false.
SQLALCHEMY_ECHO=false
# If True, will test connections for liveness upon each checkout
SQLALCHEMY_POOL_PRE_PING=false
# Whether to enable the Last in first out option or use default FIFO queue if is false
SQLALCHEMY_POOL_USE_LIFO=false

# Maximum number of connections to the database
# Default is 100
#
# Reference: https://www.postgresql.org/docs/current/runtime-config-connection.html#GUC-MAX-CONNECTIONS
POSTGRES_MAX_CONNECTIONS=100

# Sets the amount of shared memory used for postgres's shared buffers.
# Default is 128MB
# Recommended value: 25% of available memory
# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-SHARED-BUFFERS
POSTGRES_SHARED_BUFFERS=128MB

# Sets the amount of memory used by each database worker for working space.
# Default is 4MB
#
# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-WORK-MEM
POSTGRES_WORK_MEM=4MB

# Sets the amount of memory reserved for maintenance activities.
# Default is 64MB
#
# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-MAINTENANCE-WORK-MEM
POSTGRES_MAINTENANCE_WORK_MEM=64MB

# Sets the planner's assumption about the effective cache size.
# Default is 4096MB
#
# Reference: https://www.postgresql.org/docs/current/runtime-config-query.html#GUC-EFFECTIVE-CACHE-SIZE
POSTGRES_EFFECTIVE_CACHE_SIZE=4096MB

# ------------------------------
# Redis Configuration
# This Redis configuration is used for caching and for pub/sub during conversation.
# ------------------------------

REDIS_HOST=redis
REDIS_PORT=6379
REDIS_USERNAME=
REDIS_PASSWORD=difyai123456
REDIS_USE_SSL=false
# SSL configuration for Redis (when REDIS_USE_SSL=true)
REDIS_SSL_CERT_REQS=CERT_NONE
# Options: CERT_NONE, CERT_OPTIONAL, CERT_REQUIRED
REDIS_SSL_CA_CERTS=
# Path to CA certificate file for SSL verification
REDIS_SSL_CERTFILE=
# Path to client certificate file for SSL authentication
REDIS_SSL_KEYFILE=
# Path to client private key file for SSL authentication
REDIS_DB=0

# Whether to use Redis Sentinel mode.
# If set to true, the application will automatically discover and connect to the master node through Sentinel.
REDIS_USE_SENTINEL=false

# List of Redis Sentinel nodes. If Sentinel mode is enabled, provide at least one Sentinel IP and port.
# Format: `<sentinel1_ip>:<sentinel1_port>,<sentinel2_ip>:<sentinel2_port>,<sentinel3_ip>:<sentinel3_port>`
REDIS_SENTINELS=
REDIS_SENTINEL_SERVICE_NAME=
REDIS_SENTINEL_USERNAME=
REDIS_SENTINEL_PASSWORD=
REDIS_SENTINEL_SOCKET_TIMEOUT=0.1

# List of Redis Cluster nodes. If Cluster mode is enabled, provide at least one Cluster IP and port.
# Format: `<Cluster1_ip>:<Cluster1_port>,<Cluster2_ip>:<Cluster2_port>,<Cluster3_ip>:<Cluster3_port>`
REDIS_USE_CLUSTERS=false
REDIS_CLUSTERS=
REDIS_CLUSTERS_PASSWORD=

# ------------------------------
# Celery Configuration
# ------------------------------

# Use standalone redis as the broker, and redis db 1 for celery broker. (redis_username is usually set by defualt as empty)
# Format as follows: `redis://<redis_username>:<redis_password>@<redis_host>:<redis_port>/<redis_database>`.
# Example: redis://:difyai123456@redis:6379/1
# If use Redis Sentinel, format as follows: `sentinel://<redis_username>:<redis_password>@<sentinel_host1>:<sentinel_port>/<redis_database>`
# For high availability, you can configure multiple Sentinel nodes (if provided) separated by semicolons like below example:
# Example: sentinel://:difyai123456@localhost:26379/1;sentinel://:difyai12345@localhost:26379/1;sentinel://:difyai12345@localhost:26379/1
CELERY_BROKER_URL=redis://:difyai123456@redis:6379/1
CELERY_BACKEND=redis
BROKER_USE_SSL=false

# If you are using Redis Sentinel for high availability, configure the following settings.
CELERY_USE_SENTINEL=false
CELERY_SENTINEL_MASTER_NAME=
CELERY_SENTINEL_PASSWORD=
CELERY_SENTINEL_SOCKET_TIMEOUT=0.1

# ------------------------------
# CORS Configuration
# Used to set the front-end cross-domain access policy.
# ------------------------------

# Specifies the allowed origins for cross-origin requests to the Web API,
# e.g. https://dify.app or * for all origins.
WEB_API_CORS_ALLOW_ORIGINS=*

# Specifies the allowed origins for cross-origin requests to the console API,
# e.g. https://cloud.dify.ai or * for all origins.
CONSOLE_CORS_ALLOW_ORIGINS=*

# ------------------------------
# File Storage Configuration
# ------------------------------

# The type of storage to use for storing user files.
STORAGE_TYPE=opendal

# Apache OpenDAL Configuration
# The configuration for OpenDAL consists of the following format: OPENDAL_<SCHEME_NAME>_<CONFIG_NAME>.
# You can find all the service configurations (CONFIG_NAME) in the repository at: https://github.com/apache/opendal/tree/main/core/src/services.
# Dify will scan configurations starting with OPENDAL_<SCHEME_NAME> and automatically apply them.
# The scheme name for the OpenDAL storage.
OPENDAL_SCHEME=fs
# Configurations for OpenDAL Local File System.
OPENDAL_FS_ROOT=storage

# ClickZetta Volume Configuration (for storage backend)
# To use ClickZetta Volume as storage backend, set STORAGE_TYPE=clickzetta-volume
# Note: ClickZetta Volume will reuse the existing CLICKZETTA_* connection parameters

# Volume type selection (three types available):
# - user: Personal/small team use, simple config, user-level permissions
# - table: Enterprise multi-tenant, smart routing, table-level + user-level permissions
# - external: Data lake integration, external storage connection, volume-level + storage-level permissions
CLICKZETTA_VOLUME_TYPE=user

# External Volume name (required only when TYPE=external)
CLICKZETTA_VOLUME_NAME=

# Table Volume table prefix (used only when TYPE=table)
CLICKZETTA_VOLUME_TABLE_PREFIX=dataset_

# Dify file directory prefix (isolates from other apps, recommended to keep default)
CLICKZETTA_VOLUME_DIFY_PREFIX=dify_km

# S3 Configuration
#
S3_ENDPOINT=
S3_REGION=us-east-1
S3_BUCKET_NAME=difyai
S3_ACCESS_KEY=
S3_SECRET_KEY=
# Whether to use AWS managed IAM roles for authenticating with the S3 service.
# If set to false, the access key and secret key must be provided.
S3_USE_AWS_MANAGED_IAM=false

# Azure Blob Configuration
#
AZURE_BLOB_ACCOUNT_NAME=difyai
AZURE_BLOB_ACCOUNT_KEY=difyai
AZURE_BLOB_CONTAINER_NAME=difyai-container
AZURE_BLOB_ACCOUNT_URL=https://<your_account_name>.blob.core.windows.net

# Google Storage Configuration
#
GOOGLE_STORAGE_BUCKET_NAME=your-bucket-name
GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64=

# The Alibaba Cloud OSS configurations,
#
ALIYUN_OSS_BUCKET_NAME=your-bucket-name
ALIYUN_OSS_ACCESS_KEY=your-access-key
ALIYUN_OSS_SECRET_KEY=your-secret-key
ALIYUN_OSS_ENDPOINT=https://oss-ap-southeast-1-internal.aliyuncs.com
ALIYUN_OSS_REGION=ap-southeast-1
ALIYUN_OSS_AUTH_VERSION=v4
# Don't start with '/'. OSS doesn't support leading slash in object names.
ALIYUN_OSS_PATH=your-path

# Tencent COS Configuration
#
TENCENT_COS_BUCKET_NAME=your-bucket-name
TENCENT_COS_SECRET_KEY=your-secret-key
TENCENT_COS_SECRET_ID=your-secret-id
TENCENT_COS_REGION=your-region
TENCENT_COS_SCHEME=your-scheme

# Oracle Storage Configuration
#
OCI_ENDPOINT=https://your-object-storage-namespace.compat.objectstorage.us-ashburn-1.oraclecloud.com
OCI_BUCKET_NAME=your-bucket-name
OCI_ACCESS_KEY=your-access-key
OCI_SECRET_KEY=your-secret-key
OCI_REGION=us-ashburn-1

# Huawei OBS Configuration
#
HUAWEI_OBS_BUCKET_NAME=your-bucket-name
HUAWEI_OBS_SECRET_KEY=your-secret-key
HUAWEI_OBS_ACCESS_KEY=your-access-key
HUAWEI_OBS_SERVER=your-server-url

# Volcengine TOS Configuration
#
VOLCENGINE_TOS_BUCKET_NAME=your-bucket-name
VOLCENGINE_TOS_SECRET_KEY=your-secret-key
VOLCENGINE_TOS_ACCESS_KEY=your-access-key
VOLCENGINE_TOS_ENDPOINT=your-server-url
VOLCENGINE_TOS_REGION=your-region

# Baidu OBS Storage Configuration
#
BAIDU_OBS_BUCKET_NAME=your-bucket-name
BAIDU_OBS_SECRET_KEY=your-secret-key
BAIDU_OBS_ACCESS_KEY=your-access-key
BAIDU_OBS_ENDPOINT=your-server-url

# Supabase Storage Configuration
#
SUPABASE_BUCKET_NAME=your-bucket-name
SUPABASE_API_KEY=your-access-key
SUPABASE_URL=your-server-url

# ------------------------------
# Vector Database Configuration
# ------------------------------

# The type of vector store to use.
# Supported values are `weaviate`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `pgvecto-rs`, `chroma`, `opensearch`, `oracle`, `tencent`, `elasticsearch`, `elasticsearch-ja`, `analyticdb`, `couchbase`, `vikingdb`, `oceanbase`, `opengauss`, `tablestore`,`vastbase`,`tidb`,`tidb_on_qdrant`,`baidu`,`lindorm`,`huawei_cloud`,`upstash`, `matrixone`, `clickzetta`.
VECTOR_STORE=weaviate
# Prefix used to create collection name in vector database
VECTOR_INDEX_NAME_PREFIX=Vector_index

# The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`.
WEAVIATE_ENDPOINT=http://weaviate:8080
WEAVIATE_API_KEY=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih

# The Qdrant endpoint URL. Only available when VECTOR_STORE is `qdrant`.
QDRANT_URL=http://qdrant:6333
QDRANT_API_KEY=difyai123456
QDRANT_CLIENT_TIMEOUT=20
QDRANT_GRPC_ENABLED=false
QDRANT_GRPC_PORT=6334
QDRANT_REPLICATION_FACTOR=1

# Milvus configuration. Only available when VECTOR_STORE is `milvus`.
# The milvus uri.
MILVUS_URI=http://host.docker.internal:19530
MILVUS_DATABASE=
MILVUS_TOKEN=
MILVUS_USER=
MILVUS_PASSWORD=
MILVUS_ENABLE_HYBRID_SEARCH=False
MILVUS_ANALYZER_PARAMS=

# MyScale configuration, only available when VECTOR_STORE is `myscale`
# For multi-language support, please set MYSCALE_FTS_PARAMS with referring to:
# https://myscale.com/docs/en/text-search/#understanding-fts-index-parameters
MYSCALE_HOST=myscale
MYSCALE_PORT=8123
MYSCALE_USER=default
MYSCALE_PASSWORD=
MYSCALE_DATABASE=dify
MYSCALE_FTS_PARAMS=

# Couchbase configurations, only available when VECTOR_STORE is `couchbase`
# The connection string must include hostname defined in the docker-compose file (couchbase-server in this case)
COUCHBASE_CONNECTION_STRING=couchbase://couchbase-server
COUCHBASE_USER=Administrator
COUCHBASE_PASSWORD=password
COUCHBASE_BUCKET_NAME=Embeddings
COUCHBASE_SCOPE_NAME=_default

# pgvector configurations, only available when VECTOR_STORE is `pgvector`
PGVECTOR_HOST=pgvector
PGVECTOR_PORT=5432
PGVECTOR_USER=postgres
PGVECTOR_PASSWORD=difyai123456
PGVECTOR_DATABASE=dify
PGVECTOR_MIN_CONNECTION=1
PGVECTOR_MAX_CONNECTION=5
PGVECTOR_PG_BIGM=false
PGVECTOR_PG_BIGM_VERSION=1.2-20240606

# vastbase configurations, only available when VECTOR_STORE is `vastbase`
VASTBASE_HOST=vastbase
VASTBASE_PORT=5432
VASTBASE_USER=dify
VASTBASE_PASSWORD=Difyai123456
VASTBASE_DATABASE=dify
VASTBASE_MIN_CONNECTION=1
VASTBASE_MAX_CONNECTION=5

# pgvecto-rs configurations, only available when VECTOR_STORE is `pgvecto-rs`
PGVECTO_RS_HOST=pgvecto-rs
PGVECTO_RS_PORT=5432
PGVECTO_RS_USER=postgres
PGVECTO_RS_PASSWORD=difyai123456
PGVECTO_RS_DATABASE=dify

# analyticdb configurations, only available when VECTOR_STORE is `analyticdb`
ANALYTICDB_KEY_ID=your-ak
ANALYTICDB_KEY_SECRET=your-sk
ANALYTICDB_REGION_ID=cn-hangzhou
ANALYTICDB_INSTANCE_ID=gp-ab123456
ANALYTICDB_ACCOUNT=testaccount
ANALYTICDB_PASSWORD=testpassword
ANALYTICDB_NAMESPACE=dify
ANALYTICDB_NAMESPACE_PASSWORD=difypassword
ANALYTICDB_HOST=gp-test.aliyuncs.com
ANALYTICDB_PORT=5432
ANALYTICDB_MIN_CONNECTION=1
ANALYTICDB_MAX_CONNECTION=5

# TiDB vector configurations, only available when VECTOR_STORE is `tidb_vector`
TIDB_VECTOR_HOST=tidb
TIDB_VECTOR_PORT=4000
TIDB_VECTOR_USER=
TIDB_VECTOR_PASSWORD=
TIDB_VECTOR_DATABASE=dify

# Matrixone vector configurations.
MATRIXONE_HOST=matrixone
MATRIXONE_PORT=6001
MATRIXONE_USER=dump
MATRIXONE_PASSWORD=111
MATRIXONE_DATABASE=dify

# Tidb on qdrant configuration, only available when VECTOR_STORE is `tidb_on_qdrant`
TIDB_ON_QDRANT_URL=http://127.0.0.1
TIDB_ON_QDRANT_API_KEY=dify
TIDB_ON_QDRANT_CLIENT_TIMEOUT=20
TIDB_ON_QDRANT_GRPC_ENABLED=false
TIDB_ON_QDRANT_GRPC_PORT=6334
TIDB_PUBLIC_KEY=dify
TIDB_PRIVATE_KEY=dify
TIDB_API_URL=http://127.0.0.1
TIDB_IAM_API_URL=http://127.0.0.1
TIDB_REGION=regions/aws-us-east-1
TIDB_PROJECT_ID=dify
TIDB_SPEND_LIMIT=100

# Chroma configuration, only available when VECTOR_STORE is `chroma`
CHROMA_HOST=127.0.0.1
CHROMA_PORT=8000
CHROMA_TENANT=default_tenant
CHROMA_DATABASE=default_database
CHROMA_AUTH_PROVIDER=chromadb.auth.token_authn.TokenAuthClientProvider
CHROMA_AUTH_CREDENTIALS=

# Oracle configuration, only available when VECTOR_STORE is `oracle`
ORACLE_USER=dify
ORACLE_PASSWORD=dify
ORACLE_DSN=oracle:1521/FREEPDB1
ORACLE_CONFIG_DIR=/app/api/storage/wallet
ORACLE_WALLET_LOCATION=/app/api/storage/wallet
ORACLE_WALLET_PASSWORD=dify
ORACLE_IS_AUTONOMOUS=false

# relyt configurations, only available when VECTOR_STORE is `relyt`
RELYT_HOST=db
RELYT_PORT=5432
RELYT_USER=postgres
RELYT_PASSWORD=difyai123456
RELYT_DATABASE=postgres

# open search configuration, only available when VECTOR_STORE is `opensearch`
OPENSEARCH_HOST=opensearch
OPENSEARCH_PORT=9200
OPENSEARCH_SECURE=true
OPENSEARCH_VERIFY_CERTS=true
OPENSEARCH_AUTH_METHOD=basic
OPENSEARCH_USER=admin
OPENSEARCH_PASSWORD=admin
# If using AWS managed IAM, e.g. Managed Cluster or OpenSearch Serverless
OPENSEARCH_AWS_REGION=ap-southeast-1
OPENSEARCH_AWS_SERVICE=aoss

# tencent vector configurations, only available when VECTOR_STORE is `tencent`
TENCENT_VECTOR_DB_URL=http://127.0.0.1
TENCENT_VECTOR_DB_API_KEY=dify
TENCENT_VECTOR_DB_TIMEOUT=30
TENCENT_VECTOR_DB_USERNAME=dify
TENCENT_VECTOR_DB_DATABASE=dify
TENCENT_VECTOR_DB_SHARD=1
TENCENT_VECTOR_DB_REPLICAS=2
TENCENT_VECTOR_DB_ENABLE_HYBRID_SEARCH=false

# ElasticSearch configuration, only available when VECTOR_STORE is `elasticsearch`
ELASTICSEARCH_HOST=0.0.0.0
ELASTICSEARCH_PORT=9200
ELASTICSEARCH_USERNAME=elastic
ELASTICSEARCH_PASSWORD=elastic
KIBANA_PORT=5601

# Using ElasticSearch Cloud Serverless, or not.
ELASTICSEARCH_USE_CLOUD=false
ELASTICSEARCH_CLOUD_URL=YOUR-ELASTICSEARCH_CLOUD_URL
ELASTICSEARCH_API_KEY=YOUR-ELASTICSEARCH_API_KEY

ELASTICSEARCH_VERIFY_CERTS=False
ELASTICSEARCH_CA_CERTS=
ELASTICSEARCH_REQUEST_TIMEOUT=100000
ELASTICSEARCH_RETRY_ON_TIMEOUT=True
ELASTICSEARCH_MAX_RETRIES=10

# baidu vector configurations, only available when VECTOR_STORE is `baidu`
BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000
BAIDU_VECTOR_DB_ACCOUNT=root
BAIDU_VECTOR_DB_API_KEY=dify
BAIDU_VECTOR_DB_DATABASE=dify
BAIDU_VECTOR_DB_SHARD=1
BAIDU_VECTOR_DB_REPLICAS=3

# VikingDB configurations, only available when VECTOR_STORE is `vikingdb`
VIKINGDB_ACCESS_KEY=your-ak
VIKINGDB_SECRET_KEY=your-sk
VIKINGDB_REGION=cn-shanghai
VIKINGDB_HOST=api-vikingdb.xxx.volces.com
VIKINGDB_SCHEMA=http
VIKINGDB_CONNECTION_TIMEOUT=30
VIKINGDB_SOCKET_TIMEOUT=30

# Lindorm configuration, only available when VECTOR_STORE is `lindorm`
LINDORM_URL=http://lindorm:30070
LINDORM_USERNAME=lindorm
LINDORM_PASSWORD=lindorm
LINDORM_QUERY_TIMEOUT=1

# OceanBase Vector configuration, only available when VECTOR_STORE is `oceanbase`
OCEANBASE_VECTOR_HOST=oceanbase
OCEANBASE_VECTOR_PORT=2881
OCEANBASE_VECTOR_USER=root@test
OCEANBASE_VECTOR_PASSWORD=difyai123456
OCEANBASE_VECTOR_DATABASE=test
OCEANBASE_CLUSTER_NAME=difyai
OCEANBASE_MEMORY_LIMIT=6G
OCEANBASE_ENABLE_HYBRID_SEARCH=false

# opengauss configurations, only available when VECTOR_STORE is `opengauss`
OPENGAUSS_HOST=opengauss
OPENGAUSS_PORT=6600
OPENGAUSS_USER=postgres
OPENGAUSS_PASSWORD=Dify@123
OPENGAUSS_DATABASE=dify
OPENGAUSS_MIN_CONNECTION=1
OPENGAUSS_MAX_CONNECTION=5
OPENGAUSS_ENABLE_PQ=false

