@lobehub/chat 0.128.2 → 0.128.3

package/docs/self-hosting/deploy-with-azure-openai.mdx

@@ -0,0 +1,48 @@
+import { Callout } from 'nextra/components';
+
+# Integrating with Azure OpenAI
+
+LobeChat supports using [Azure OpenAI][azure-openai-url] as the model service provider for OpenAI. This article will explain how to configure Azure OpenAI.
+
+## Usage Limitations
+
+Due to development costs ([#178][rfc]), the current version of LobeChat does not fully comply with the implementation model of Azure OpenAI. Instead, it adopts a solution based on `openai` to be compatible with Azure OpenAI. As a result, the following limitations exist:
+
+- Only one of OpenAI and Azure OpenAI can be selected. Once you enable Azure OpenAI, you will not be able to use OpenAI as the model service provider.
+- LobeChat requires the deployment name to be the same as the model name in order to function properly. For example, the deployment name for the `gpt-35-turbo` model must be `gpt-35-turbo`. Otherwise, LobeChat will not be able to match the corresponding model correctly. ![](https://github-production-user-asset-6210df.s3.amazonaws.com/28616219/267082091-d89d53d3-1c8c-40ca-ba15-0a9af2a79264.png)
+- Due to the complexity of integrating with Azure OpenAI's SDK, it is currently not possible to query the list of configured models.
+
+## Configuring in the Interface
+
+Click in the bottom left corner "Actions" - "Settings", then switch to the "Language Model" tab and enable the "Azure OpenAI" switch to start using Azure OpenAI.
+
+![](https://github-production-user-asset-6210df.s3.amazonaws.com/28616219/267083420-422a3714-627e-4bef-9fbc-141a2a8ca916.png)
+
+You can fill in the corresponding configuration items as needed:
+
+- **API Key**: The API key you applied for on the Azure OpenAI account page, which can be found in the "Keys and Endpoints" section.
+- **API Address**: Azure API address, which can be found in the "Keys and Endpoints" section when checking resources in the Azure portal.
+- **Azure API Version**: The API version of Azure, following the format YYYY-MM-DD. Refer to the [latest version][azure-api-verion-url].
+
+After completing the configuration of the above fields, click "Check". If it prompts "Check passed", it means the configuration was successful.
+
+## Configuration during Deployment
+
+If you want the deployed version to be pre-configured with Azure OpenAI for end users to use directly, you need to configure the following environment variables during deployment:
+
+| Environment Variable | Type | Description | Default Value | Example |
+| --- | --- | --- | --- | --- |
+| `USE_AZURE_OPENAI` | Required | Set this value to `1` to enable Azure OpenAI configuration | - | `1` |
+| `AZURE_API_KEY` | Required | This is the API key you obtained from the Azure OpenAI account page | - | `c55168be3874490ef0565d9779ecd5a6` |
+| `OPENAI_PROXY_URL` | Required | Azure API address, can be found in the "Keys and Endpoints" section when checking resources in the Azure portal | - | `https://docs-test-001.openai.azure.com` |
+| `AZURE_API_VERSION` | Optional | Azure API version, following the format YYYY-MM-DD | 2023-08-01-preview | `2023-05-15`, see [latest version][azure-api-verion-url] |
+| `ACCESS_CODE` | Optional | Add a password to access this service. You can set a long password to prevent brute force attacks. When this value is separated by commas, it becomes an array of passwords | - | `awCT74` or `e3@09!` or `code1,code2,code3` |
+
+<Callout>
+  When you enable `USE_AZURE_OPENAI` on the server, users will be unable to modify and use the
+  OpenAI API key in the frontend configuration.
+</Callout>
+
+[azure-api-verion-url]: https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions
+[azure-openai-url]: https://learn.microsoft.com/zh-cn/azure/ai-services/openai/concepts/models
+[rfc]: https://github.com/lobehub/lobe-chat/discussions/178

package/docs/{Deployment/Deploy-with-Azure-OpenAI.zh-CN.md → self-hosting/deploy-with-azure-openai.zh-CN.mdx}

@@ -1,20 +1,15 @@
-# 使用 Azure OpenAI 部署
+import { Callout } from 'nextra/components';
 
-LobeChat 支持使用 [Azure OpenAI][azure-openai-url] 作为 OpenAI 的模型服务商，本文将介绍如何配置 Azure OpenAI。
-
-#### TOC
+# 与 Azure OpenAI 集成使用
 
-- [使用限制](#使用限制)
-- [在界面中配置](#在界面中配置)
-- [在部署时配置](#在部署时配置)
+LobeChat 支持使用 [Azure OpenAI][azure-openai-url] 作为 OpenAI 的模型服务商，本文将介绍如何配置 Azure OpenAI。
 
 ## 使用限制
 
 从研发成本考虑 ([#178][rfc])，目前阶段的 LobeChat 并没有 100% 完全符合 Azure OpenAI 的实现模型，采用了以 `openai` 为基座，兼容 Azure OpeAI 的解决方案。因此会带来以下局限性：
 