# huawei cloud search service vector configurations, only available when VECTOR_STORE is `huawei_cloud`
HUAWEI_CLOUD_HOSTS=https://127.0.0.1:9200
HUAWEI_CLOUD_USER=admin
HUAWEI_CLOUD_PASSWORD=admin

# Upstash Vector configuration, only available when VECTOR_STORE is `upstash`
UPSTASH_VECTOR_URL=https://xxx-vector.upstash.io
UPSTASH_VECTOR_TOKEN=dify

# TableStore Vector configuration
# (only used when VECTOR_STORE is tablestore)
TABLESTORE_ENDPOINT=https://instance-name.cn-hangzhou.ots.aliyuncs.com
TABLESTORE_INSTANCE_NAME=instance-name
TABLESTORE_ACCESS_KEY_ID=xxx
TABLESTORE_ACCESS_KEY_SECRET=xxx
TABLESTORE_NORMALIZE_FULLTEXT_BM25_SCORE=false

# Clickzetta configuration, only available when VECTOR_STORE is `clickzetta`
CLICKZETTA_USERNAME=
CLICKZETTA_PASSWORD=
CLICKZETTA_INSTANCE=
CLICKZETTA_SERVICE=api.clickzetta.com
CLICKZETTA_WORKSPACE=quick_start
CLICKZETTA_VCLUSTER=default_ap
CLICKZETTA_SCHEMA=dify
CLICKZETTA_BATCH_SIZE=100
CLICKZETTA_ENABLE_INVERTED_INDEX=true
CLICKZETTA_ANALYZER_TYPE=chinese
CLICKZETTA_ANALYZER_MODE=smart
CLICKZETTA_VECTOR_DISTANCE_FUNCTION=cosine_distance

# ------------------------------
# Knowledge Configuration
# ------------------------------

# Upload file size limit, default 15M.
UPLOAD_FILE_SIZE_LIMIT=15

# The maximum number of files that can be uploaded at a time, default 5.
UPLOAD_FILE_BATCH_LIMIT=5

# ETL type, support: `dify`, `Unstructured`
# `dify` Dify's proprietary file extraction scheme
# `Unstructured` Unstructured.io file extraction scheme
ETL_TYPE=dify

# Unstructured API path and API key, needs to be configured when ETL_TYPE is Unstructured
# Or using Unstructured for document extractor node for pptx.
# For example: http://unstructured:8000/general/v0/general
UNSTRUCTURED_API_URL=
UNSTRUCTURED_API_KEY=
SCARF_NO_ANALYTICS=true

# ------------------------------
# Model Configuration
# ------------------------------

# The maximum number of tokens allowed for prompt generation.
# This setting controls the upper limit of tokens that can be used by the LLM
# when generating a prompt in the prompt generation tool.
# Default: 512 tokens.
PROMPT_GENERATION_MAX_TOKENS=512

# The maximum number of tokens allowed for code generation.
# This setting controls the upper limit of tokens that can be used by the LLM
# when generating code in the code generation tool.
# Default: 1024 tokens.
CODE_GENERATION_MAX_TOKENS=1024

# Enable or disable plugin based token counting. If disabled, token counting will return 0.
# This can improve performance by skipping token counting operations.
# Default: false (disabled).
PLUGIN_BASED_TOKEN_COUNTING_ENABLED=false

# ------------------------------
# Multi-modal Configuration
# ------------------------------

# The format of the image/video/audio/document sent when the multi-modal model is input,
# the default is base64, optional url.
# The delay of the call in url mode will be lower than that in base64 mode.
# It is generally recommended to use the more compatible base64 mode.
# If configured as url, you need to configure FILES_URL as an externally accessible address so that the multi-modal model can access the image/video/audio/document.
MULTIMODAL_SEND_FORMAT=base64
# Upload image file size limit, default 10M.
UPLOAD_IMAGE_FILE_SIZE_LIMIT=10
# Upload video file size limit, default 100M.
UPLOAD_VIDEO_FILE_SIZE_LIMIT=100
# Upload audio file size limit, default 50M.
UPLOAD_AUDIO_FILE_SIZE_LIMIT=50

# ------------------------------
# Sentry Configuration
# Used for application monitoring and error log tracking.
# ------------------------------
SENTRY_DSN=

# API Service Sentry DSN address, default is empty, when empty,
# all monitoring information is not reported to Sentry.
# If not set, Sentry error reporting will be disabled.
API_SENTRY_DSN=
# API Service The reporting ratio of Sentry events, if it is 0.01, it is 1%.
API_SENTRY_TRACES_SAMPLE_RATE=1.0
# API Service The reporting ratio of Sentry profiles, if it is 0.01, it is 1%.
API_SENTRY_PROFILES_SAMPLE_RATE=1.0

# Web Service Sentry DSN address, default is empty, when empty,
# all monitoring information is not reported to Sentry.
# If not set, Sentry error reporting will be disabled.
WEB_SENTRY_DSN=

# ------------------------------
# Notion Integration Configuration
# Variables can be obtained by applying for Notion integration: https://www.notion.so/my-integrations
# ------------------------------

# Configure as "public" or "internal".
# Since Notion's OAuth redirect URL only supports HTTPS,
# if deploying locally, please use Notion's internal integration.
NOTION_INTEGRATION_TYPE=public
# Notion OAuth client secret (used for public integration type)
NOTION_CLIENT_SECRET=
# Notion OAuth client id (used for public integration type)
NOTION_CLIENT_ID=
# Notion internal integration secret.
# If the value of NOTION_INTEGRATION_TYPE is "internal",
# you need to configure this variable.
NOTION_INTERNAL_SECRET=

# ------------------------------
# Mail related configuration
# ------------------------------

# Mail type, support: resend, smtp, sendgrid
MAIL_TYPE=resend

# Default send from email address, if not specified
# If using SendGrid, use the 'from' field for authentication if necessary.
MAIL_DEFAULT_SEND_FROM=

# API-Key for the Resend email provider, used when MAIL_TYPE is `resend`.
RESEND_API_URL=https://api.resend.com
RESEND_API_KEY=your-resend-api-key


# SMTP server configuration, used when MAIL_TYPE is `smtp`
SMTP_SERVER=
SMTP_PORT=465
SMTP_USERNAME=
SMTP_PASSWORD=
SMTP_USE_TLS=true
SMTP_OPPORTUNISTIC_TLS=false

# Sendgid configuration
SENDGRID_API_KEY=

# ------------------------------
# Others Configuration
# ------------------------------

# Maximum length of segmentation tokens for indexing
INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000

# Member invitation link valid time (hours),
# Default: 72.
INVITE_EXPIRY_HOURS=72

# Reset password token valid time (minutes),
RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
CHANGE_EMAIL_TOKEN_EXPIRY_MINUTES=5
OWNER_TRANSFER_TOKEN_EXPIRY_MINUTES=5

# The sandbox service endpoint.
CODE_EXECUTION_ENDPOINT=http://sandbox:8194
CODE_EXECUTION_API_KEY=dify-sandbox
CODE_MAX_NUMBER=9223372036854775807
CODE_MIN_NUMBER=-9223372036854775808
CODE_MAX_DEPTH=5
CODE_MAX_PRECISION=20
CODE_MAX_STRING_LENGTH=80000
CODE_MAX_STRING_ARRAY_LENGTH=30
CODE_MAX_OBJECT_ARRAY_LENGTH=30
CODE_MAX_NUMBER_ARRAY_LENGTH=1000
CODE_EXECUTION_CONNECT_TIMEOUT=10
CODE_EXECUTION_READ_TIMEOUT=60
CODE_EXECUTION_WRITE_TIMEOUT=10
TEMPLATE_TRANSFORM_MAX_LENGTH=80000

# Workflow runtime configuration
WORKFLOW_MAX_EXECUTION_STEPS=500
WORKFLOW_MAX_EXECUTION_TIME=1200
WORKFLOW_CALL_MAX_DEPTH=5
MAX_VARIABLE_SIZE=204800
WORKFLOW_PARALLEL_DEPTH_LIMIT=3
WORKFLOW_FILE_UPLOAD_LIMIT=10

# Workflow storage configuration
# Options: rdbms, hybrid
# rdbms: Use only the relational database (default)
# hybrid: Save new data to object storage, read from both object storage and RDBMS
WORKFLOW_NODE_EXECUTION_STORAGE=rdbms

# Repository configuration
# Core workflow execution repository implementation
# Options:
#   - core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository (default)
#   - core.repositories.celery_workflow_execution_repository.CeleryWorkflowExecutionRepository
CORE_WORKFLOW_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository

# Core workflow node execution repository implementation
# Options:
#   - core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository (default)
#   - core.repositories.celery_workflow_node_execution_repository.CeleryWorkflowNodeExecutionRepository
CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository

# API workflow run repository implementation
API_WORKFLOW_RUN_REPOSITORY=repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository

# API workflow node execution repository implementation
API_WORKFLOW_NODE_EXECUTION_REPOSITORY=repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository

# Workflow log cleanup configuration
# Enable automatic cleanup of workflow run logs to manage database size
WORKFLOW_LOG_CLEANUP_ENABLED=false
# Number of days to retain workflow run logs (default: 30 days)
WORKFLOW_LOG_RETENTION_DAYS=30
# Batch size for workflow log cleanup operations (default: 100)
WORKFLOW_LOG_CLEANUP_BATCH_SIZE=100

# HTTP request node in workflow configuration
HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760
HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576
HTTP_REQUEST_NODE_SSL_VERIFY=True

# Respect X-* headers to redirect clients
RESPECT_XFORWARD_HEADERS_ENABLED=false

# SSRF Proxy server HTTP URL
SSRF_PROXY_HTTP_URL=http://ssrf_proxy:3128
# SSRF Proxy server HTTPS URL
SSRF_PROXY_HTTPS_URL=http://ssrf_proxy:3128

# Maximum loop count in the workflow
LOOP_NODE_MAX_COUNT=100

# The maximum number of tools that can be used in the agent.
MAX_TOOLS_NUM=10

# Maximum number of Parallelism branches in the workflow
MAX_PARALLEL_LIMIT=10

# The maximum number of iterations for agent setting
MAX_ITERATIONS_NUM=99

# ------------------------------
# Environment Variables for web Service
# ------------------------------

# The timeout for the text generation in millisecond
TEXT_GENERATION_TIMEOUT_MS=60000

# Allow rendering unsafe URLs which have "data:" scheme.
ALLOW_UNSAFE_DATA_SCHEME=false

# Maximum number of tree depth in the workflow
MAX_TREE_DEPTH=50

# ------------------------------
# Environment Variables for db Service
# ------------------------------

# The name of the default postgres user.
POSTGRES_USER=${DB_USERNAME}
# The password for the default postgres user.
POSTGRES_PASSWORD=${DB_PASSWORD}
# The name of the default postgres database.
POSTGRES_DB=${DB_DATABASE}
# postgres data directory
PGDATA=/var/lib/postgresql/data/pgdata

# ------------------------------
# Environment Variables for sandbox Service
# ------------------------------

# The API key for the sandbox service
SANDBOX_API_KEY=dify-sandbox
# The mode in which the Gin framework runs
SANDBOX_GIN_MODE=release
# The timeout for the worker in seconds
SANDBOX_WORKER_TIMEOUT=15
# Enable network for the sandbox service
SANDBOX_ENABLE_NETWORK=true
# HTTP proxy URL for SSRF protection
SANDBOX_HTTP_PROXY=http://ssrf_proxy:3128
# HTTPS proxy URL for SSRF protection
SANDBOX_HTTPS_PROXY=http://ssrf_proxy:3128
# The port on which the sandbox service runs
SANDBOX_PORT=8194

# ------------------------------
# Environment Variables for weaviate Service
# (only used when VECTOR_STORE is weaviate)
# ------------------------------
WEAVIATE_PERSISTENCE_DATA_PATH=/var/lib/weaviate
WEAVIATE_QUERY_DEFAULTS_LIMIT=25
WEAVIATE_AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true
WEAVIATE_DEFAULT_VECTORIZER_MODULE=none
WEAVIATE_CLUSTER_HOSTNAME=node1
WEAVIATE_AUTHENTICATION_APIKEY_ENABLED=true
WEAVIATE_AUTHENTICATION_APIKEY_ALLOWED_KEYS=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
[email protected]
WEAVIATE_AUTHORIZATION_ADMINLIST_ENABLED=true
[email protected]

# ------------------------------
# Environment Variables for Chroma
# (only used when VECTOR_STORE is chroma)
# ------------------------------

# Authentication credentials for Chroma server
CHROMA_SERVER_AUTHN_CREDENTIALS=difyai123456
# Authentication provider for Chroma server
CHROMA_SERVER_AUTHN_PROVIDER=chromadb.auth.token_authn.TokenAuthenticationServerProvider
# Persistence setting for Chroma server
CHROMA_IS_PERSISTENT=TRUE

# ------------------------------
# Environment Variables for Oracle Service
# (only used when VECTOR_STORE is oracle)
# ------------------------------
ORACLE_PWD=Dify123456
ORACLE_CHARACTERSET=AL32UTF8

# ------------------------------
# Environment Variables for milvus Service
# (only used when VECTOR_STORE is milvus)
# ------------------------------
# ETCD configuration for auto compaction mode
ETCD_AUTO_COMPACTION_MODE=revision
# ETCD configuration for auto compaction retention in terms of number of revisions
ETCD_AUTO_COMPACTION_RETENTION=1000
# ETCD configuration for backend quota in bytes
ETCD_QUOTA_BACKEND_BYTES=4294967296
# ETCD configuration for the number of changes before triggering a snapshot
ETCD_SNAPSHOT_COUNT=50000
# MinIO access key for authentication
MINIO_ACCESS_KEY=minioadmin
# MinIO secret key for authentication
MINIO_SECRET_KEY=minioadmin
# ETCD service endpoints
ETCD_ENDPOINTS=etcd:2379
# MinIO service address
MINIO_ADDRESS=minio:9000
# Enable or disable security authorization
MILVUS_AUTHORIZATION_ENABLED=true

# ------------------------------
# Environment Variables for pgvector / pgvector-rs Service
# (only used when VECTOR_STORE is pgvector / pgvector-rs)
# ------------------------------
PGVECTOR_PGUSER=postgres
# The password for the default postgres user.
PGVECTOR_POSTGRES_PASSWORD=difyai123456
# The name of the default postgres database.
PGVECTOR_POSTGRES_DB=dify
# postgres data directory
PGVECTOR_PGDATA=/var/lib/postgresql/data/pgdata

# ------------------------------
# Environment Variables for opensearch
# (only used when VECTOR_STORE is opensearch)
# ------------------------------
OPENSEARCH_DISCOVERY_TYPE=single-node
OPENSEARCH_BOOTSTRAP_MEMORY_LOCK=true
OPENSEARCH_JAVA_OPTS_MIN=512m
OPENSEARCH_JAVA_OPTS_MAX=1024m
OPENSEARCH_INITIAL_ADMIN_PASSWORD=Qazwsxedc!@#123
OPENSEARCH_MEMLOCK_SOFT=-1
OPENSEARCH_MEMLOCK_HARD=-1
OPENSEARCH_NOFILE_SOFT=65536
OPENSEARCH_NOFILE_HARD=65536

# ------------------------------
# Environment Variables for Nginx reverse proxy
# ------------------------------
NGINX_SERVER_NAME=_
NGINX_HTTPS_ENABLED=false
# HTTP port
NGINX_PORT=80
# SSL settings are only applied when HTTPS_ENABLED is true
NGINX_SSL_PORT=443
# if HTTPS_ENABLED is true, you're required to add your own SSL certificates/keys to the `./nginx/ssl` directory
# and modify the env vars below accordingly.
NGINX_SSL_CERT_FILENAME=dify.crt
NGINX_SSL_CERT_KEY_FILENAME=dify.key
NGINX_SSL_PROTOCOLS=TLSv1.1 TLSv1.2 TLSv1.3

# Nginx performance tuning
NGINX_WORKER_PROCESSES=auto
NGINX_CLIENT_MAX_BODY_SIZE=100M
NGINX_KEEPALIVE_TIMEOUT=65

# Proxy settings
NGINX_PROXY_READ_TIMEOUT=3600s
NGINX_PROXY_SEND_TIMEOUT=3600s

# Set true to accept requests for /.well-known/acme-challenge/
NGINX_ENABLE_CERTBOT_CHALLENGE=false

# ------------------------------
# Certbot Configuration
# ------------------------------

# Email address (required to get certificates from Let's Encrypt)
[email protected]

# Domain name
CERTBOT_DOMAIN=your_domain.com

# certbot command options
# i.e: --force-renewal --dry-run --test-cert --debug
CERTBOT_OPTIONS=

# ------------------------------
# Environment Variables for SSRF Proxy
# ------------------------------
SSRF_HTTP_PORT=3128
SSRF_COREDUMP_DIR=/var/spool/squid
SSRF_REVERSE_PROXY_PORT=8194
SSRF_SANDBOX_HOST=sandbox
SSRF_DEFAULT_TIME_OUT=5
SSRF_DEFAULT_CONNECT_TIME_OUT=5
SSRF_DEFAULT_READ_TIME_OUT=5
SSRF_DEFAULT_WRITE_TIME_OUT=5

# ------------------------------
# docker env var for specifying vector db type at startup
# (based on the vector db type, the corresponding docker
# compose profile will be used)
# if you want to use unstructured, add ',unstructured' to the end
# ------------------------------
COMPOSE_PROFILES=${VECTOR_STORE:-weaviate}

# ------------------------------
# Docker Compose Service Expose Host Port Configurations
# ------------------------------
EXPOSE_NGINX_PORT=80
EXPOSE_NGINX_SSL_PORT=443

# ----------------------------------------------------------------------------
# ModelProvider & Tool Position Configuration
# Used to specify the model providers and tools that can be used in the app.
# ----------------------------------------------------------------------------

# Pin, include, and exclude tools
# Use comma-separated values with no spaces between items.
# Example: POSITION_TOOL_PINS=bing,google
POSITION_TOOL_PINS=
POSITION_TOOL_INCLUDES=
POSITION_TOOL_EXCLUDES=

# Pin, include, and exclude model providers
# Use comma-separated values with no spaces between items.
# Example: POSITION_PROVIDER_PINS=openai,openllm
POSITION_PROVIDER_PINS=
POSITION_PROVIDER_INCLUDES=
POSITION_PROVIDER_EXCLUDES=

# CSP https://developer.mozilla.org/en-US/docs/Web/HTTP/CSP
CSP_WHITELIST=

# Enable or disable create tidb service job
CREATE_TIDB_SERVICE_JOB_ENABLED=false

# Maximum number of submitted thread count in a ThreadPool for parallel node execution
MAX_SUBMIT_COUNT=100

# The maximum number of top-k value for RAG.
TOP_K_MAX_VALUE=10

# ------------------------------
# Plugin Daemon Configuration
# ------------------------------

DB_PLUGIN_DATABASE=dify_plugin
EXPOSE_PLUGIN_DAEMON_PORT=5002
PLUGIN_DAEMON_PORT=5002
PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
PLUGIN_DAEMON_URL=http://plugin_daemon:5002
PLUGIN_MAX_PACKAGE_SIZE=52428800
PLUGIN_PPROF_ENABLED=false

PLUGIN_DEBUGGING_HOST=0.0.0.0
PLUGIN_DEBUGGING_PORT=5003
EXPOSE_PLUGIN_DEBUGGING_HOST=localhost
EXPOSE_PLUGIN_DEBUGGING_PORT=5003

# If this key is changed, DIFY_INNER_API_KEY in plugin_daemon service must also be updated or agent node will fail.
PLUGIN_DIFY_INNER_API_KEY=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1
PLUGIN_DIFY_INNER_API_URL=http://api:5001

ENDPOINT_URL_TEMPLATE=http://localhost/e/{hook_id}

MARKETPLACE_ENABLED=true
MARKETPLACE_API_URL=https://marketplace.dify.ai

FORCE_VERIFYING_SIGNATURE=true

PLUGIN_STDIO_BUFFER_SIZE=1024
PLUGIN_STDIO_MAX_BUFFER_SIZE=5242880

PLUGIN_PYTHON_ENV_INIT_TIMEOUT=120
PLUGIN_MAX_EXECUTION_TIMEOUT=600
# PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple
PIP_MIRROR_URL=

# https://github.com/langgenius/dify-plugin-daemon/blob/main/.env.example
# Plugin storage type, local aws_s3 tencent_cos azure_blob aliyun_oss volcengine_tos
PLUGIN_STORAGE_TYPE=local
PLUGIN_STORAGE_LOCAL_ROOT=/app/storage
PLUGIN_WORKING_PATH=/app/storage/cwd
PLUGIN_INSTALLED_PATH=plugin
PLUGIN_PACKAGE_CACHE_PATH=plugin_packages
PLUGIN_MEDIA_CACHE_PATH=assets
# Plugin oss bucket
PLUGIN_STORAGE_OSS_BUCKET=
# Plugin oss s3 credentials
PLUGIN_S3_USE_AWS=false
PLUGIN_S3_USE_AWS_MANAGED_IAM=false
PLUGIN_S3_ENDPOINT=
PLUGIN_S3_USE_PATH_STYLE=false
PLUGIN_AWS_ACCESS_KEY=
PLUGIN_AWS_SECRET_KEY=
PLUGIN_AWS_REGION=
# Plugin oss azure blob
PLUGIN_AZURE_BLOB_STORAGE_CONTAINER_NAME=
PLUGIN_AZURE_BLOB_STORAGE_CONNECTION_STRING=
# Plugin oss tencent cos
PLUGIN_TENCENT_COS_SECRET_KEY=
PLUGIN_TENCENT_COS_SECRET_ID=
PLUGIN_TENCENT_COS_REGION=
# Plugin oss aliyun oss
PLUGIN_ALIYUN_OSS_REGION=
PLUGIN_ALIYUN_OSS_ENDPOINT=
PLUGIN_ALIYUN_OSS_ACCESS_KEY_ID=
PLUGIN_ALIYUN_OSS_ACCESS_KEY_SECRET=
PLUGIN_ALIYUN_OSS_AUTH_VERSION=v4
PLUGIN_ALIYUN_OSS_PATH=
# Plugin oss volcengine tos
PLUGIN_VOLCENGINE_TOS_ENDPOINT=
PLUGIN_VOLCENGINE_TOS_ACCESS_KEY=
PLUGIN_VOLCENGINE_TOS_SECRET_KEY=
PLUGIN_VOLCENGINE_TOS_REGION=

# ------------------------------
# OTLP Collector Configuration
# ------------------------------
ENABLE_OTEL=false
OTLP_TRACE_ENDPOINT=
OTLP_METRIC_ENDPOINT=
OTLP_BASE_ENDPOINT=http://localhost:4318
OTLP_API_KEY=
OTEL_EXPORTER_OTLP_PROTOCOL=
OTEL_EXPORTER_TYPE=otlp
OTEL_SAMPLING_RATE=0.1
OTEL_BATCH_EXPORT_SCHEDULE_DELAY=5000
OTEL_MAX_QUEUE_SIZE=2048
OTEL_MAX_EXPORT_BATCH_SIZE=512
OTEL_METRIC_EXPORT_INTERVAL=60000
OTEL_BATCH_EXPORT_TIMEOUT=10000
OTEL_METRIC_EXPORT_TIMEOUT=30000

# Prevent Clickjacking
ALLOW_EMBED=false

# Dataset queue monitor configuration
QUEUE_MONITOR_THRESHOLD=200
# You can configure multiple ones, separated by commas. eg: [email protected],[email protected]
QUEUE_MONITOR_ALERT_EMAILS=
# Monitor interval in minutes, default is 30 minutes
QUEUE_MONITOR_INTERVAL=30

# Swagger UI configuration
SWAGGER_UI_ENABLED=true
SWAGGER_UI_PATH=/swagger-ui.html

# Celery schedule tasks configuration
ENABLE_CLEAN_EMBEDDING_CACHE_TASK=false
ENABLE_CLEAN_UNUSED_DATASETS_TASK=false
ENABLE_CREATE_TIDB_SERVERLESS_TASK=false
ENABLE_UPDATE_TIDB_SERVERLESS_STATUS_TASK=false
ENABLE_CLEAN_MESSAGES=false
ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK=false
ENABLE_DATASETS_QUEUE_MONITOR=false
ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK=true

太长了，其实很多都可以安装好之后，我们慢慢配置的，这边先无视它……

然后处于好奇，我们来看一下它的docker-compose.yml文件

# ==================================================================
# WARNING: This file is auto-generated by generate_docker_compose
# Do not modify this file directly. Instead, update the .env.example
# or docker-compose-template.yaml and regenerate this file.
# ==================================================================

x-shared-env: &shared-api-worker-env
  CONSOLE_API_URL: ${CONSOLE_API_URL:-}
  CONSOLE_WEB_URL: ${CONSOLE_WEB_URL:-}
  SERVICE_API_URL: ${SERVICE_API_URL:-}
  APP_API_URL: ${APP_API_URL:-}
  APP_WEB_URL: ${APP_WEB_URL:-}
  FILES_URL: ${FILES_URL:-}
  INTERNAL_FILES_URL: ${INTERNAL_FILES_URL:-}
  LANG: ${LANG:-en_US.UTF-8}
  LC_ALL: ${LC_ALL:-en_US.UTF-8}
  PYTHONIOENCODING: ${PYTHONIOENCODING:-utf-8}
  LOG_LEVEL: ${LOG_LEVEL:-INFO}
  LOG_FILE: ${LOG_FILE:-/app/logs/server.log}
  LOG_FILE_MAX_SIZE: ${LOG_FILE_MAX_SIZE:-20}
  LOG_FILE_BACKUP_COUNT: ${LOG_FILE_BACKUP_COUNT:-5}
  LOG_DATEFORMAT: ${LOG_DATEFORMAT:-%Y-%m-%d %H:%M:%S}
  LOG_TZ: ${LOG_TZ:-UTC}
  DEBUG: ${DEBUG:-false}
  FLASK_DEBUG: ${FLASK_DEBUG:-false}
  ENABLE_REQUEST_LOGGING: ${ENABLE_REQUEST_LOGGING:-False}
  SECRET_KEY: ${SECRET_KEY:-sk-9f73s3ljTXVcMT3Blb3ljTqtsKiGHXVcMT3BlbkFJLK7U}
  INIT_PASSWORD: ${INIT_PASSWORD:-}
  DEPLOY_ENV: ${DEPLOY_ENV:-PRODUCTION}
  CHECK_UPDATE_URL: ${CHECK_UPDATE_URL:-https://updates.dify.ai}
  OPENAI_API_BASE: ${OPENAI_API_BASE:-https://api.openai.com/v1}
  MIGRATION_ENABLED: ${MIGRATION_ENABLED:-true}
  FILES_ACCESS_TIMEOUT: ${FILES_ACCESS_TIMEOUT:-300}
  ACCESS_TOKEN_EXPIRE_MINUTES: ${ACCESS_TOKEN_EXPIRE_MINUTES:-60}
  REFRESH_TOKEN_EXPIRE_DAYS: ${REFRESH_TOKEN_EXPIRE_DAYS:-30}
  APP_MAX_ACTIVE_REQUESTS: ${APP_MAX_ACTIVE_REQUESTS:-0}
  APP_MAX_EXECUTION_TIME: ${APP_MAX_EXECUTION_TIME:-1200}
  DIFY_BIND_ADDRESS: ${DIFY_BIND_ADDRESS:-0.0.0.0}
  DIFY_PORT: ${DIFY_PORT:-5001}
  SERVER_WORKER_AMOUNT: ${SERVER_WORKER_AMOUNT:-1}
  SERVER_WORKER_CLASS: ${SERVER_WORKER_CLASS:-gevent}
  SERVER_WORKER_CONNECTIONS: ${SERVER_WORKER_CONNECTIONS:-10}
  CELERY_WORKER_CLASS: ${CELERY_WORKER_CLASS:-}
  GUNICORN_TIMEOUT: ${GUNICORN_TIMEOUT:-360}
  CELERY_WORKER_AMOUNT: ${CELERY_WORKER_AMOUNT:-}
  CELERY_AUTO_SCALE: ${CELERY_AUTO_SCALE:-false}
  CELERY_MAX_WORKERS: ${CELERY_MAX_WORKERS:-}
  CELERY_MIN_WORKERS: ${CELERY_MIN_WORKERS:-}
  API_TOOL_DEFAULT_CONNECT_TIMEOUT: ${API_TOOL_DEFAULT_CONNECT_TIMEOUT:-10}
  API_TOOL_DEFAULT_READ_TIMEOUT: ${API_TOOL_DEFAULT_READ_TIMEOUT:-60}
  ENABLE_WEBSITE_JINAREADER: ${ENABLE_WEBSITE_JINAREADER:-true}
  ENABLE_WEBSITE_FIRECRAWL: ${ENABLE_WEBSITE_FIRECRAWL:-true}
  ENABLE_WEBSITE_WATERCRAWL: ${ENABLE_WEBSITE_WATERCRAWL:-true}
  DB_USERNAME: ${DB_USERNAME:-postgres}
  DB_PASSWORD: ${DB_PASSWORD:-difyai123456}
  DB_HOST: ${DB_HOST:-db}
  DB_PORT: ${DB_PORT:-5432}
  DB_DATABASE: ${DB_DATABASE:-dify}
  SQLALCHEMY_POOL_SIZE: ${SQLALCHEMY_POOL_SIZE:-30}
  SQLALCHEMY_MAX_OVERFLOW: ${SQLALCHEMY_MAX_OVERFLOW:-10}
  SQLALCHEMY_POOL_RECYCLE: ${SQLALCHEMY_POOL_RECYCLE:-3600}
  SQLALCHEMY_ECHO: ${SQLALCHEMY_ECHO:-false}
  SQLALCHEMY_POOL_PRE_PING: ${SQLALCHEMY_POOL_PRE_PING:-false}
  SQLALCHEMY_POOL_USE_LIFO: ${SQLALCHEMY_POOL_USE_LIFO:-false}
  POSTGRES_MAX_CONNECTIONS: ${POSTGRES_MAX_CONNECTIONS:-100}
  POSTGRES_SHARED_BUFFERS: ${POSTGRES_SHARED_BUFFERS:-128MB}
  POSTGRES_WORK_MEM: ${POSTGRES_WORK_MEM:-4MB}
  POSTGRES_MAINTENANCE_WORK_MEM: ${POSTGRES_MAINTENANCE_WORK_MEM:-64MB}
  POSTGRES_EFFECTIVE_CACHE_SIZE: ${POSTGRES_EFFECTIVE_CACHE_SIZE:-4096MB}
  REDIS_HOST: ${REDIS_HOST:-redis}
  REDIS_PORT: ${REDIS_PORT:-6379}
  REDIS_USERNAME: ${REDIS_USERNAME:-}
  REDIS_PASSWORD: ${REDIS_PASSWORD:-difyai123456}
  REDIS_USE_SSL: ${REDIS_USE_SSL:-false}
  REDIS_SSL_CERT_REQS: ${REDIS_SSL_CERT_REQS:-CERT_NONE}
  REDIS_SSL_CA_CERTS: ${REDIS_SSL_CA_CERTS:-}
  REDIS_SSL_CERTFILE: ${REDIS_SSL_CERTFILE:-}
  REDIS_SSL_KEYFILE: ${REDIS_SSL_KEYFILE:-}
  REDIS_DB: ${REDIS_DB:-0}
  REDIS_USE_SENTINEL: ${REDIS_USE_SENTINEL:-false}
  REDIS_SENTINELS: ${REDIS_SENTINELS:-}
  REDIS_SENTINEL_SERVICE_NAME: ${REDIS_SENTINEL_SERVICE_NAME:-}
  REDIS_SENTINEL_USERNAME: ${REDIS_SENTINEL_USERNAME:-}
  REDIS_SENTINEL_PASSWORD: ${REDIS_SENTINEL_PASSWORD:-}
  REDIS_SENTINEL_SOCKET_TIMEOUT: ${REDIS_SENTINEL_SOCKET_TIMEOUT:-0.1}
  REDIS_USE_CLUSTERS: ${REDIS_USE_CLUSTERS:-false}
  REDIS_CLUSTERS: ${REDIS_CLUSTERS:-}
  REDIS_CLUSTERS_PASSWORD: ${REDIS_CLUSTERS_PASSWORD:-}
  CELERY_BROKER_URL: ${CELERY_BROKER_URL:-redis://:difyai123456@redis:6379/1}
  CELERY_BACKEND: ${CELERY_BACKEND:-redis}
  BROKER_USE_SSL: ${BROKER_USE_SSL:-false}
  CELERY_USE_SENTINEL: ${CELERY_USE_SENTINEL:-false}
  CELERY_SENTINEL_MASTER_NAME: ${CELERY_SENTINEL_MASTER_NAME:-}
  CELERY_SENTINEL_PASSWORD: ${CELERY_SENTINEL_PASSWORD:-}
  CELERY_SENTINEL_SOCKET_TIMEOUT: ${CELERY_SENTINEL_SOCKET_TIMEOUT:-0.1}
  WEB_API_CORS_ALLOW_ORIGINS: ${WEB_API_CORS_ALLOW_ORIGINS:-*}
  CONSOLE_CORS_ALLOW_ORIGINS: ${CONSOLE_CORS_ALLOW_ORIGINS:-*}
  STORAGE_TYPE: ${STORAGE_TYPE:-opendal}
  OPENDAL_SCHEME: ${OPENDAL_SCHEME:-fs}
  OPENDAL_FS_ROOT: ${OPENDAL_FS_ROOT:-storage}
  CLICKZETTA_VOLUME_TYPE: ${CLICKZETTA_VOLUME_TYPE:-user}
  CLICKZETTA_VOLUME_NAME: ${CLICKZETTA_VOLUME_NAME:-}
  CLICKZETTA_VOLUME_TABLE_PREFIX: ${CLICKZETTA_VOLUME_TABLE_PREFIX:-dataset_}
  CLICKZETTA_VOLUME_DIFY_PREFIX: ${CLICKZETTA_VOLUME_DIFY_PREFIX:-dify_km}
  S3_ENDPOINT: ${S3_ENDPOINT:-}
  S3_REGION: ${S3_REGION:-us-east-1}
  S3_BUCKET_NAME: ${S3_BUCKET_NAME:-difyai}
  S3_ACCESS_KEY: ${S3_ACCESS_KEY:-}
  S3_SECRET_KEY: ${S3_SECRET_KEY:-}
  S3_USE_AWS_MANAGED_IAM: ${S3_USE_AWS_MANAGED_IAM:-false}
  AZURE_BLOB_ACCOUNT_NAME: ${AZURE_BLOB_ACCOUNT_NAME:-difyai}
  AZURE_BLOB_ACCOUNT_KEY: ${AZURE_BLOB_ACCOUNT_KEY:-difyai}
  AZURE_BLOB_CONTAINER_NAME: ${AZURE_BLOB_CONTAINER_NAME:-difyai-container}
  AZURE_BLOB_ACCOUNT_URL: ${AZURE_BLOB_ACCOUNT_URL:-https://<your_account_name>.blob.core.windows.net}
  GOOGLE_STORAGE_BUCKET_NAME: ${GOOGLE_STORAGE_BUCKET_NAME:-your-bucket-name}
  GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: ${GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64:-}
  ALIYUN_OSS_BUCKET_NAME: ${ALIYUN_OSS_BUCKET_NAME:-your-bucket-name}
  ALIYUN_OSS_ACCESS_KEY: ${ALIYUN_OSS_ACCESS_KEY:-your-access-key}
  ALIYUN_OSS_SECRET_KEY: ${ALIYUN_OSS_SECRET_KEY:-your-secret-key}
  ALIYUN_OSS_ENDPOINT: ${ALIYUN_OSS_ENDPOINT:-https://oss-ap-southeast-1-internal.aliyuncs.com}
  ALIYUN_OSS_REGION: ${ALIYUN_OSS_REGION:-ap-southeast-1}
  ALIYUN_OSS_AUTH_VERSION: ${ALIYUN_OSS_AUTH_VERSION:-v4}
  ALIYUN_OSS_PATH: ${ALIYUN_OSS_PATH:-your-path}
  TENCENT_COS_BUCKET_NAME: ${TENCENT_COS_BUCKET_NAME:-your-bucket-name}
  TENCENT_COS_SECRET_KEY: ${TENCENT_COS_SECRET_KEY:-your-secret-key}
  TENCENT_COS_SECRET_ID: ${TENCENT_COS_SECRET_ID:-your-secret-id}
  TENCENT_COS_REGION: ${TENCENT_COS_REGION:-your-region}
  TENCENT_COS_SCHEME: ${TENCENT_COS_SCHEME:-your-scheme}
  OCI_ENDPOINT: ${OCI_ENDPOINT:-https://your-object-storage-namespace.compat.objectstorage.us-ashburn-1.oraclecloud.com}
  OCI_BUCKET_NAME: ${OCI_BUCKET_NAME:-your-bucket-name}
  OCI_ACCESS_KEY: ${OCI_ACCESS_KEY:-your-access-key}
  OCI_SECRET_KEY: ${OCI_SECRET_KEY:-your-secret-key}
  OCI_REGION: ${OCI_REGION:-us-ashburn-1}
  HUAWEI_OBS_BUCKET_NAME: ${HUAWEI_OBS_BUCKET_NAME:-your-bucket-name}
  HUAWEI_OBS_SECRET_KEY: ${HUAWEI_OBS_SECRET_KEY:-your-secret-key}
  HUAWEI_OBS_ACCESS_KEY: ${HUAWEI_OBS_ACCESS_KEY:-your-access-key}
  HUAWEI_OBS_SERVER: ${HUAWEI_OBS_SERVER:-your-server-url}
  VOLCENGINE_TOS_BUCKET_NAME: ${VOLCENGINE_TOS_BUCKET_NAME:-your-bucket-name}
  VOLCENGINE_TOS_SECRET_KEY: ${VOLCENGINE_TOS_SECRET_KEY:-your-secret-key}
  VOLCENGINE_TOS_ACCESS_KEY: ${VOLCENGINE_TOS_ACCESS_KEY:-your-access-key}
  VOLCENGINE_TOS_ENDPOINT: ${VOLCENGINE_TOS_ENDPOINT:-your-server-url}
  VOLCENGINE_TOS_REGION: ${VOLCENGINE_TOS_REGION:-your-region}
  BAIDU_OBS_BUCKET_NAME: ${BAIDU_OBS_BUCKET_NAME:-your-bucket-name}
  BAIDU_OBS_SECRET_KEY: ${BAIDU_OBS_SECRET_KEY:-your-secret-key}
  BAIDU_OBS_ACCESS_KEY: ${BAIDU_OBS_ACCESS_KEY:-your-access-key}
  BAIDU_OBS_ENDPOINT: ${BAIDU_OBS_ENDPOINT:-your-server-url}
  SUPABASE_BUCKET_NAME: ${SUPABASE_BUCKET_NAME:-your-bucket-name}
  SUPABASE_API_KEY: ${SUPABASE_API_KEY:-your-access-key}
  SUPABASE_URL: ${SUPABASE_URL:-your-server-url}
  VECTOR_STORE: ${VECTOR_STORE:-weaviate}
  VECTOR_INDEX_NAME_PREFIX: ${VECTOR_INDEX_NAME_PREFIX:-Vector_index}
  WEAVIATE_ENDPOINT: ${WEAVIATE_ENDPOINT:-http://weaviate:8080}
  WEAVIATE_API_KEY: ${WEAVIATE_API_KEY:-WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih}
  QDRANT_URL: ${QDRANT_URL:-http://qdrant:6333}
  QDRANT_API_KEY: ${QDRANT_API_KEY:-difyai123456}
  QDRANT_CLIENT_TIMEOUT: ${QDRANT_CLIENT_TIMEOUT:-20}
  QDRANT_GRPC_ENABLED: ${QDRANT_GRPC_ENABLED:-false}
  QDRANT_GRPC_PORT: ${QDRANT_GRPC_PORT:-6334}
  QDRANT_REPLICATION_FACTOR: ${QDRANT_REPLICATION_FACTOR:-1}
  MILVUS_URI: ${MILVUS_URI:-http://host.docker.internal:19530}
  MILVUS_DATABASE: ${MILVUS_DATABASE:-}
  MILVUS_TOKEN: ${MILVUS_TOKEN:-}
  MILVUS_USER: ${MILVUS_USER:-}
  MILVUS_PASSWORD: ${MILVUS_PASSWORD:-}
  MILVUS_ENABLE_HYBRID_SEARCH: ${MILVUS_ENABLE_HYBRID_SEARCH:-False}
  MILVUS_ANALYZER_PARAMS: ${MILVUS_ANALYZER_PARAMS:-}
  MYSCALE_HOST: ${MYSCALE_HOST:-myscale}
  MYSCALE_PORT: ${MYSCALE_PORT:-8123}
  MYSCALE_USER: ${MYSCALE_USER:-default}
  MYSCALE_PASSWORD: ${MYSCALE_PASSWORD:-}
  MYSCALE_DATABASE: ${MYSCALE_DATABASE:-dify}
  MYSCALE_FTS_PARAMS: ${MYSCALE_FTS_PARAMS:-}
  COUCHBASE_CONNECTION_STRING: ${COUCHBASE_CONNECTION_STRING:-couchbase://couchbase-server}
  COUCHBASE_USER: ${COUCHBASE_USER:-Administrator}
  COUCHBASE_PASSWORD: ${COUCHBASE_PASSWORD:-password}
  COUCHBASE_BUCKET_NAME: ${COUCHBASE_BUCKET_NAME:-Embeddings}
  COUCHBASE_SCOPE_NAME: ${COUCHBASE_SCOPE_NAME:-_default}
  PGVECTOR_HOST: ${PGVECTOR_HOST:-pgvector}
  PGVECTOR_PORT: ${PGVECTOR_PORT:-5432}
  PGVECTOR_USER: ${PGVECTOR_USER:-postgres}
  PGVECTOR_PASSWORD: ${PGVECTOR_PASSWORD:-difyai123456}
  PGVECTOR_DATABASE: ${PGVECTOR_DATABASE:-dify}
  PGVECTOR_MIN_CONNECTION: ${PGVECTOR_MIN_CONNECTION:-1}
  PGVECTOR_MAX_CONNECTION: ${PGVECTOR_MAX_CONNECTION:-5}
  PGVECTOR_PG_BIGM: ${PGVECTOR_PG_BIGM:-false}
  PGVECTOR_PG_BIGM_VERSION: ${PGVECTOR_PG_BIGM_VERSION:-1.2-20240606}
  VASTBASE_HOST: ${VASTBASE_HOST:-vastbase}
  VASTBASE_PORT: ${VASTBASE_PORT:-5432}
  VASTBASE_USER: ${VASTBASE_USER:-dify}
  VASTBASE_PASSWORD: ${VASTBASE_PASSWORD:-Difyai123456}
  VASTBASE_DATABASE: ${VASTBASE_DATABASE:-dify}
  VASTBASE_MIN_CONNECTION: ${VASTBASE_MIN_CONNECTION:-1}
  VASTBASE_MAX_CONNECTION: ${VASTBASE_MAX_CONNECTION:-5}
  PGVECTO_RS_HOST: ${PGVECTO_RS_HOST:-pgvecto-rs}
  PGVECTO_RS_PORT: ${PGVECTO_RS_PORT:-5432}
  PGVECTO_RS_USER: ${PGVECTO_RS_USER:-postgres}
  PGVECTO_RS_PASSWORD: ${PGVECTO_RS_PASSWORD:-difyai123456}
  PGVECTO_RS_DATABASE: ${PGVECTO_RS_DATABASE:-dify}
  ANALYTICDB_KEY_ID: ${ANALYTICDB_KEY_ID:-your-ak}
  ANALYTICDB_KEY_SECRET: ${ANALYTICDB_KEY_SECRET:-your-sk}
  ANALYTICDB_REGION_ID: ${ANALYTICDB_REGION_ID:-cn-hangzhou}
  ANALYTICDB_INSTANCE_ID: ${ANALYTICDB_INSTANCE_ID:-gp-ab123456}
  ANALYTICDB_ACCOUNT: ${ANALYTICDB_ACCOUNT:-testaccount}
  ANALYTICDB_PASSWORD: ${ANALYTICDB_PASSWORD:-testpassword}
  ANALYTICDB_NAMESPACE: ${ANALYTICDB_NAMESPACE:-dify}
  ANALYTICDB_NAMESPACE_PASSWORD: ${ANALYTICDB_NAMESPACE_PASSWORD:-difypassword}
  ANALYTICDB_HOST: ${ANALYTICDB_HOST:-gp-test.aliyuncs.com}
  ANALYTICDB_PORT: ${ANALYTICDB_PORT:-5432}
  ANALYTICDB_MIN_CONNECTION: ${ANALYTICDB_MIN_CONNECTION:-1}
  ANALYTICDB_MAX_CONNECTION: ${ANALYTICDB_MAX_CONNECTION:-5}
  TIDB_VECTOR_HOST: ${TIDB_VECTOR_HOST:-tidb}
  TIDB_VECTOR_PORT: ${TIDB_VECTOR_PORT:-4000}
  TIDB_VECTOR_USER: ${TIDB_VECTOR_USER:-}
  TIDB_VECTOR_PASSWORD: ${TIDB_VECTOR_PASSWORD:-}
  TIDB_VECTOR_DATABASE: ${TIDB_VECTOR_DATABASE:-dify}
  MATRIXONE_HOST: ${MATRIXONE_HOST:-matrixone}
  MATRIXONE_PORT: ${MATRIXONE_PORT:-6001}
  MATRIXONE_USER: ${MATRIXONE_USER:-dump}
  MATRIXONE_PASSWORD: ${MATRIXONE_PASSWORD:-111}
  MATRIXONE_DATABASE: ${MATRIXONE_DATABASE:-dify}
  TIDB_ON_QDRANT_URL: ${TIDB_ON_QDRANT_URL:-http://127.0.0.1}
  TIDB_ON_QDRANT_API_KEY: ${TIDB_ON_QDRANT_API_KEY:-dify}
  TIDB_ON_QDRANT_CLIENT_TIMEOUT: ${TIDB_ON_QDRANT_CLIENT_TIMEOUT:-20}
  TIDB_ON_QDRANT_GRPC_ENABLED: ${TIDB_ON_QDRANT_GRPC_ENABLED:-false}
  TIDB_ON_QDRANT_GRPC_PORT: ${TIDB_ON_QDRANT_GRPC_PORT:-6334}
  TIDB_PUBLIC_KEY: ${TIDB_PUBLIC_KEY:-dify}
  TIDB_PRIVATE_KEY: ${TIDB_PRIVATE_KEY:-dify}
  TIDB_API_URL: ${TIDB_API_URL:-http://127.0.0.1}
  TIDB_IAM_API_URL: ${TIDB_IAM_API_URL:-http://127.0.0.1}
  TIDB_REGION: ${TIDB_REGION:-regions/aws-us-east-1}
  TIDB_PROJECT_ID: ${TIDB_PROJECT_ID:-dify}
  TIDB_SPEND_LIMIT: ${TIDB_SPEND_LIMIT:-100}
  CHROMA_HOST: ${CHROMA_HOST:-127.0.0.1}
  CHROMA_PORT: ${CHROMA_PORT:-8000}
  CHROMA_TENANT: ${CHROMA_TENANT:-default_tenant}
  CHROMA_DATABASE: ${CHROMA_DATABASE:-default_database}
  CHROMA_AUTH_PROVIDER: ${CHROMA_AUTH_PROVIDER:-chromadb.auth.token_authn.TokenAuthClientProvider}
  CHROMA_AUTH_CREDENTIALS: ${CHROMA_AUTH_CREDENTIALS:-}
  ORACLE_USER: ${ORACLE_USER:-dify}
  ORACLE_PASSWORD: ${ORACLE_PASSWORD:-dify}
  ORACLE_DSN: ${ORACLE_DSN:-oracle:1521/FREEPDB1}
  ORACLE_CONFIG_DIR: ${ORACLE_CONFIG_DIR:-/app/api/storage/wallet}
  ORACLE_WALLET_LOCATION: ${ORACLE_WALLET_LOCATION:-/app/api/storage/wallet}
  ORACLE_WALLET_PASSWORD: ${ORACLE_WALLET_PASSWORD:-dify}
  ORACLE_IS_AUTONOMOUS: ${ORACLE_IS_AUTONOMOUS:-false}
  RELYT_HOST: ${RELYT_HOST:-db}
  RELYT_PORT: ${RELYT_PORT:-5432}
  RELYT_USER: ${RELYT_USER:-postgres}
  RELYT_PASSWORD: ${RELYT_PASSWORD:-difyai123456}
  RELYT_DATABASE: ${RELYT_DATABASE:-postgres}
  OPENSEARCH_HOST: ${OPENSEARCH_HOST:-opensearch}
  OPENSEARCH_PORT: ${OPENSEARCH_PORT:-9200}
  OPENSEARCH_SECURE: ${OPENSEARCH_SECURE:-true}
  OPENSEARCH_VERIFY_CERTS: ${OPENSEARCH_VERIFY_CERTS:-true}
  OPENSEARCH_AUTH_METHOD: ${OPENSEARCH_AUTH_METHOD:-basic}
  OPENSEARCH_USER: ${OPENSEARCH_USER:-admin}
  OPENSEARCH_PASSWORD: ${OPENSEARCH_PASSWORD:-admin}
  OPENSEARCH_AWS_REGION: ${OPENSEARCH_AWS_REGION:-ap-southeast-1}
  OPENSEARCH_AWS_SERVICE: ${OPENSEARCH_AWS_SERVICE:-aoss}
  TENCENT_VECTOR_DB_URL: ${TENCENT_VECTOR_DB_URL:-http://127.0.0.1}
  TENCENT_VECTOR_DB_API_KEY: ${TENCENT_VECTOR_DB_API_KEY:-dify}
  TENCENT_VECTOR_DB_TIMEOUT: ${TENCENT_VECTOR_DB_TIMEOUT:-30}
  TENCENT_VECTOR_DB_USERNAME: ${TENCENT_VECTOR_DB_USERNAME:-dify}
  TENCENT_VECTOR_DB_DATABASE: ${TENCENT_VECTOR_DB_DATABASE:-dify}
  TENCENT_VECTOR_DB_SHARD: ${TENCENT_VECTOR_DB_SHARD:-1}
  TENCENT_VECTOR_DB_REPLICAS: ${TENCENT_VECTOR_DB_REPLICAS:-2}
  TENCENT_VECTOR_DB_ENABLE_HYBRID_SEARCH: ${TENCENT_VECTOR_DB_ENABLE_HYBRID_SEARCH:-false}
  ELASTICSEARCH_HOST: ${ELASTICSEARCH_HOST:-0.0.0.0}
  ELASTICSEARCH_PORT: ${ELASTICSEARCH_PORT:-9200}
  ELASTICSEARCH_USERNAME: ${ELASTICSEARCH_USERNAME:-elastic}
  ELASTICSEARCH_PASSWORD: ${ELASTICSEARCH_PASSWORD:-elastic}
  KIBANA_PORT: ${KIBANA_PORT:-5601}
  ELASTICSEARCH_USE_CLOUD: ${ELASTICSEARCH_USE_CLOUD:-false}
  ELASTICSEARCH_CLOUD_URL: ${ELASTICSEARCH_CLOUD_URL:-YOUR-ELASTICSEARCH_CLOUD_URL}
  ELASTICSEARCH_API_KEY: ${ELASTICSEARCH_API_KEY:-YOUR-ELASTICSEARCH_API_KEY}
  ELASTICSEARCH_VERIFY_CERTS: ${ELASTICSEARCH_VERIFY_CERTS:-False}
  ELASTICSEARCH_CA_CERTS: ${ELASTICSEARCH_CA_CERTS:-}
  ELASTICSEARCH_REQUEST_TIMEOUT: ${ELASTICSEARCH_REQUEST_TIMEOUT:-100000}
  ELASTICSEARCH_RETRY_ON_TIMEOUT: ${ELASTICSEARCH_RETRY_ON_TIMEOUT:-True}
  ELASTICSEARCH_MAX_RETRIES: ${ELASTICSEARCH_MAX_RETRIES:-10}
  BAIDU_VECTOR_DB_ENDPOINT: ${BAIDU_VECTOR_DB_ENDPOINT:-http://127.0.0.1:5287}
  BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS: ${BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS:-30000}
  BAIDU_VECTOR_DB_ACCOUNT: ${BAIDU_VECTOR_DB_ACCOUNT:-root}
  BAIDU_VECTOR_DB_API_KEY: ${BAIDU_VECTOR_DB_API_KEY:-dify}
  BAIDU_VECTOR_DB_DATABASE: ${BAIDU_VECTOR_DB_DATABASE:-dify}
  BAIDU_VECTOR_DB_SHARD: ${BAIDU_VECTOR_DB_SHARD:-1}
  BAIDU_VECTOR_DB_REPLICAS: ${BAIDU_VECTOR_DB_REPLICAS:-3}
  VIKINGDB_ACCESS_KEY: ${VIKINGDB_ACCESS_KEY:-your-ak}
  VIKINGDB_SECRET_KEY: ${VIKINGDB_SECRET_KEY:-your-sk}
  VIKINGDB_REGION: ${VIKINGDB_REGION:-cn-shanghai}
  VIKINGDB_HOST: ${VIKINGDB_HOST:-api-vikingdb.xxx.volces.com}
  VIKINGDB_SCHEMA: ${VIKINGDB_SCHEMA:-http}
  VIKINGDB_CONNECTION_TIMEOUT: ${VIKINGDB_CONNECTION_TIMEOUT:-30}
  VIKINGDB_SOCKET_TIMEOUT: ${VIKINGDB_SOCKET_TIMEOUT:-30}
  LINDORM_URL: ${LINDORM_URL:-http://lindorm:30070}
  LINDORM_USERNAME: ${LINDORM_USERNAME:-lindorm}
  LINDORM_PASSWORD: ${LINDORM_PASSWORD:-lindorm}
  LINDORM_QUERY_TIMEOUT: ${LINDORM_QUERY_TIMEOUT:-1}
  OCEANBASE_VECTOR_HOST: ${OCEANBASE_VECTOR_HOST:-oceanbase}
  OCEANBASE_VECTOR_PORT: ${OCEANBASE_VECTOR_PORT:-2881}
  OCEANBASE_VECTOR_USER: ${OCEANBASE_VECTOR_USER:-root@test}
  OCEANBASE_VECTOR_PASSWORD: ${OCEANBASE_VECTOR_PASSWORD:-difyai123456}
  OCEANBASE_VECTOR_DATABASE: ${OCEANBASE_VECTOR_DATABASE:-test}
  OCEANBASE_CLUSTER_NAME: ${OCEANBASE_CLUSTER_NAME:-difyai}
  OCEANBASE_MEMORY_LIMIT: ${OCEANBASE_MEMORY_LIMIT:-6G}
  OCEANBASE_ENABLE_HYBRID_SEARCH: ${OCEANBASE_ENABLE_HYBRID_SEARCH:-false}
  OPENGAUSS_HOST: ${OPENGAUSS_HOST:-opengauss}
  OPENGAUSS_PORT: ${OPENGAUSS_PORT:-6600}
  OPENGAUSS_USER: ${OPENGAUSS_USER:-postgres}
  OPENGAUSS_PASSWORD: ${OPENGAUSS_PASSWORD:-Dify@123}
  OPENGAUSS_DATABASE: ${OPENGAUSS_DATABASE:-dify}
  OPENGAUSS_MIN_CONNECTION: ${OPENGAUSS_MIN_CONNECTION:-1}
  OPENGAUSS_MAX_CONNECTION: ${OPENGAUSS_MAX_CONNECTION:-5}
  OPENGAUSS_ENABLE_PQ: ${OPENGAUSS_ENABLE_PQ:-false}
  HUAWEI_CLOUD_HOSTS: ${HUAWEI_CLOUD_HOSTS:-https://127.0.0.1:9200}
  HUAWEI_CLOUD_USER: ${HUAWEI_CLOUD_USER:-admin}
  HUAWEI_CLOUD_PASSWORD: ${HUAWEI_CLOUD_PASSWORD:-admin}
  UPSTASH_VECTOR_URL: ${UPSTASH_VECTOR_URL:-https://xxx-vector.upstash.io}
  UPSTASH_VECTOR_TOKEN: ${UPSTASH_VECTOR_TOKEN:-dify}
  TABLESTORE_ENDPOINT: ${TABLESTORE_ENDPOINT:-https://instance-name.cn-hangzhou.ots.aliyuncs.com}
  TABLESTORE_INSTANCE_NAME: ${TABLESTORE_INSTANCE_NAME:-instance-name}
  TABLESTORE_ACCESS_KEY_ID: ${TABLESTORE_ACCESS_KEY_ID:-xxx}
  TABLESTORE_ACCESS_KEY_SECRET: ${TABLESTORE_ACCESS_KEY_SECRET:-xxx}
  TABLESTORE_NORMALIZE_FULLTEXT_BM25_SCORE: ${TABLESTORE_NORMALIZE_FULLTEXT_BM25_SCORE:-false}
  CLICKZETTA_USERNAME: ${CLICKZETTA_USERNAME:-}
  CLICKZETTA_PASSWORD: ${CLICKZETTA_PASSWORD:-}
  CLICKZETTA_INSTANCE: ${CLICKZETTA_INSTANCE:-}
  CLICKZETTA_SERVICE: ${CLICKZETTA_SERVICE:-api.clickzetta.com}
  CLICKZETTA_WORKSPACE: ${CLICKZETTA_WORKSPACE:-quick_start}
  CLICKZETTA_VCLUSTER: ${CLICKZETTA_VCLUSTER:-default_ap}
  CLICKZETTA_SCHEMA: ${CLICKZETTA_SCHEMA:-dify}
  CLICKZETTA_BATCH_SIZE: ${CLICKZETTA_BATCH_SIZE:-100}
  CLICKZETTA_ENABLE_INVERTED_INDEX: ${CLICKZETTA_ENABLE_INVERTED_INDEX:-true}
  CLICKZETTA_ANALYZER_TYPE: ${CLICKZETTA_ANALYZER_TYPE:-chinese}
  CLICKZETTA_ANALYZER_MODE: ${CLICKZETTA_ANALYZER_MODE:-smart}
  CLICKZETTA_VECTOR_DISTANCE_FUNCTION: ${CLICKZETTA_VECTOR_DISTANCE_FUNCTION:-cosine_distance}
  UPLOAD_FILE_SIZE_LIMIT: ${UPLOAD_FILE_SIZE_LIMIT:-15}
  UPLOAD_FILE_BATCH_LIMIT: ${UPLOAD_FILE_BATCH_LIMIT:-5}
  ETL_TYPE: ${ETL_TYPE:-dify}
  UNSTRUCTURED_API_URL: ${UNSTRUCTURED_API_URL:-}
  UNSTRUCTURED_API_KEY: ${UNSTRUCTURED_API_KEY:-}
  SCARF_NO_ANALYTICS: ${SCARF_NO_ANALYTICS:-true}
  PROMPT_GENERATION_MAX_TOKENS: ${PROMPT_GENERATION_MAX_TOKENS:-512}
  CODE_GENERATION_MAX_TOKENS: ${CODE_GENERATION_MAX_TOKENS:-1024}
  PLUGIN_BASED_TOKEN_COUNTING_ENABLED: ${PLUGIN_BASED_TOKEN_COUNTING_ENABLED:-false}
  MULTIMODAL_SEND_FORMAT: ${MULTIMODAL_SEND_FORMAT:-base64}
  UPLOAD_IMAGE_FILE_SIZE_LIMIT: ${UPLOAD_IMAGE_FILE_SIZE_LIMIT:-10}
  UPLOAD_VIDEO_FILE_SIZE_LIMIT: ${UPLOAD_VIDEO_FILE_SIZE_LIMIT:-100}
  UPLOAD_AUDIO_FILE_SIZE_LIMIT: ${UPLOAD_AUDIO_FILE_SIZE_LIMIT:-50}
  SENTRY_DSN: ${SENTRY_DSN:-}
  API_SENTRY_DSN: ${API_SENTRY_DSN:-}
  API_SENTRY_TRACES_SAMPLE_RATE: ${API_SENTRY_TRACES_SAMPLE_RATE:-1.0}
  API_SENTRY_PROFILES_SAMPLE_RATE: ${API_SENTRY_PROFILES_SAMPLE_RATE:-1.0}
  WEB_SENTRY_DSN: ${WEB_SENTRY_DSN:-}
  NOTION_INTEGRATION_TYPE: ${NOTION_INTEGRATION_TYPE:-public}
  NOTION_CLIENT_SECRET: ${NOTION_CLIENT_SECRET:-}
  NOTION_CLIENT_ID: ${NOTION_CLIENT_ID:-}
  NOTION_INTERNAL_SECRET: ${NOTION_INTERNAL_SECRET:-}
  MAIL_TYPE: ${MAIL_TYPE:-resend}
  MAIL_DEFAULT_SEND_FROM: ${MAIL_DEFAULT_SEND_FROM:-}
  RESEND_API_URL: ${RESEND_API_URL:-https://api.resend.com}
  RESEND_API_KEY: ${RESEND_API_KEY:-your-resend-api-key}
  SMTP_SERVER: ${SMTP_SERVER:-}
  SMTP_PORT: ${SMTP_PORT:-465}
  SMTP_USERNAME: ${SMTP_USERNAME:-}
  SMTP_PASSWORD: ${SMTP_PASSWORD:-}
  SMTP_USE_TLS: ${SMTP_USE_TLS:-true}
  SMTP_OPPORTUNISTIC_TLS: ${SMTP_OPPORTUNISTIC_TLS:-false}
  SENDGRID_API_KEY: ${SENDGRID_API_KEY:-}
  INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: ${INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH:-4000}
  INVITE_EXPIRY_HOURS: ${INVITE_EXPIRY_HOURS:-72}
  RESET_PASSWORD_TOKEN_EXPIRY_MINUTES: ${RESET_PASSWORD_TOKEN_EXPIRY_MINUTES:-5}
  CHANGE_EMAIL_TOKEN_EXPIRY_MINUTES: ${CHANGE_EMAIL_TOKEN_EXPIRY_MINUTES:-5}
  OWNER_TRANSFER_TOKEN_EXPIRY_MINUTES: ${OWNER_TRANSFER_TOKEN_EXPIRY_MINUTES:-5}
  CODE_EXECUTION_ENDPOINT: ${CODE_EXECUTION_ENDPOINT:-http://sandbox:8194}
  CODE_EXECUTION_API_KEY: ${CODE_EXECUTION_API_KEY:-dify-sandbox}
  CODE_MAX_NUMBER: ${CODE_MAX_NUMBER:-9223372036854775807}
  CODE_MIN_NUMBER: ${CODE_MIN_NUMBER:--9223372036854775808}
  CODE_MAX_DEPTH: ${CODE_MAX_DEPTH:-5}
  CODE_MAX_PRECISION: ${CODE_MAX_PRECISION:-20}
  CODE_MAX_STRING_LENGTH: ${CODE_MAX_STRING_LENGTH:-80000}
  CODE_MAX_STRING_ARRAY_LENGTH: ${CODE_MAX_STRING_ARRAY_LENGTH:-30}
  CODE_MAX_OBJECT_ARRAY_LENGTH: ${CODE_MAX_OBJECT_ARRAY_LENGTH:-30}
  CODE_MAX_NUMBER_ARRAY_LENGTH: ${CODE_MAX_NUMBER_ARRAY_LENGTH:-1000}
  CODE_EXECUTION_CONNECT_TIMEOUT: ${CODE_EXECUTION_CONNECT_TIMEOUT:-10}
  CODE_EXECUTION_READ_TIMEOUT: ${CODE_EXECUTION_READ_TIMEOUT:-60}
  CODE_EXECUTION_WRITE_TIMEOUT: ${CODE_EXECUTION_WRITE_TIMEOUT:-10}
  TEMPLATE_TRANSFORM_MAX_LENGTH: ${TEMPLATE_TRANSFORM_MAX_LENGTH:-80000}
  WORKFLOW_MAX_EXECUTION_STEPS: ${WORKFLOW_MAX_EXECUTION_STEPS:-500}
  WORKFLOW_MAX_EXECUTION_TIME: ${WORKFLOW_MAX_EXECUTION_TIME:-1200}
  WORKFLOW_CALL_MAX_DEPTH: ${WORKFLOW_CALL_MAX_DEPTH:-5}
  MAX_VARIABLE_SIZE: ${MAX_VARIABLE_SIZE:-204800}
  WORKFLOW_PARALLEL_DEPTH_LIMIT: ${WORKFLOW_PARALLEL_DEPTH_LIMIT:-3}
  WORKFLOW_FILE_UPLOAD_LIMIT: ${WORKFLOW_FILE_UPLOAD_LIMIT:-10}
  WORKFLOW_NODE_EXECUTION_STORAGE: ${WORKFLOW_NODE_EXECUTION_STORAGE:-rdbms}
  CORE_WORKFLOW_EXECUTION_REPOSITORY: ${CORE_WORKFLOW_EXECUTION_REPOSITORY:-core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository}
  CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY: ${CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY:-core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository}
  API_WORKFLOW_RUN_REPOSITORY: ${API_WORKFLOW_RUN_REPOSITORY:-repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository}
  API_WORKFLOW_NODE_EXECUTION_REPOSITORY: ${API_WORKFLOW_NODE_EXECUTION_REPOSITORY:-repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository}
  WORKFLOW_LOG_CLEANUP_ENABLED: ${WORKFLOW_LOG_CLEANUP_ENABLED:-false}
  WORKFLOW_LOG_RETENTION_DAYS: ${WORKFLOW_LOG_RETENTION_DAYS:-30}
  WORKFLOW_LOG_CLEANUP_BATCH_SIZE: ${WORKFLOW_LOG_CLEANUP_BATCH_SIZE:-100}
  HTTP_REQUEST_NODE_MAX_BINARY_SIZE: ${HTTP_REQUEST_NODE_MAX_BINARY_SIZE:-10485760}
  HTTP_REQUEST_NODE_MAX_TEXT_SIZE: ${HTTP_REQUEST_NODE_MAX_TEXT_SIZE:-1048576}
  HTTP_REQUEST_NODE_SSL_VERIFY: ${HTTP_REQUEST_NODE_SSL_VERIFY:-True}
  RESPECT_XFORWARD_HEADERS_ENABLED: ${RESPECT_XFORWARD_HEADERS_ENABLED:-false}
  SSRF_PROXY_HTTP_URL: ${SSRF_PROXY_HTTP_URL:-http://ssrf_proxy:3128}
  SSRF_PROXY_HTTPS_URL: ${SSRF_PROXY_HTTPS_URL:-http://ssrf_proxy:3128}
  LOOP_NODE_MAX_COUNT: ${LOOP_NODE_MAX_COUNT:-100}
  MAX_TOOLS_NUM: ${MAX_TOOLS_NUM:-10}
  MAX_PARALLEL_LIMIT: ${MAX_PARALLEL_LIMIT:-10}
  MAX_ITERATIONS_NUM: ${MAX_ITERATIONS_NUM:-99}
  TEXT_GENERATION_TIMEOUT_MS: ${TEXT_GENERATION_TIMEOUT_MS:-60000}
  ALLOW_UNSAFE_DATA_SCHEME: ${ALLOW_UNSAFE_DATA_SCHEME:-false}
  MAX_TREE_DEPTH: ${MAX_TREE_DEPTH:-50}
  POSTGRES_USER: ${POSTGRES_USER:-${DB_USERNAME}}
  POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-${DB_PASSWORD}}
  POSTGRES_DB: ${POSTGRES_DB:-${DB_DATABASE}}
  PGDATA: ${PGDATA:-/var/lib/postgresql/data/pgdata}
  SANDBOX_API_KEY: ${SANDBOX_API_KEY:-dify-sandbox}
  SANDBOX_GIN_MODE: ${SANDBOX_GIN_MODE:-release}
  SANDBOX_WORKER_TIMEOUT: ${SANDBOX_WORKER_TIMEOUT:-15}
  SANDBOX_ENABLE_NETWORK: ${SANDBOX_ENABLE_NETWORK:-true}
  SANDBOX_HTTP_PROXY: ${SANDBOX_HTTP_PROXY:-http://ssrf_proxy:3128}
  SANDBOX_HTTPS_PROXY: ${SANDBOX_HTTPS_PROXY:-http://ssrf_proxy:3128}
  SANDBOX_PORT: ${SANDBOX_PORT:-8194}
  WEAVIATE_PERSISTENCE_DATA_PATH: ${WEAVIATE_PERSISTENCE_DATA_PATH:-/var/lib/weaviate}
  WEAVIATE_QUERY_DEFAULTS_LIMIT: ${WEAVIATE_QUERY_DEFAULTS_LIMIT:-25}
  WEAVIATE_AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: ${WEAVIATE_AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED:-true}
  WEAVIATE_DEFAULT_VECTORIZER_MODULE: ${WEAVIATE_DEFAULT_VECTORIZER_MODULE:-none}
  WEAVIATE_CLUSTER_HOSTNAME: ${WEAVIATE_CLUSTER_HOSTNAME:-node1}
  WEAVIATE_AUTHENTICATION_APIKEY_ENABLED: ${WEAVIATE_AUTHENTICATION_APIKEY_ENABLED:-true}
  WEAVIATE_AUTHENTICATION_APIKEY_ALLOWED_KEYS: ${WEAVIATE_AUTHENTICATION_APIKEY_ALLOWED_KEYS:-WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih}
  WEAVIATE_AUTHENTICATION_APIKEY_USERS: ${WEAVIATE_AUTHENTICATION_APIKEY_USERS:[email protected]}
  WEAVIATE_AUTHORIZATION_ADMINLIST_ENABLED: ${WEAVIATE_AUTHORIZATION_ADMINLIST_ENABLED:-true}
  WEAVIATE_AUTHORIZATION_ADMINLIST_USERS: ${WEAVIATE_AUTHORIZATION_ADMINLIST_USERS:[email protected]}
  CHROMA_SERVER_AUTHN_CREDENTIALS: ${CHROMA_SERVER_AUTHN_CREDENTIALS:-difyai123456}
  CHROMA_SERVER_AUTHN_PROVIDER: ${CHROMA_SERVER_AUTHN_PROVIDER:-chromadb.auth.token_authn.TokenAuthenticationServerProvider}
  CHROMA_IS_PERSISTENT: ${CHROMA_IS_PERSISTENT:-TRUE}
  ORACLE_PWD: ${ORACLE_PWD:-Dify123456}
  ORACLE_CHARACTERSET: ${ORACLE_CHARACTERSET:-AL32UTF8}
  ETCD_AUTO_COMPACTION_MODE: ${ETCD_AUTO_COMPACTION_MODE:-revision}
  ETCD_AUTO_COMPACTION_RETENTION: ${ETCD_AUTO_COMPACTION_RETENTION:-1000}
  ETCD_QUOTA_BACKEND_BYTES: ${ETCD_QUOTA_BACKEND_BYTES:-4294967296}
  ETCD_SNAPSHOT_COUNT: ${ETCD_SNAPSHOT_COUNT:-50000}
  MINIO_ACCESS_KEY: ${MINIO_ACCESS_KEY:-minioadmin}
  MINIO_SECRET_KEY: ${MINIO_SECRET_KEY:-minioadmin}
  ETCD_ENDPOINTS: ${ETCD_ENDPOINTS:-etcd:2379}
  MINIO_ADDRESS: ${MINIO_ADDRESS:-minio:9000}
  MILVUS_AUTHORIZATION_ENABLED: ${MILVUS_AUTHORIZATION_ENABLED:-true}
  PGVECTOR_PGUSER: ${PGVECTOR_PGUSER:-postgres}
  PGVECTOR_POSTGRES_PASSWORD: ${PGVECTOR_POSTGRES_PASSWORD:-difyai123456}
  PGVECTOR_POSTGRES_DB: ${PGVECTOR_POSTGRES_DB:-dify}
  PGVECTOR_PGDATA: ${PGVECTOR_PGDATA:-/var/lib/postgresql/data/pgdata}
  OPENSEARCH_DISCOVERY_TYPE: ${OPENSEARCH_DISCOVERY_TYPE:-single-node}
  OPENSEARCH_BOOTSTRAP_MEMORY_LOCK: ${OPENSEARCH_BOOTSTRAP_MEMORY_LOCK:-true}
  OPENSEARCH_JAVA_OPTS_MIN: ${OPENSEARCH_JAVA_OPTS_MIN:-512m}
  OPENSEARCH_JAVA_OPTS_MAX: ${OPENSEARCH_JAVA_OPTS_MAX:-1024m}
  OPENSEARCH_INITIAL_ADMIN_PASSWORD: ${OPENSEARCH_INITIAL_ADMIN_PASSWORD:-Qazwsxedc!@#123}
  OPENSEARCH_MEMLOCK_SOFT: ${OPENSEARCH_MEMLOCK_SOFT:--1}
  OPENSEARCH_MEMLOCK_HARD: ${OPENSEARCH_MEMLOCK_HARD:--1}
  OPENSEARCH_NOFILE_SOFT: ${OPENSEARCH_NOFILE_SOFT:-65536}
  OPENSEARCH_NOFILE_HARD: ${OPENSEARCH_NOFILE_HARD:-65536}
  NGINX_SERVER_NAME: ${NGINX_SERVER_NAME:-_}
  NGINX_HTTPS_ENABLED: ${NGINX_HTTPS_ENABLED:-false}
  NGINX_PORT: ${NGINX_PORT:-80}
  NGINX_SSL_PORT: ${NGINX_SSL_PORT:-443}
  NGINX_SSL_CERT_FILENAME: ${NGINX_SSL_CERT_FILENAME:-dify.crt}
  NGINX_SSL_CERT_KEY_FILENAME: ${NGINX_SSL_CERT_KEY_FILENAME:-dify.key}
  NGINX_SSL_PROTOCOLS: ${NGINX_SSL_PROTOCOLS:-TLSv1.1 TLSv1.2 TLSv1.3}
  NGINX_WORKER_PROCESSES: ${NGINX_WORKER_PROCESSES:-auto}
  NGINX_CLIENT_MAX_BODY_SIZE: ${NGINX_CLIENT_MAX_BODY_SIZE:-100M}
  NGINX_KEEPALIVE_TIMEOUT: ${NGINX_KEEPALIVE_TIMEOUT:-65}
  NGINX_PROXY_READ_TIMEOUT: ${NGINX_PROXY_READ_TIMEOUT:-3600s}
  NGINX_PROXY_SEND_TIMEOUT: ${NGINX_PROXY_SEND_TIMEOUT:-3600s}
  NGINX_ENABLE_CERTBOT_CHALLENGE: ${NGINX_ENABLE_CERTBOT_CHALLENGE:-false}
  CERTBOT_EMAIL: ${CERTBOT_EMAIL:[email protected]}
  CERTBOT_DOMAIN: ${CERTBOT_DOMAIN:-your_domain.com}
  CERTBOT_OPTIONS: ${CERTBOT_OPTIONS:-}
  SSRF_HTTP_PORT: ${SSRF_HTTP_PORT:-3128}
  SSRF_COREDUMP_DIR: ${SSRF_COREDUMP_DIR:-/var/spool/squid}
  SSRF_REVERSE_PROXY_PORT: ${SSRF_REVERSE_PROXY_PORT:-8194}
  SSRF_SANDBOX_HOST: ${SSRF_SANDBOX_HOST:-sandbox}
  SSRF_DEFAULT_TIME_OUT: ${SSRF_DEFAULT_TIME_OUT:-5}
  SSRF_DEFAULT_CONNECT_TIME_OUT: ${SSRF_DEFAULT_CONNECT_TIME_OUT:-5}
  SSRF_DEFAULT_READ_TIME_OUT: ${SSRF_DEFAULT_READ_TIME_OUT:-5}
  SSRF_DEFAULT_WRITE_TIME_OUT: ${SSRF_DEFAULT_WRITE_TIME_OUT:-5}
  EXPOSE_NGINX_PORT: ${EXPOSE_NGINX_PORT:-80}
  EXPOSE_NGINX_SSL_PORT: ${EXPOSE_NGINX_SSL_PORT:-443}
  POSITION_TOOL_PINS: ${POSITION_TOOL_PINS:-}
  POSITION_TOOL_INCLUDES: ${POSITION_TOOL_INCLUDES:-}
  POSITION_TOOL_EXCLUDES: ${POSITION_TOOL_EXCLUDES:-}
  POSITION_PROVIDER_PINS: ${POSITION_PROVIDER_PINS:-}
  POSITION_PROVIDER_INCLUDES: ${POSITION_PROVIDER_INCLUDES:-}
  POSITION_PROVIDER_EXCLUDES: ${POSITION_PROVIDER_EXCLUDES:-}
  CSP_WHITELIST: ${CSP_WHITELIST:-}
  CREATE_TIDB_SERVICE_JOB_ENABLED: ${CREATE_TIDB_SERVICE_JOB_ENABLED:-false}
  MAX_SUBMIT_COUNT: ${MAX_SUBMIT_COUNT:-100}
  TOP_K_MAX_VALUE: ${TOP_K_MAX_VALUE:-10}
  DB_PLUGIN_DATABASE: ${DB_PLUGIN_DATABASE:-dify_plugin}
  EXPOSE_PLUGIN_DAEMON_PORT: ${EXPOSE_PLUGIN_DAEMON_PORT:-5002}
  PLUGIN_DAEMON_PORT: ${PLUGIN_DAEMON_PORT:-5002}
  PLUGIN_DAEMON_KEY: ${PLUGIN_DAEMON_KEY:-lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi}
  PLUGIN_DAEMON_URL: ${PLUGIN_DAEMON_URL:-http://plugin_daemon:5002}
  PLUGIN_MAX_PACKAGE_SIZE: ${PLUGIN_MAX_PACKAGE_SIZE:-52428800}
  PLUGIN_PPROF_ENABLED: ${PLUGIN_PPROF_ENABLED:-false}
  PLUGIN_DEBUGGING_HOST: ${PLUGIN_DEBUGGING_HOST:-0.0.0.0}
  PLUGIN_DEBUGGING_PORT: ${PLUGIN_DEBUGGING_PORT:-5003}
  EXPOSE_PLUGIN_DEBUGGING_HOST: ${EXPOSE_PLUGIN_DEBUGGING_HOST:-localhost}
  EXPOSE_PLUGIN_DEBUGGING_PORT: ${EXPOSE_PLUGIN_DEBUGGING_PORT:-5003}
  PLUGIN_DIFY_INNER_API_KEY: ${PLUGIN_DIFY_INNER_API_KEY:-QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1}
  PLUGIN_DIFY_INNER_API_URL: ${PLUGIN_DIFY_INNER_API_URL:-http://api:5001}
  ENDPOINT_URL_TEMPLATE: ${ENDPOINT_URL_TEMPLATE:-http://localhost/e/{hook_id}}
  MARKETPLACE_ENABLED: ${MARKETPLACE_ENABLED:-true}
  MARKETPLACE_API_URL: ${MARKETPLACE_API_URL:-https://marketplace.dify.ai}
  FORCE_VERIFYING_SIGNATURE: ${FORCE_VERIFYING_SIGNATURE:-true}
  PLUGIN_STDIO_BUFFER_SIZE: ${PLUGIN_STDIO_BUFFER_SIZE:-1024}
  PLUGIN_STDIO_MAX_BUFFER_SIZE: ${PLUGIN_STDIO_MAX_BUFFER_SIZE:-5242880}
  PLUGIN_PYTHON_ENV_INIT_TIMEOUT: ${PLUGIN_PYTHON_ENV_INIT_TIMEOUT:-120}
  PLUGIN_MAX_EXECUTION_TIMEOUT: ${PLUGIN_MAX_EXECUTION_TIMEOUT:-600}
  PIP_MIRROR_URL: ${PIP_MIRROR_URL:-}
  PLUGIN_STORAGE_TYPE: ${PLUGIN_STORAGE_TYPE:-local}
  PLUGIN_STORAGE_LOCAL_ROOT: ${PLUGIN_STORAGE_LOCAL_ROOT:-/app/storage}
  PLUGIN_WORKING_PATH: ${PLUGIN_WORKING_PATH:-/app/storage/cwd}
  PLUGIN_INSTALLED_PATH: ${PLUGIN_INSTALLED_PATH:-plugin}
  PLUGIN_PACKAGE_CACHE_PATH: ${PLUGIN_PACKAGE_CACHE_PATH:-plugin_packages}
  PLUGIN_MEDIA_CACHE_PATH: ${PLUGIN_MEDIA_CACHE_PATH:-assets}
  PLUGIN_STORAGE_OSS_BUCKET: ${PLUGIN_STORAGE_OSS_BUCKET:-}
  PLUGIN_S3_USE_AWS: ${PLUGIN_S3_USE_AWS:-false}
  PLUGIN_S3_USE_AWS_MANAGED_IAM: ${PLUGIN_S3_USE_AWS_MANAGED_IAM:-false}
  PLUGIN_S3_ENDPOINT: ${PLUGIN_S3_ENDPOINT:-}
  PLUGIN_S3_USE_PATH_STYLE: ${PLUGIN_S3_USE_PATH_STYLE:-false}
  PLUGIN_AWS_ACCESS_KEY: ${PLUGIN_AWS_ACCESS_KEY:-}
  PLUGIN_AWS_SECRET_KEY: ${PLUGIN_AWS_SECRET_KEY:-}
  PLUGIN_AWS_REGION: ${PLUGIN_AWS_REGION:-}
  PLUGIN_AZURE_BLOB_STORAGE_CONTAINER_NAME: ${PLUGIN_AZURE_BLOB_STORAGE_CONTAINER_NAME:-}
  PLUGIN_AZURE_BLOB_STORAGE_CONNECTION_STRING: ${PLUGIN_AZURE_BLOB_STORAGE_CONNECTION_STRING:-}
  PLUGIN_TENCENT_COS_SECRET_KEY: ${PLUGIN_TENCENT_COS_SECRET_KEY:-}
  PLUGIN_TENCENT_COS_SECRET_ID: ${PLUGIN_TENCENT_COS_SECRET_ID:-}
  PLUGIN_TENCENT_COS_REGION: ${PLUGIN_TENCENT_COS_REGION:-}
  PLUGIN_ALIYUN_OSS_REGION: ${PLUGIN_ALIYUN_OSS_REGION:-}
  PLUGIN_ALIYUN_OSS_ENDPOINT: ${PLUGIN_ALIYUN_OSS_ENDPOINT:-}
  PLUGIN_ALIYUN_OSS_ACCESS_KEY_ID: ${PLUGIN_ALIYUN_OSS_ACCESS_KEY_ID:-}
  PLUGIN_ALIYUN_OSS_ACCESS_KEY_SECRET: ${PLUGIN_ALIYUN_OSS_ACCESS_KEY_SECRET:-}
  PLUGIN_ALIYUN_OSS_AUTH_VERSION: ${PLUGIN_ALIYUN_OSS_AUTH_VERSION:-v4}
  PLUGIN_ALIYUN_OSS_PATH: ${PLUGIN_ALIYUN_OSS_PATH:-}
  PLUGIN_VOLCENGINE_TOS_ENDPOINT: ${PLUGIN_VOLCENGINE_TOS_ENDPOINT:-}
  PLUGIN_VOLCENGINE_TOS_ACCESS_KEY: ${PLUGIN_VOLCENGINE_TOS_ACCESS_KEY:-}
  PLUGIN_VOLCENGINE_TOS_SECRET_KEY: ${PLUGIN_VOLCENGINE_TOS_SECRET_KEY:-}
  PLUGIN_VOLCENGINE_TOS_REGION: ${PLUGIN_VOLCENGINE_TOS_REGION:-}
  ENABLE_OTEL: ${ENABLE_OTEL:-false}
  OTLP_TRACE_ENDPOINT: ${OTLP_TRACE_ENDPOINT:-}
  OTLP_METRIC_ENDPOINT: ${OTLP_METRIC_ENDPOINT:-}
  OTLP_BASE_ENDPOINT: ${OTLP_BASE_ENDPOINT:-http://localhost:4318}
  OTLP_API_KEY: ${OTLP_API_KEY:-}
  OTEL_EXPORTER_OTLP_PROTOCOL: ${OTEL_EXPORTER_OTLP_PROTOCOL:-}
  OTEL_EXPORTER_TYPE: ${OTEL_EXPORTER_TYPE:-otlp}
  OTEL_SAMPLING_RATE: ${OTEL_SAMPLING_RATE:-0.1}
  OTEL_BATCH_EXPORT_SCHEDULE_DELAY: ${OTEL_BATCH_EXPORT_SCHEDULE_DELAY:-5000}
  OTEL_MAX_QUEUE_SIZE: ${OTEL_MAX_QUEUE_SIZE:-2048}
  OTEL_MAX_EXPORT_BATCH_SIZE: ${OTEL_MAX_EXPORT_BATCH_SIZE:-512}
  OTEL_METRIC_EXPORT_INTERVAL: ${OTEL_METRIC_EXPORT_INTERVAL:-60000}
  OTEL_BATCH_EXPORT_TIMEOUT: ${OTEL_BATCH_EXPORT_TIMEOUT:-10000}
  OTEL_METRIC_EXPORT_TIMEOUT: ${OTEL_METRIC_EXPORT_TIMEOUT:-30000}
  ALLOW_EMBED: ${ALLOW_EMBED:-false}
  QUEUE_MONITOR_THRESHOLD: ${QUEUE_MONITOR_THRESHOLD:-200}
  QUEUE_MONITOR_ALERT_EMAILS: ${QUEUE_MONITOR_ALERT_EMAILS:-}
  QUEUE_MONITOR_INTERVAL: ${QUEUE_MONITOR_INTERVAL:-30}
  SWAGGER_UI_ENABLED: ${SWAGGER_UI_ENABLED:-true}
  SWAGGER_UI_PATH: ${SWAGGER_UI_PATH:-/swagger-ui.html}
  ENABLE_CLEAN_EMBEDDING_CACHE_TASK: ${ENABLE_CLEAN_EMBEDDING_CACHE_TASK:-false}
  ENABLE_CLEAN_UNUSED_DATASETS_TASK: ${ENABLE_CLEAN_UNUSED_DATASETS_TASK:-false}
  ENABLE_CREATE_TIDB_SERVERLESS_TASK: ${ENABLE_CREATE_TIDB_SERVERLESS_TASK:-false}
  ENABLE_UPDATE_TIDB_SERVERLESS_STATUS_TASK: ${ENABLE_UPDATE_TIDB_SERVERLESS_STATUS_TASK:-false}
  ENABLE_CLEAN_MESSAGES: ${ENABLE_CLEAN_MESSAGES:-false}
  ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK: ${ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK:-false}
  ENABLE_DATASETS_QUEUE_MONITOR: ${ENABLE_DATASETS_QUEUE_MONITOR:-false}
  ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK: ${ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK:-true}

services:
  # API service
  api:
    image: langgenius/dify-api:1.8.0
    restart: always
    environment:
      # Use the shared environment variables.
      <<: *shared-api-worker-env
      # Startup mode, 'api' starts the API server.
      MODE: api
      SENTRY_DSN: ${API_SENTRY_DSN:-}
      SENTRY_TRACES_SAMPLE_RATE: ${API_SENTRY_TRACES_SAMPLE_RATE:-1.0}
      SENTRY_PROFILES_SAMPLE_RATE: ${API_SENTRY_PROFILES_SAMPLE_RATE:-1.0}
      PLUGIN_REMOTE_INSTALL_HOST: ${EXPOSE_PLUGIN_DEBUGGING_HOST:-localhost}
      PLUGIN_REMOTE_INSTALL_PORT: ${EXPOSE_PLUGIN_DEBUGGING_PORT:-5003}
      PLUGIN_MAX_PACKAGE_SIZE: ${PLUGIN_MAX_PACKAGE_SIZE:-52428800}
      INNER_API_KEY_FOR_PLUGIN: ${PLUGIN_DIFY_INNER_API_KEY:-QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1}
    depends_on:
      db:
        condition: service_healthy
      redis:
        condition: service_started
    volumes:
      # Mount the storage directory to the container, for storing user files.
      - ./volumes/app/storage:/app/api/storage
    networks:
      - ssrf_proxy_network
      - default

  # worker service
  # The Celery worker for processing the queue.
  worker:
    image: langgenius/dify-api:1.8.0
    restart: always
    environment:
      # Use the shared environment variables.
      <<: *shared-api-worker-env
      # Startup mode, 'worker' starts the Celery worker for processing the queue.
      MODE: worker
      SENTRY_DSN: ${API_SENTRY_DSN:-}
      SENTRY_TRACES_SAMPLE_RATE: ${API_SENTRY_TRACES_SAMPLE_RATE:-1.0}
      SENTRY_PROFILES_SAMPLE_RATE: ${API_SENTRY_PROFILES_SAMPLE_RATE:-1.0}
      PLUGIN_MAX_PACKAGE_SIZE: ${PLUGIN_MAX_PACKAGE_SIZE:-52428800}
      INNER_API_KEY_FOR_PLUGIN: ${PLUGIN_DIFY_INNER_API_KEY:-QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1}
    depends_on:
      db:
        condition: service_healthy
      redis:
        condition: service_started
    volumes:
      # Mount the storage directory to the container, for storing user files.
      - ./volumes/app/storage:/app/api/storage
    networks:
      - ssrf_proxy_network
      - default

  # worker_beat service
  # Celery beat for scheduling periodic tasks.
  worker_beat:
    image: langgenius/dify-api:1.8.0
    restart: always
    environment:
      # Use the shared environment variables.
      <<: *shared-api-worker-env
      # Startup mode, 'worker_beat' starts the Celery beat for scheduling periodic tasks.
      MODE: beat
    depends_on:
      db:
        condition: service_healthy
      redis:
        condition: service_started
    networks:
      - ssrf_proxy_network
      - default

  # Frontend web application.
  web:
    image: langgenius/dify-web:1.8.0
    restart: always
    environment:
      CONSOLE_API_URL: ${CONSOLE_API_URL:-}
      APP_API_URL: ${APP_API_URL:-}
      SENTRY_DSN: ${WEB_SENTRY_DSN:-}
      NEXT_TELEMETRY_DISABLED: ${NEXT_TELEMETRY_DISABLED:-0}
      TEXT_GENERATION_TIMEOUT_MS: ${TEXT_GENERATION_TIMEOUT_MS:-60000}
      CSP_WHITELIST: ${CSP_WHITELIST:-}
      ALLOW_EMBED: ${ALLOW_EMBED:-false}
      ALLOW_UNSAFE_DATA_SCHEME: ${ALLOW_UNSAFE_DATA_SCHEME:-false}
      MARKETPLACE_API_URL: ${MARKETPLACE_API_URL:-https://marketplace.dify.ai}
      MARKETPLACE_URL: ${MARKETPLACE_URL:-https://marketplace.dify.ai}
      TOP_K_MAX_VALUE: ${TOP_K_MAX_VALUE:-}
      INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: ${INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH:-}
      PM2_INSTANCES: ${PM2_INSTANCES:-2}
      LOOP_NODE_MAX_COUNT: ${LOOP_NODE_MAX_COUNT:-100}
      MAX_TOOLS_NUM: ${MAX_TOOLS_NUM:-10}
      MAX_PARALLEL_LIMIT: ${MAX_PARALLEL_LIMIT:-10}
      MAX_ITERATIONS_NUM: ${MAX_ITERATIONS_NUM:-99}
      MAX_TREE_DEPTH: ${MAX_TREE_DEPTH:-50}
      ENABLE_WEBSITE_JINAREADER: ${ENABLE_WEBSITE_JINAREADER:-true}
      ENABLE_WEBSITE_FIRECRAWL: ${ENABLE_WEBSITE_FIRECRAWL:-true}
      ENABLE_WEBSITE_WATERCRAWL: ${ENABLE_WEBSITE_WATERCRAWL:-true}
  # The postgres database.
  db:
    image: postgres:15-alpine
    restart: always
    environment:
      POSTGRES_USER: ${POSTGRES_USER:-postgres}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-difyai123456}
      POSTGRES_DB: ${POSTGRES_DB:-dify}
      PGDATA: ${PGDATA:-/var/lib/postgresql/data/pgdata}
    command: >
      postgres -c 'max_connections=${POSTGRES_MAX_CONNECTIONS:-100}'
               -c 'shared_buffers=${POSTGRES_SHARED_BUFFERS:-128MB}'
               -c 'work_mem=${POSTGRES_WORK_MEM:-4MB}'
               -c 'maintenance_work_mem=${POSTGRES_MAINTENANCE_WORK_MEM:-64MB}'
               -c 'effective_cache_size=${POSTGRES_EFFECTIVE_CACHE_SIZE:-4096MB}'
    volumes:
      - ./volumes/db/data:/var/lib/postgresql/data
    healthcheck:
      test: [ 'CMD', 'pg_isready', '-h', 'db', '-U', '${PGUSER:-postgres}', '-d', '${POSTGRES_DB:-dify}' ]
      interval: 1s
      timeout: 3s
      retries: 60

  # The redis cache.
  redis:
    image: redis:6-alpine
    restart: always
    environment:
      REDISCLI_AUTH: ${REDIS_PASSWORD:-difyai123456}
    volumes:
      # Mount the redis data directory to the container.
      - ./volumes/redis/data:/data
    # Set the redis password when startup redis server.
    command: redis-server --requirepass ${REDIS_PASSWORD:-difyai123456}
    healthcheck:
      test: [ 'CMD', 'redis-cli', 'ping' ]

  # The DifySandbox
  sandbox:
    image: langgenius/dify-sandbox:0.2.12
    restart: always
    environment:
      # The DifySandbox configurations
      # Make sure you are changing this key for your deployment with a strong key.
      # You can generate a strong key using `openssl rand -base64 42`.
      API_KEY: ${SANDBOX_API_KEY:-dify-sandbox}
      GIN_MODE: ${SANDBOX_GIN_MODE:-release}
      WORKER_TIMEOUT: ${SANDBOX_WORKER_TIMEOUT:-15}
      ENABLE_NETWORK: ${SANDBOX_ENABLE_NETWORK:-true}
      HTTP_PROXY: ${SANDBOX_HTTP_PROXY:-http://ssrf_proxy:3128}
      HTTPS_PROXY: ${SANDBOX_HTTPS_PROXY:-http://ssrf_proxy:3128}
      SANDBOX_PORT: ${SANDBOX_PORT:-8194}
      PIP_MIRROR_URL: ${PIP_MIRROR_URL:-}
    volumes:
      - ./volumes/sandbox/dependencies:/dependencies
      - ./volumes/sandbox/conf:/conf
    healthcheck:
      test: [ 'CMD', 'curl', '-f', 'http://localhost:8194/health' ]
    networks:
      - ssrf_proxy_network

  # plugin daemon
  plugin_daemon:
    image: langgenius/dify-plugin-daemon:0.2.0-local
    restart: always
    environment:
      # Use the shared environment variables.
      <<: *shared-api-worker-env
      DB_DATABASE: ${DB_PLUGIN_DATABASE:-dify_plugin}
      SERVER_PORT: ${PLUGIN_DAEMON_PORT:-5002}
      SERVER_KEY: ${PLUGIN_DAEMON_KEY:-lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi}
      MAX_PLUGIN_PACKAGE_SIZE: ${PLUGIN_MAX_PACKAGE_SIZE:-52428800}
      PPROF_ENABLED: ${PLUGIN_PPROF_ENABLED:-false}
      DIFY_INNER_API_URL: ${PLUGIN_DIFY_INNER_API_URL:-http://api:5001}
      DIFY_INNER_API_KEY: ${PLUGIN_DIFY_INNER_API_KEY:-QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1}
      PLUGIN_REMOTE_INSTALLING_HOST: ${PLUGIN_DEBUGGING_HOST:-0.0.0.0}
      PLUGIN_REMOTE_INSTALLING_PORT: ${PLUGIN_DEBUGGING_PORT:-5003}
      PLUGIN_WORKING_PATH: ${PLUGIN_WORKING_PATH:-/app/storage/cwd}
      FORCE_VERIFYING_SIGNATURE: ${FORCE_VERIFYING_SIGNATURE:-true}
      PYTHON_ENV_INIT_TIMEOUT: ${PLUGIN_PYTHON_ENV_INIT_TIMEOUT:-120}
      PLUGIN_MAX_EXECUTION_TIMEOUT: ${PLUGIN_MAX_EXECUTION_TIMEOUT:-600}
      PLUGIN_STDIO_BUFFER_SIZE: ${PLUGIN_STDIO_BUFFER_SIZE:-1024}
      PLUGIN_STDIO_MAX_BUFFER_SIZE: ${PLUGIN_STDIO_MAX_BUFFER_SIZE:-5242880}
      PIP_MIRROR_URL: ${PIP_MIRROR_URL:-}
      PLUGIN_STORAGE_TYPE: ${PLUGIN_STORAGE_TYPE:-local}
      PLUGIN_STORAGE_LOCAL_ROOT: ${PLUGIN_STORAGE_LOCAL_ROOT:-/app/storage}
      PLUGIN_INSTALLED_PATH: ${PLUGIN_INSTALLED_PATH:-plugin}
      PLUGIN_PACKAGE_CACHE_PATH: ${PLUGIN_PACKAGE_CACHE_PATH:-plugin_packages}
      PLUGIN_MEDIA_CACHE_PATH: ${PLUGIN_MEDIA_CACHE_PATH:-assets}
      PLUGIN_STORAGE_OSS_BUCKET: ${PLUGIN_STORAGE_OSS_BUCKET:-}
      S3_USE_AWS_MANAGED_IAM: ${PLUGIN_S3_USE_AWS_MANAGED_IAM:-false}
      S3_USE_AWS: ${PLUGIN_S3_USE_AWS:-false}
      S3_ENDPOINT: ${PLUGIN_S3_ENDPOINT:-}
      S3_USE_PATH_STYLE: ${PLUGIN_S3_USE_PATH_STYLE:-false}
      AWS_ACCESS_KEY: ${PLUGIN_AWS_ACCESS_KEY:-}
      AWS_SECRET_KEY: ${PLUGIN_AWS_SECRET_KEY:-}
      AWS_REGION: ${PLUGIN_AWS_REGION:-}
      AZURE_BLOB_STORAGE_CONNECTION_STRING: ${PLUGIN_AZURE_BLOB_STORAGE_CONNECTION_STRING:-}
      AZURE_BLOB_STORAGE_CONTAINER_NAME: ${PLUGIN_AZURE_BLOB_STORAGE_CONTAINER_NAME:-}
      TENCENT_COS_SECRET_KEY: ${PLUGIN_TENCENT_COS_SECRET_KEY:-}
      TENCENT_COS_SECRET_ID: ${PLUGIN_TENCENT_COS_SECRET_ID:-}
      TENCENT_COS_REGION: ${PLUGIN_TENCENT_COS_REGION:-}
      ALIYUN_OSS_REGION: ${PLUGIN_ALIYUN_OSS_REGION:-}
      ALIYUN_OSS_ENDPOINT: ${PLUGIN_ALIYUN_OSS_ENDPOINT:-}
      ALIYUN_OSS_ACCESS_KEY_ID: ${PLUGIN_ALIYUN_OSS_ACCESS_KEY_ID:-}
      ALIYUN_OSS_ACCESS_KEY_SECRET: ${PLUGIN_ALIYUN_OSS_ACCESS_KEY_SECRET:-}
      ALIYUN_OSS_AUTH_VERSION: ${PLUGIN_ALIYUN_OSS_AUTH_VERSION:-v4}
      ALIYUN_OSS_PATH: ${PLUGIN_ALIYUN_OSS_PATH:-}
      VOLCENGINE_TOS_ENDPOINT: ${PLUGIN_VOLCENGINE_TOS_ENDPOINT:-}
      VOLCENGINE_TOS_ACCESS_KEY: ${PLUGIN_VOLCENGINE_TOS_ACCESS_KEY:-}
      VOLCENGINE_TOS_SECRET_KEY: ${PLUGIN_VOLCENGINE_TOS_SECRET_KEY:-}
      VOLCENGINE_TOS_REGION: ${PLUGIN_VOLCENGINE_TOS_REGION:-}
    ports:
      - "${EXPOSE_PLUGIN_DEBUGGING_PORT:-5003}:${PLUGIN_DEBUGGING_PORT:-5003}"
    volumes:
      - ./volumes/plugin_daemon:/app/storage
    depends_on:
      db:
        condition: service_healthy

  # ssrf_proxy server
  # for more information, please refer to
  # https://docs.dify.ai/learn-more/faq/install-faq#18-why-is-ssrf-proxy-needed%3F
  ssrf_proxy:
    image: ubuntu/squid:latest
    restart: always
    volumes:
      - ./ssrf_proxy/squid.conf.template:/etc/squid/squid.conf.template
      - ./ssrf_proxy/docker-entrypoint.sh:/docker-entrypoint-mount.sh
    entrypoint: [ 'sh', '-c', "cp /docker-entrypoint-mount.sh /docker-entrypoint.sh && sed -i 's/\r$$//' /docker-entrypoint.sh && chmod +x /docker-entrypoint.sh && /docker-entrypoint.sh" ]
    environment:
      # pls clearly modify the squid env vars to fit your network environment.
      HTTP_PORT: ${SSRF_HTTP_PORT:-3128}
      COREDUMP_DIR: ${SSRF_COREDUMP_DIR:-/var/spool/squid}
      REVERSE_PROXY_PORT: ${SSRF_REVERSE_PROXY_PORT:-8194}
      SANDBOX_HOST: ${SSRF_SANDBOX_HOST:-sandbox}
      SANDBOX_PORT: ${SANDBOX_PORT:-8194}
    networks:
      - ssrf_proxy_network
      - default

  # Certbot service
  # use `docker-compose --profile certbot up` to start the certbot service.
  certbot:
    image: certbot/certbot
    profiles:
      - certbot
    volumes:
      - ./volumes/certbot/conf:/etc/letsencrypt
      - ./volumes/certbot/www:/var/www/html
      - ./volumes/certbot/logs:/var/log/letsencrypt
      - ./volumes/certbot/conf/live:/etc/letsencrypt/live
      - ./certbot/update-cert.template.txt:/update-cert.template.txt
      - ./certbot/docker-entrypoint.sh:/docker-entrypoint.sh
    environment:
      - CERTBOT_EMAIL=${CERTBOT_EMAIL}
      - CERTBOT_DOMAIN=${CERTBOT_DOMAIN}
      - CERTBOT_OPTIONS=${CERTBOT_OPTIONS:-}
    entrypoint: [ '/docker-entrypoint.sh' ]
    command: [ 'tail', '-f', '/dev/null' ]

  # The nginx reverse proxy.
  # used for reverse proxying the API service and Web service.
  nginx:
    image: nginx:latest
    restart: always
    volumes:
      - ./nginx/nginx.conf.template:/etc/nginx/nginx.conf.template
      - ./nginx/proxy.conf.template:/etc/nginx/proxy.conf.template
      - ./nginx/https.conf.template:/etc/nginx/https.conf.template
      - ./nginx/conf.d:/etc/nginx/conf.d
      - ./nginx/docker-entrypoint.sh:/docker-entrypoint-mount.sh
      - ./nginx/ssl:/etc/ssl # cert dir (legacy)
      - ./volumes/certbot/conf/live:/etc/letsencrypt/live # cert dir (with certbot container)
      - ./volumes/certbot/conf:/etc/letsencrypt
      - ./volumes/certbot/www:/var/www/html
    entrypoint: [ 'sh', '-c', "cp /docker-entrypoint-mount.sh /docker-entrypoint.sh && sed -i 's/\r$$//' /docker-entrypoint.sh && chmod +x /docker-entrypoint.sh && /docker-entrypoint.sh" ]
    environment:
      NGINX_SERVER_NAME: ${NGINX_SERVER_NAME:-_}
      NGINX_HTTPS_ENABLED: ${NGINX_HTTPS_ENABLED:-false}
      NGINX_SSL_PORT: ${NGINX_SSL_PORT:-443}
      NGINX_PORT: ${NGINX_PORT:-80}
      # You're required to add your own SSL certificates/keys to the `./nginx/ssl` directory
      # and modify the env vars below in .env if HTTPS_ENABLED is true.
      NGINX_SSL_CERT_FILENAME: ${NGINX_SSL_CERT_FILENAME:-dify.crt}
      NGINX_SSL_CERT_KEY_FILENAME: ${NGINX_SSL_CERT_KEY_FILENAME:-dify.key}
      NGINX_SSL_PROTOCOLS: ${NGINX_SSL_PROTOCOLS:-TLSv1.1 TLSv1.2 TLSv1.3}
      NGINX_WORKER_PROCESSES: ${NGINX_WORKER_PROCESSES:-auto}
      NGINX_CLIENT_MAX_BODY_SIZE: ${NGINX_CLIENT_MAX_BODY_SIZE:-100M}
      NGINX_KEEPALIVE_TIMEOUT: ${NGINX_KEEPALIVE_TIMEOUT:-65}
      NGINX_PROXY_READ_TIMEOUT: ${NGINX_PROXY_READ_TIMEOUT:-3600s}
      NGINX_PROXY_SEND_TIMEOUT: ${NGINX_PROXY_SEND_TIMEOUT:-3600s}
      NGINX_ENABLE_CERTBOT_CHALLENGE: ${NGINX_ENABLE_CERTBOT_CHALLENGE:-false}
      CERTBOT_DOMAIN: ${CERTBOT_DOMAIN:-}
    depends_on:
      - api
      - web
    ports:
      - '${EXPOSE_NGINX_PORT:-80}:${NGINX_PORT:-80}'
      - '${EXPOSE_NGINX_SSL_PORT:-443}:${NGINX_SSL_PORT:-443}'

  # The Weaviate vector store.
  weaviate:
    image: semitechnologies/weaviate:1.19.0
    profiles:
      - ''
      - weaviate
    restart: always
    volumes:
      # Mount the Weaviate data directory to the con tainer.
      - ./volumes/weaviate:/var/lib/weaviate
    environment:
      # The Weaviate configurations
      # You can refer to the [Weaviate](https://weaviate.io/developers/weaviate/config-refs/env-vars) documentation for more information.
      PERSISTENCE_DATA_PATH: ${WEAVIATE_PERSISTENCE_DATA_PATH:-/var/lib/weaviate}
      QUERY_DEFAULTS_LIMIT: ${WEAVIATE_QUERY_DEFAULTS_LIMIT:-25}
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: ${WEAVIATE_AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED:-false}
      DEFAULT_VECTORIZER_MODULE: ${WEAVIATE_DEFAULT_VECTORIZER_MODULE:-none}
      CLUSTER_HOSTNAME: ${WEAVIATE_CLUSTER_HOSTNAME:-node1}
      AUTHENTICATION_APIKEY_ENABLED: ${WEAVIATE_AUTHENTICATION_APIKEY_ENABLED:-true}
      AUTHENTICATION_APIKEY_ALLOWED_KEYS: ${WEAVIATE_AUTHENTICATION_APIKEY_ALLOWED_KEYS:-WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih}
      AUTHENTICATION_APIKEY_USERS: ${WEAVIATE_AUTHENTICATION_APIKEY_USERS:[email protected]}
      AUTHORIZATION_ADMINLIST_ENABLED: ${WEAVIATE_AUTHORIZATION_ADMINLIST_ENABLED:-true}
      AUTHORIZATION_ADMINLIST_USERS: ${WEAVIATE_AUTHORIZATION_ADMINLIST_USERS:[email protected]}

  # Qdrant vector store.
  # (if used, you need to set VECTOR_STORE to qdrant in the api & worker service.)
  qdrant:
    image: langgenius/qdrant:v1.7.3
    profiles:
      - qdrant
    restart: always
    volumes:
      - ./volumes/qdrant:/qdrant/storage
    environment:
      QDRANT_API_KEY: ${QDRANT_API_KEY:-difyai123456}

  # The Couchbase vector store.
  couchbase-server:
    build: ./couchbase-server
    profiles:
      - couchbase
    restart: always
    environment:
      - CLUSTER_NAME=dify_search
      - COUCHBASE_ADMINISTRATOR_USERNAME=${COUCHBASE_USER:-Administrator}
      - COUCHBASE_ADMINISTRATOR_PASSWORD=${COUCHBASE_PASSWORD:-password}
      - COUCHBASE_BUCKET=${COUCHBASE_BUCKET_NAME:-Embeddings}
      - COUCHBASE_BUCKET_RAMSIZE=512
      - COUCHBASE_RAM_SIZE=2048
      - COUCHBASE_EVENTING_RAM_SIZE=512
      - COUCHBASE_INDEX_RAM_SIZE=512
      - COUCHBASE_FTS_RAM_SIZE=1024
    hostname: couchbase-server
    container_name: couchbase-server
    working_dir: /opt/couchbase
    stdin_open: true
    tty: true
    entrypoint: [ "" ]
    command: sh -c "/opt/couchbase/init/init-cbserver.sh"
    volumes:
      - ./volumes/couchbase/data:/opt/couchbase/var/lib/couchbase/data
    healthcheck:
      # ensure bucket was created before proceeding
      test: [ "CMD-SHELL", "curl -s -f -u Administrator:password http://localhost:8091/pools/default/buckets | grep -q '\\[{' || exit 1" ]
      interval: 10s
      retries: 10
      start_period: 30s
      timeout: 10s

  # The pgvector vector database.
  pgvector:
    image: pgvector/pgvector:pg16
    profiles:
      - pgvector
    restart: always
    environment:
      PGUSER: ${PGVECTOR_PGUSER:-postgres}
      # The password for the default postgres user.
      POSTGRES_PASSWORD: ${PGVECTOR_POSTGRES_PASSWORD:-difyai123456}
      # The name of the default postgres database.
      POSTGRES_DB: ${PGVECTOR_POSTGRES_DB:-dify}
      # postgres data directory
      PGDATA: ${PGVECTOR_PGDATA:-/var/lib/postgresql/data/pgdata}
      # pg_bigm module for full text search
      PG_BIGM: ${PGVECTOR_PG_BIGM:-false}
      PG_BIGM_VERSION: ${PGVECTOR_PG_BIGM_VERSION:-1.2-20240606}
    volumes:
      - ./volumes/pgvector/data:/var/lib/postgresql/data
      - ./pgvector/docker-entrypoint.sh:/docker-entrypoint.sh
    entrypoint: [ '/docker-entrypoint.sh' ]
    healthcheck:
      test: [ 'CMD', 'pg_isready' ]
      interval: 1s
      timeout: 3s
      retries: 30

  # get image from https://www.vastdata.com.cn/
  vastbase:
    image: vastdata/vastbase-vector
    profiles:
      - vastbase
    restart: always
    environment:
      - VB_DBCOMPATIBILITY=PG
      - VB_DB=dify
      - VB_USERNAME=dify
      - VB_PASSWORD=Difyai123456
    ports:
      - '5434:5432'
    volumes:
      - ./vastbase/lic:/home/vastbase/vastbase/lic
      - ./vastbase/data:/home/vastbase/data
      - ./vastbase/backup:/home/vastbase/backup
      - ./vastbase/backup_log:/home/vastbase/backup_log
    healthcheck:
      test: [ 'CMD', 'pg_isready' ]
      interval: 1s
      timeout: 3s
      retries: 30

  # pgvecto-rs vector store
  pgvecto-rs:
    image: tensorchord/pgvecto-rs:pg16-v0.3.0
    profiles:
      - pgvecto-rs
    restart: always
    environment:
      PGUSER: ${PGVECTOR_PGUSER:-postgres}
      # The password for the default postgres user.
      POSTGRES_PASSWORD: ${PGVECTOR_POSTGRES_PASSWORD:-difyai123456}
      # The name of the default postgres database.
      POSTGRES_DB: ${PGVECTOR_POSTGRES_DB:-dify}
      # postgres data directory
      PGDATA: ${PGVECTOR_PGDATA:-/var/lib/postgresql/data/pgdata}
    volumes:
      - ./volumes/pgvecto_rs/data:/var/lib/postgresql/data
    healthcheck:
      test: [ 'CMD', 'pg_isready' ]
      interval: 1s
      timeout: 3s
      retries: 30

  # Chroma vector database
  chroma:
    image: ghcr.io/chroma-core/chroma:0.5.20
    profiles:
      - chroma
    restart: always
    volumes:
      - ./volumes/chroma:/chroma/chroma
    environment:
      CHROMA_SERVER_AUTHN_CREDENTIALS: ${CHROMA_SERVER_AUTHN_CREDENTIALS:-difyai123456}
      CHROMA_SERVER_AUTHN_PROVIDER: ${CHROMA_SERVER_AUTHN_PROVIDER:-chromadb.auth.token_authn.TokenAuthenticationServerProvider}
      IS_PERSISTENT: ${CHROMA_IS_PERSISTENT:-TRUE}

  # OceanBase vector database
  oceanbase:
    image: oceanbase/oceanbase-ce:4.3.5-lts
    container_name: oceanbase
    profiles:
      - oceanbase
    restart: always
    volumes:
      - ./volumes/oceanbase/data:/root/ob
      - ./volumes/oceanbase/conf:/root/.obd/cluster
      - ./volumes/oceanbase/init.d:/root/boot/init.d
    environment:
      OB_MEMORY_LIMIT: ${OCEANBASE_MEMORY_LIMIT:-6G}
      OB_SYS_PASSWORD: ${OCEANBASE_VECTOR_PASSWORD:-difyai123456}
      OB_TENANT_PASSWORD: ${OCEANBASE_VECTOR_PASSWORD:-difyai123456}
      OB_CLUSTER_NAME: ${OCEANBASE_CLUSTER_NAME:-difyai}
      OB_SERVER_IP: 127.0.0.1
      MODE: mini
    ports:
      - "${OCEANBASE_VECTOR_PORT:-2881}:2881"
    healthcheck:
      test: [ 'CMD-SHELL', 'obclient -h127.0.0.1 -P2881 -uroot@test -p$${OB_TENANT_PASSWORD} -e "SELECT 1;"' ]
      interval: 10s
      retries: 30
      start_period: 30s
      timeout: 10s

  # Oracle vector database
  oracle:
    image: container-registry.oracle.com/database/free:latest
    profiles:
      - oracle
    restart: always
    volumes:
      - source: oradata
        type: volume
        target: /opt/oracle/oradata
      - ./startupscripts:/opt/oracle/scripts/startup
    environment:
      ORACLE_PWD: ${ORACLE_PWD:-Dify123456}
      ORACLE_CHARACTERSET: ${ORACLE_CHARACTERSET:-AL32UTF8}

  # Milvus vector database services
  etcd:
    container_name: milvus-etcd
    image: quay.io/coreos/etcd:v3.5.5
    profiles:
      - milvus
    environment:
      ETCD_AUTO_COMPACTION_MODE: ${ETCD_AUTO_COMPACTION_MODE:-revision}
      ETCD_AUTO_COMPACTION_RETENTION: ${ETCD_AUTO_COMPACTION_RETENTION:-1000}
      ETCD_QUOTA_BACKEND_BYTES: ${ETCD_QUOTA_BACKEND_BYTES:-4294967296}
      ETCD_SNAPSHOT_COUNT: ${ETCD_SNAPSHOT_COUNT:-50000}
    volumes:
      - ./volumes/milvus/etcd:/etcd
    command: etcd -advertise-client-urls=http://127.0.0.1:2379 -listen-client-urls http://0.0.0.0:2379 --data-dir /etcd
    healthcheck:
      test: [ 'CMD', 'etcdctl', 'endpoint', 'health' ]
      interval: 30s
      timeout: 20s
      retries: 3
    networks:
      - milvus

  minio:
    container_name: milvus-minio
    image: minio/minio:RELEASE.2023-03-20T20-16-18Z
    profiles:
      - milvus
    environment:
      MINIO_ACCESS_KEY: ${MINIO_ACCESS_KEY:-minioadmin}
      MINIO_SECRET_KEY: ${MINIO_SECRET_KEY:-minioadmin}
    volumes:
      - ./volumes/milvus/minio:/minio_data
    command: minio server /minio_data --console-address ":9001"
    healthcheck:
      test: [ 'CMD', 'curl', '-f', 'http://localhost:9000/minio/health/live' ]
      interval: 30s
      timeout: 20s
      retries: 3
    networks:
      - milvus

  milvus-standalone:
    container_name: milvus-standalone
    image: milvusdb/milvus:v2.5.15
    profiles:
      - milvus
    command: [ 'milvus', 'run', 'standalone' ]
    environment:
      ETCD_ENDPOINTS: ${ETCD_ENDPOINTS:-etcd:2379}
      MINIO_ADDRESS: ${MINIO_ADDRESS:-minio:9000}
      common.security.authorizationEnabled: ${MILVUS_AUTHORIZATION_ENABLED:-true}
    volumes:
      - ./volumes/milvus/milvus:/var/lib/milvus
    healthcheck:
      test: [ 'CMD', 'curl', '-f', 'http://localhost:9091/healthz' ]
      interval: 30s
      start_period: 90s
      timeout: 20s
      retries: 3
    depends_on:
      - etcd
      - minio
    ports:
      - 19530:19530
      - 9091:9091
    networks:
      - milvus

  # Opensearch vector database
  opensearch:
    container_name: opensearch
    image: opensearchproject/opensearch:latest
    profiles:
      - opensearch
    environment:
      discovery.type: ${OPENSEARCH_DISCOVERY_TYPE:-single-node}
      bootstrap.memory_lock: ${OPENSEARCH_BOOTSTRAP_MEMORY_LOCK:-true}
      OPENSEARCH_JAVA_OPTS: -Xms${OPENSEARCH_JAVA_OPTS_MIN:-512m} -Xmx${OPENSEARCH_JAVA_OPTS_MAX:-1024m}
      OPENSEARCH_INITIAL_ADMIN_PASSWORD: ${OPENSEARCH_INITIAL_ADMIN_PASSWORD:-Qazwsxedc!@#123}
    ulimits:
      memlock:
        soft: ${OPENSEARCH_MEMLOCK_SOFT:--1}
        hard: ${OPENSEARCH_MEMLOCK_HARD:--1}
      nofile:
        soft: ${OPENSEARCH_NOFILE_SOFT:-65536}
        hard: ${OPENSEARCH_NOFILE_HARD:-65536}
    volumes:
      - ./volumes/opensearch/data:/usr/share/opensearch/data
    networks:
      - opensearch-net

  opensearch-dashboards:
    container_name: opensearch-dashboards
    image: opensearchproject/opensearch-dashboards:latest
    profiles:
      - opensearch
    environment:
      OPENSEARCH_HOSTS: '["https://opensearch:9200"]'
    volumes:
      - ./volumes/opensearch/opensearch_dashboards.yml:/usr/share/opensearch-dashboards/config/opensearch_dashboards.yml
    networks:
      - opensearch-net
    depends_on:
      - opensearch

  # opengauss vector database.
  opengauss:
    image: opengauss/opengauss:7.0.0-RC1
    profiles:
      - opengauss
    privileged: true
    restart: always
    environment:
      GS_USERNAME: ${OPENGAUSS_USER:-postgres}
      GS_PASSWORD: ${OPENGAUSS_PASSWORD:-Dify@123}
      GS_PORT: ${OPENGAUSS_PORT:-6600}
      GS_DB: ${OPENGAUSS_DATABASE:-dify}
    volumes:
      - ./volumes/opengauss/data:/var/lib/opengauss/data
    healthcheck:
      test: [ "CMD-SHELL", "netstat -lntp | grep tcp6 > /dev/null 2>&1" ]
      interval: 10s
      timeout: 10s
      retries: 10
    ports:
      - ${OPENGAUSS_PORT:-6600}:${OPENGAUSS_PORT:-6600}

  # MyScale vector database
  myscale:
    container_name: myscale
    image: myscale/myscaledb:1.6.4
    profiles:
      - myscale
    restart: always
    tty: true
    volumes:
      - ./volumes/myscale/data:/var/lib/clickhouse
      - ./volumes/myscale/log:/var/log/clickhouse-server
      - ./volumes/myscale/config/users.d/custom_users_config.xml:/etc/clickhouse-server/users.d/custom_users_config.xml
    ports:
      - ${MYSCALE_PORT:-8123}:${MYSCALE_PORT:-8123}

  # Matrixone vector store.
  matrixone:
    hostname: matrixone
    image: matrixorigin/matrixone:2.1.1
    profiles:
      - matrixone
    restart: always
    volumes:
      - ./volumes/matrixone/data:/mo-data
    ports:
      - ${MATRIXONE_PORT:-6001}:${MATRIXONE_PORT:-6001}

  # https://www.elastic.co/guide/en/elasticsearch/reference/current/settings.html
  # https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html#docker-prod-prerequisites
  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:8.14.3
    container_name: elasticsearch
    profiles:
      - elasticsearch
      - elasticsearch-ja
    restart: always
    volumes:
      - ./elasticsearch/docker-entrypoint.sh:/docker-entrypoint-mount.sh
      - dify_es01_data:/usr/share/elasticsearch/data
    environment:
      ELASTIC_PASSWORD: ${ELASTICSEARCH_PASSWORD:-elastic}
      VECTOR_STORE: ${VECTOR_STORE:-}
      cluster.name: dify-es-cluster
      node.name: dify-es0
      discovery.type: single-node
      xpack.license.self_generated.type: basic
      xpack.security.enabled: 'true'
      xpack.security.enrollment.enabled: 'false'
      xpack.security.http.ssl.enabled: 'false'
    ports:
      - ${ELASTICSEARCH_PORT:-9200}:9200
    deploy:
      resources:
        limits:
          memory: 2g
    entrypoint: [ 'sh', '-c', "sh /docker-entrypoint-mount.sh" ]
    healthcheck:
      test: [ 'CMD', 'curl', '-s', 'http://localhost:9200/_cluster/health?pretty' ]
      interval: 30s
      timeout: 10s
      retries: 50

  # https://www.elastic.co/guide/en/kibana/current/docker.html
  # https://www.elastic.co/guide/en/kibana/current/settings.html
  kibana:
    image: docker.elastic.co/kibana/kibana:8.14.3
    container_name: kibana
    profiles:
      - elasticsearch
    depends_on:
      - elasticsearch
    restart: always
    environment:
      XPACK_ENCRYPTEDSAVEDOBJECTS_ENCRYPTIONKEY: d1a66dfd-c4d3-4a0a-8290-2abcb83ab3aa
      NO_PROXY: localhost,127.0.0.1,elasticsearch,kibana
      XPACK_SECURITY_ENABLED: 'true'
      XPACK_SECURITY_ENROLLMENT_ENABLED: 'false'
      XPACK_SECURITY_HTTP_SSL_ENABLED: 'false'
      XPACK_FLEET_ISAIRGAPPED: 'true'
      I18N_LOCALE: zh-CN
      SERVER_PORT: '5601'
      ELASTICSEARCH_HOSTS: http://elasticsearch:9200
    ports:
      - ${KIBANA_PORT:-5601}:5601
    healthcheck:
      test: [ 'CMD-SHELL', 'curl -s http://localhost:5601 >/dev/null || exit 1' ]
      interval: 30s
      timeout: 10s
      retries: 3

  # unstructured .
  # (if used, you need to set ETL_TYPE to Unstructured in the api & worker service.)
  unstructured:
    image: downloads.unstructured.io/unstructured-io/unstructured-api:latest
    profiles:
      - unstructured
    restart: always
    volumes:
      - ./volumes/unstructured:/app/data

networks:
  # create a network between sandbox, api and ssrf_proxy, and can not access outside.
  ssrf_proxy_network:
    driver: bridge
    internal: true
  milvus:
    driver: bridge
  opensearch-net:
    driver: bridge
    internal: true

volumes:
  oradata:
  dify_es01_data:

其实一个一个分析，它的结构和我们之前部署的docker项目是类似的，只不过一次性起了很多个容器。

我们这边可以先不管它，直接暴力拉起

docker compose up -d

我这边在公司，本来以为很快能拉好镜像，结果网非常的慢，我等不及就去吃中饭了，等到吃饭回来发现已经拉好了。

在这期间，如果决定要本地使用，不调用云端API的话，我们可以先把Ollama和本地的模型先下载起来。

安装Ollama（可选）

其实这个也可以用docker来装，但是既然给了安装版，我们就直接到官网下载即可。

什么是Ollama？

Ollama 是一个便于本地部署和运行大型语言模型（Large Language Models, LLMs）的工具。使用通俗的语言来说，如果你想在自己的电脑上运行如 GPT这样的大型人工智能模型，而不是通过互联网连接到它们，那么 Ollama 是一个实现这一目标的工具。

Ollama支持非常多的开源模型，比如：

更多支持的模型可以看这边：https://ollama.com/library

当然它还支持自定义模型，这边就不深入了，有兴趣的可以研究：https://github.com/ollama/ollama

装好之后，命令行运行:

ollama -v

查看到版本号说明安装好了。

接下来，比如我们下载一个llama3 8B的模型：

ollama run llama3

这边可能需要比较长的时间，取决于你的网速。

下载好了就可以进行交互了：

/? 可以查看帮助：

/bye 可以退出

其实现在已经搞定了，你可以让它帮你干活了，但是每次都要用命令行，有些人觉得不方便，而且也不能给别人用，下面我们就给它搞一个图形化界面，扩展一下功能，也能让局域网里的其他小伙伴也用上你的这个模型（注意多人同时访问会导致机器负载飙升，具体取决于你机器的性能和模型参数的大小）

配置Dify

等所有容器都拉取好了，我们就可以通过在浏览器地址栏输入:127.0.0.1来访问Dify了。

第一次登录会让你注册一个管理员账号，然后我们就可以登录了，

后台是这个样子的，

我们先来到设置，配置一下大模型，

这边可以看到很多的模型供应商，

我们本地部署，就用ollama，

点击安装，

安装好了之后，来添加模型，

这里的基础URL，填写：http://host.docker.internal:11434

模型名称的话，看看我们ollama里下载了什么模型，打开终端，输入

ollama list

可以看到我这边下载了很多模型，

我们就选择gpt最近刚开源的gpt-oss:20b

其他信息填写如图，

这边是支持函数调用的，选择是，不支持视觉，

这样我们就添加好一个模型啦。

如果你的本地电脑算力不够，也可以选择使用云端的模型，比如DeepSeek之类的，

添加方法也很简单，下载模型供应商，然后在这边点击配置，

填入你在DeepSeek官网拿到的API Key就行了。

OpenAI、ANTHROPIC也是类似的方法，填API Key就可以。

接着，我们就来创建一个空白应用，

这边选择最简单的，创建一个聊天助手，

创建的过程中，你可以调试，这边的自定义程度会高一些，

创建好之后，可以选择发布，或者点击探索，

就可以在这边调出使用了。

当然，这只是最简单的功能，dify的魅力在于降低AI应用开发的门槛，快速构建和部署生产级的生成式AI应用

它通过以下核心功能来实现这个目标：

1. 简化开发流程：Dify是一个开源的大语言模型（LLM）应用开发平台，融合了后端即服务（BaaS）和LLMOps理念，提供可视化的Prompt编排、数据集管理、RAG（检索增强生成）引擎、Agent框架等功能，使开发者无需深入底层技术也能快速搭建AI应用。
2. 支持低代码/无代码开发：通过直观的界面和拖拽操作，非技术人员也能参与AI应用的定义和数据运营，极大地降低了开发门槛。
3. 灵活的模型支持：Dify支持多种主流大语言模型（如GPT、Claude、DeepSeek等）以及开源模型，开发者可根据需求灵活选择和切换模型。
4. 高效的RAG和Agent功能：Dify的RAG技术通过结合外部知识库提升生成内容的准确性，而Agent框架赋予AI自主推理和任务执行能力，适用于复杂场景如智能客服、内容生成等。189.html)
5. 企业级应用支持：Dify提供私有化部署、API集成、多租户隔离等功能，适合企业构建内部AI网关或快速将AI能力融入现有业务，助力AI转型。

总结来说，Dify通过提供一站式、易用的开发平台，帮助开发者、企业甚至非技术人员快速实现AI应用创意，节省开发时间，专注于创新和业务需求，特别适合从原型设计到生产部署的全流程管理。

大家可以自行探索一下Dify的高级玩法，我自己也在慢慢摸索学习，之后有机会可以和大家分享！

支持MCP，轻量又全面的记账软件——ezBookkeeping｜好玩儿的Docker项目

2025-08-12 20:36:51

前阵子去欧洲玩了一段时间，鸽了挺久了，今天有点时间，立马来和大家分享好玩儿的Docker项目。

1. 介绍

ezBookkeeping 是一款轻量级的个人理财应用，你可以自己架设（自托管）。它界面简洁，用起来很顺手，记账功能也强大。

这款应用的设计核心就是简单和便携。它部署起来毫不费力，上手快，而且对系统资源的占用极小。无论是微型服务器、NAS 设备，还是树莓派，都能轻松运行。

ezBookkeeping 支持全平台，对各种设备都很友好。在手机、平板和电脑上用，体验都一样流畅。它还支持 PWA（渐进式网页应用），你可以直接把它添加到手机主屏幕，像本地应用一样方便地使用。

1.1 功能特点

开源与自托管

• 为你提供隐私和数据控制权

轻量又快速

• 性能卓越，即使在低配置环境下也能流畅运行

安装简单

• 支持 Docker 部署
• 兼容 SQLite, MySQL, PostgreSQL 数据库
• 跨平台运行（支持 Windows, macOS, Linux）
• 支持多种处理器架构 (x86, amd64, ARM)

界面友好

• 界面已针对移动和桌面设备优化
• 支持 PWA，在手机上可获得类似原生应用的体验
• 提供深色模式

AI 赋能

• 支持 MCP (Model Context Protocol)，可集成 AI 功能

强大的记账功能

• 支持两级账户和分类
• 可为交易添加图片附件
• 具备地图位置追踪功能
• 支持周期性（重复）交易
• 提供高级筛选、搜索、数据可视化和分析功能

本地化与全球化

• 支持多种语言和货币
• 自动更新汇率
• 支持多时区显示
• 可自定义日期、数字和货币格式

安全保障

• 支持双重身份验证 (2FA)
• 登录频率限制
• 应用锁定功能（支持 PIN 码 / WebAuthn）

数据导入/导出

• 支持多种格式，包括 CSV, OFX, QFX, QIF, IIF, Camt.053, MT940, GnuCash, Firefly III, Beancount 等等

简单来说，这是一个记账的项目，然后它还可以支持MCP，可以搭配大语言模型一起食用。

2. 相关地址

官方GitHub地址：https://github.com/mayswind/ezbookkeeping (目前958个star，欢迎大家去给作者点星星！）

官方Demo：https://ezbookkeeping-demo.mayswind.net

3. 搭建环境

• 服务器：咕咕这边用的是莱卡云香港服务器，当然你也可以选择其他高性价比的服务器。内存1G以上即可，硬盘当然是越大越好啦。
• 系统：Debian 11 （DD 脚本 非必需 DD，用原来的系统也 OK，之后教程都是用 Debian 或者 Ubuntu 搭建～）
• 安装好 Docker、Docker-compose（相关脚本）
• 【必需】域名一枚，并做好解析到服务器上（域名购买、域名解析 视频教程）
• 【非必需】提前安装好宝塔面板海外版本 aapanel，并安装好 Nginx（安装地址）
• 【非必需本教程选用】安装好 Nginx Proxy Manager（相关教程）

4. 搭建视频（有时间补充！）

4.1 YouTube

视频地址：

4.2 哔哩哔哩

哔哩哔哩：

5. 搭建方式

5.1 安装 Docker 与 Nginx Proxy Manager

可以直接参考这篇内容：

https://blog.laoda.de/archives/nginxproxymanager/

5.2 创建安装目录

创建一下安装的目录：

sudo -i

mkdir -p /root/data/docker_data/ezbookkeeping

cd ezbookkeeping

我们来简单修改一下作者提供的docker-compose.yml文件

vim docker-compose.yml

咕咕修改之后的：

services:
  ezbookkeeping:
    image: mayswind/ezbookkeeping
    container_name: ezbookkeeping
    restart: unless-stopped
    ports:
      - 8082:8080
    volumes:
      - /etc/localtime:/etc/localtime:ro
      - ./storage:/ezbookkeeping/storage
      - ./log:/ezbookkeeping/log
    #  - ./ezbookkeeping.ini:/ezbookkeeping/conf/ezbookkeeping.ini
    environment:
      - EBK_DATABASE_TYPE=mysql
      - EBK_DATABASE_HOST=mysql:3306
      - EBK_DATABASE_NAME=ezbookkeeping
      - EBK_DATABASE_USER=ezbookkeeping
      - EBK_DATABASE_PASSWD=ezbookkeeping
      - EBK_LOG_MODE=file
      - EBK_SECURITY_SECRET_KEY=its_should_be_a_random_string
      - EBK_MCP_ENABLE_MCP=true
    # depends_on:
    #  mysql:
    #    condition: service_healthy

  mysql:  
    image: mysql:8.0 
    container_name: ezbookkeeping-mysql
    restart: unless-stopped
    volumes:  
        - ./data:/var/lib/mysql
    environment:  
        - MYSQL_DATABASE=ezbookkeeping  
        - MYSQL_USER=ezbookkeeping  
        - MYSQL_PASSWORD=ezbookkeeping  
        - MYSQL_ROOT_PASSWORD=ezbookkeeping
    healthcheck:  
        test: ["CMD", "mysqladmin", "ping", "-p ezbookkeeping"]  
        retries: 3  
        timeout: 5s

修改完成之后，可以在英文输入法下，按 i 修改，完成之后，按一下 esc，然后 :wq 保存退出。

接着创建文件夹，赋予文件权限：

cd /root/data/docker_data/ezbookkeeping
mkdir ./{data,log,storage}
chmod a+rw {log,storage}

5.3 打开服务器防火墙（非必需）并访问网页

打开防火墙的端口 8082

举例，腾讯云打开方法如下（部分服务商没有自带的面板防火墙，就不用这步操作了）：

类似图中的，这边我们填 8082，示例填 ezbookkeeping ，确定即可（如果你在 docker-compose 文件里换了 9009，这边就需要填 9009，以此类推）

查看端口是否被占用（以 8082 为例），输入：

lsof -i:8082  #查看 8082 端口是否被占用，如果被占用，重新自定义一个端口

如果啥也没出现，表示端口未被占用，我们可以继续下面的操作了～

如果出现：

-bash: lsof: command not found

运行：

apt install lsof  #安装 lsof

如果端口没有被占用（被占用了就修改一下端口，比如改成 8381，注意 docker 命令行里和防火墙都要改）

5.4 启动 ezbookkeeping

cd /root/data/docker_data/ezbookkeeping

docker compose up -d   # 注意，老版本用户用 docker-compose up -d

等待拉取好镜像，出现 done的字样之后，

理论上我们就可以输入 http://ip:8082 访问了。

但是这边我们推荐先搞一下反向代理！

做反向代理前，你需要一个域名！

namesilo 上面 xyz 后缀的域名一年就 7 块钱，可以年抛。（冷知识，namesilo上 6位数字的xyz续费永远都是0.99美元 = =）

如果想要长期使用，还是建议买 com 后缀的域名，更加正规一些，可以输入 laodade 来获得 1 美元的优惠（不知道现在还有没有）

namesilo 自带隐私保护，咕咕一直在用这家，价格也是这些注册商里面比较低的，关键是他家不像其他家域名注册商，没有七七八八的套路！（就是后台界面有些 丑 古老 = =）

【域名购买】Namesilo 优惠码和域名解析教程（附带服务器购买推荐和注意事项）

我们接着往下看！

6. 反向代理

6.1 利用 Nginx Proxy Manager

在添加反向代理之前，确保你已经完成了域名解析，不会的可以看这个：域名一枚，并做好解析到服务器上（域名购买、域名解析 视频教程）

之后，登陆 Nginx Proxy Manager（不会的看这个：安装 Nginx Proxy Manager（相关教程））

注意：

Nginx Proxy Manager（以下简称 NPM）会用到 80、443 端口，所以本机不能占用（比如原来就有 Nginx）

直接丢几张图：

注意填写对应的 域名、IP 和 端口，按文章来的话，应该是 8082

IP 填写：

如果 Nginx Proxy Manager 和 ezbookkeeping 在同一台服务器上，可以在终端输入：

ip addr show docker0

查看对应的 Docker 容器内部 IP。

否则直接填 ezbookkeeping 所在的服务器 IP 就行。

6.2 利用宝塔面板

发现还是有不少小伙伴习惯用宝塔面板，这边也贴一个宝塔面板的反代配置：

直接新建一个站点，不要数据库，不要 php，纯静态即可。

然后打开下面的配置，修改 Nginx 的配置。

代码如下：

location / {
      proxy_pass http://127.0.0.1:8082/;       # 注意改成你实际使用的端口
      rewrite ^/(.*)$ /$1 break;
      proxy_redirect off;
      proxy_set_header Host $host;
      proxy_set_header X-Forwarded-Proto $scheme;
      proxy_set_header X-Real-IP $remote_addr;
      proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
      proxy_set_header Upgrade-Insecure-Requests 1;
      proxy_set_header X-Forwarded-Proto https;
    }

此方法对 90% 的反向代理都能生效，然后就可以用域名来安装访问了。

有同学可能会问，为什么不直接用宝塔自带的反向代理功能。

也可以，不过咕咕自己之前遇到过当有多个网站需要反代的时候，在这边设置会报错的情况 = =

所以后来就不用了，直接用上面的方法来操作了。

7. 使用教程

登录你的域名之后，可以看到首页：

这个时候需要创建一个新账号：

这里的预设分类，可以选择打开：

进入后台，结构很清晰：

我们先来添加一下账户：

比如，取名就叫做“咕咕的账本”：

先来手动添加一笔试试看：

可以正常添加：

MCP配置

一开始我们就说了，这个账本支持MCP。

MCP（模型上下文协议）是由 Anthropic 开发的一种开放协议，它能让 AI 模型安全地连接到外部数据源和和工具。

简单来说，MCP 就像一座桥梁，它提供了一种通用的标准，让 AI 工具能安全地获取信息和执行操作，同时确保数据安全和用户可以掌控一切。

有了 MCP 协议，你就可以用自己喜欢的 AI 工具来：

• 添加交易记录：比如，直接用自然语言（就是日常说话的方式）来创建交易，或者从不同的文件格式中批量导入交易记录。
• 查询交易数据：比如，让你的 AI 工具帮你分析历史交易记录。
• 以及做更多的事情。

更多MCP相关介绍可以看这边：https://ezbookkeeping.mayswind.net/mcp

这边我们来看看怎么配置。

首先找到右上角的用户设置，

生成MCP令牌：

有两种形式，分别是普通的令牌和json配置：

普通：

eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VyVG9rZW5JZCI6IjMzOTQ1NTM3NTIyOTE5OTc4MzYiLCJqdGkiOiIzNzY4ODA2Njg4MjQ1NjbWUiOiJSb3kiLCJ0eXBlIjo1LCJpYXQiOjE3NTQ5ODc3NzcsImV4cCI6MTA5NzgzNTk4MTR9.7JL_4kzKhihatpfQxIkhD6Z_ibZ_vBYtcQ_D9UCV--0

JSON配置：

{
    "mcpServers": {
        "ezbookkeeping-mcp": {
            "type": "streamable-http",
            "url": "http://localhost:8080/mcp",
            "headers": {
                "Authorization": "Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VyVG9rZW5JZCI6IjMzOTQ1NTM3NTIyOTE5OTc4MzYiLCJqdGkiOiIzNzY4ODA2Njg4hbWUiOiJSb3kiLCJ0eXBlIjo1LCJpYXQiOjE3NTQ5ODc3NzcsImV4cCI6MTA5NzgzNTk4MTR9.7JL_4kzKhihatpfQxIkhD6Z_ibZ_vBYtcQ_D9UCV--0"
            }
        }
    }
}

这边可以保存下来，下次打开就看不到了。

Cherry Studio配置

这边以Cherry Studio为例，看看MCP怎么配置。

配置情况如图：

• 名称：主要用于识别，例如：ezBookkeeping
• 类型：选择 streamableHttp 协议
• URL：为 你的域名/mcp
• 请求头： 为 Authorization=Bearer {token}

接着可以查看一下可以调用的工具：

然后为了确保大模型能正确理解什么是今天，还需要加个时间MCP，这次我们选择json导入，

{
    "mcpServers": {
        "mcp-server-time": {
            "command": "uvx",
            "args": ["mcp-server-time"]
        }
    }
}

这下，你应该有两个MCP服务了。

查看一下时间工具的功能：

接着，我们到Cherry Studio里新建一个助手，

选择启用这两个MCP服务：

测试一下，可以看到回答的时候，调用了MCP服务，

这边提示错误，我没有说记录到哪个账本：

还需要说明交易类别，

后续，

记录成功！

不过这次似乎没有调用时间MCP，时间似乎有问题……

然后我尝试使用Deepseek，直接不调用MCP服务了，很奇怪。

后续一直没调用MCP服务，暂时还没解决，我的是Mac，有解决的小伙伴可以评论区分享一下。

7.1 更新 ezbookkeeping

cd /root/data/docker_data/ezbookkeeping

docker compose pull

docker compose up -d    # 请不要使用 docker compose stop 来停止容器，因为这么做需要额外的时间等待容器停止；docker compose up -d 直接升级容器时会自动停止并立刻重建新的容器，完全没有必要浪费那些时间。

docker image prune  # prune 命令用来删除不再使用的 docker 对象。删除所有未被 tag 标记和未被容器使用的镜像

提示：

WARNING! This will remove all dangling images.
Are you sure you want to continue? [y/N]

输入 y

利用 Docker 搭建的应用，更新非常容易～

7.2 卸载 ezbookkeeping

同样进入安装页面，先停止所有容器。

cd /root/data/docker_data/ezbookkeeping

docker compose down

cd ..

rm -rf /root/data/docker_data/ezbookkeeping  # 完全删除

可以卸载得很干净。

8. 常见问题及注意点

还是MCP调用的问题，不是非常稳定，暂时不确定是不是Cherry Studio的问题。

9. 结尾

祝大家用得开心，有问题可以去 GitHub 提 Issues，也可以在评论区互相交流探讨。

同时，项目处于初期，有能力给项目做贡献的同学，也欢迎积极加入到 [项目]https://github.com/mayswind/ezbookkeeping) 中来，贡献自己的一份力量！

最后，感谢开发人员们的辛苦付出，让我们能用到这么优秀的项目！也希望开源项目越来越好！

10. 参考资料

官方GitHub：https://github.com/mayswind/ezbookkeeping