 - OpenAI 与 Azure OpenAI 只能二选一，当你开启使用 Azure OpenAI 后，将无法使用 OpenAI 作为模型服务商；
-- LobeChat 约定了与模型同名的部署名才能正常使用，比如 `gpt-35-turbo` 模型的部署名，必须为 `gpt-35-turbo`，否则 LobeChat 将无法正常正确匹配到相应模型
-  ![](https://github-production-user-asset-6210df.s3.amazonaws.com/28616219/267082091-d89d53d3-1c8c-40ca-ba15-0a9af2a79264.png)
+- LobeChat 约定了与模型同名的部署名才能正常使用，比如 `gpt-35-turbo` 模型的部署名，必须为 `gpt-35-turbo`，否则 LobeChat 将无法正常正确匹配到相应模型 ![](https://github-production-user-asset-6210df.s3.amazonaws.com/28616219/267082091-d89d53d3-1c8c-40ca-ba15-0a9af2a79264.png)
 - 由于 Azure OpenAI 的 SDK 接入复杂度，当前无法查询配置资源的模型列表；
 
 ## 在界面中配置
@@ -31,23 +26,23 @@ LobeChat 支持使用 [Azure OpenAI][azure-openai-url] 作为 OpenAI 的模型
 
 完成上述字段配置后，点击「检查」，如果提示「检查通过」，则说明配置成功。
 
-<br/>
+<br />
 
 ## 在部署时配置
 
 如果你希望部署的版本直接配置好 Azure OpenAI，让终端用户直接使用，那么你需要在部署时配置以下环境变量：
 
-| 环境变量            | 类型 | 描述                                                                             | 默认值             | 示例                                               |
-| ------------------- | ---- | -------------------------------------------------------------------------------- | ------------------ | -------------------------------------------------- |
-| `USE_AZURE_OPENAI`  | 必选 | 设置改值为 `1` 开启 Azure OpenAI 配置                                            | -                  | `1`                                                |
-| `AZURE_API_KEY`     | 必选 | 这是你在 Azure OpenAI 账户页面申请的 API 密钥                                    | -                  | `c55168be3874490ef0565d9779ecd5a6`                 |
-| `OPENAI_PROXY_URL`  | 必选 | Azure API 地址，从 Azure 门户检查资源时，可在 “密钥和终结点” 部分中找到此值      | -                  | `https://docs-test-001.openai.azure.com`           |
-| `AZURE_API_VERSION` | 可选 | Azure 的 API 版本，遵循 YYYY-MM-DD 格式                                          | 2023-08-01-preview | `2023-05-15`，查阅[最新版本][azure-api-verion-url] |
-| `ACCESS_CODE`       | 可选 | 添加访问此服务的密码，你可以设置一个长密码以防被爆破，该值用逗号分隔时为密码数组 | -                  | `awCT74` 或 `e3@09!` or `code1,code2,code3`        |
-
-> \[!NOTE]
->
-> 当你在服务端开启 `USE_AZURE_OPENAI` 后，用户将无法在前端配置中修改并使用 OpenAI key。
+| 环境变量 | 类型 | 描述 | 默认值 | 示例 |
+| --- | --- | --- | --- | --- |
+| `USE_AZURE_OPENAI` | 必选 | 设置改值为 `1` 开启 Azure OpenAI 配置 | - | `1` |
+| `AZURE_API_KEY` | 必选 | 这是你在 Azure OpenAI 账户页面申请的 API 密钥 | - | `c55168be3874490ef0565d9779ecd5a6` |
+| `OPENAI_PROXY_URL` | 必选 | Azure API 地址，从 Azure 门户检查资源时，可在 “密钥和终结点” 部分中找到此值 | - | `https://docs-test-001.openai.azure.com` |
+| `AZURE_API_VERSION` | 可选 | Azure 的 API 版本，遵循 YYYY-MM-DD 格式 | 2023-08-01-preview | `2023-05-15`，查阅[最新版本][azure-api-verion-url] |
+| `ACCESS_CODE` | 可选 | 添加访问此服务的密码，你可以设置一个长密码以防被爆破，该值用逗号分隔时为密码数组 | - | `awCT74` 或 `e3@09!` or `code1,code2,code3` |
+
+<Callout>
+  当你在服务端开启 `USE_AZURE_OPENAI` 后，用户将无法在前端配置中修改并使用 OpenAI API key。
+</Callout>
 
 [azure-api-verion-url]: https://learn.microsoft.com/zh-cn/azure/ai-services/openai/reference#chat-completions
 [azure-openai-url]: https://learn.microsoft.com/zh-cn/azure/ai-services/openai/concepts/models

package/docs/self-hosting/docker-compose.mdx

@@ -0,0 +1,121 @@
+import { Callout, Steps, Tabs } from 'nextra/components';
+
+# Docker Compose Deployment Guide
+
+[![][docker-release-shield]][docker-release-link][![][docker-size-shield]][docker-size-link][![][docker-pulls-shield]][docker-pulls-link]
+
+We provide a [Docker image][docker-release-link] for deploying the LobeChat service on your private device.
+
+<Steps>
+
+### Install Docker Container Environment
+
+(Skip this step if already installed)
+
+<Tabs items={['Ubuntu', 'CentOS']}>
+<Tabs.Tab>
+
+```fish
+$ apt install docker.io
+```
+
+</Tabs.Tab>
+<Tabs.Tab>
+
+```fish
+$ yum install docker
+```
+
+</Tabs.Tab>
+
+</Tabs>
+
+### Run Docker Compose Deployment Command
+
+When using `docker-compose`, the configuration file is as follows:
+
+```yml
+version: '3.8'
+
+services:
+  lobe-chat:
+    image: lobehub/lobe-chat
+    container_name: lobe-chat
+    restart: always
+    ports:
+      - '3210:3210'
+    environment:
+      OPENAI_API_KEY: sk-xxxx
+      OPENAI_PROXY_URL: https://api-proxy.com/v1
+      ACCESS_CODE: lobe66
+```
+
+Run the following command to start the Lobe Chat service:
+
+```bash
+$ docker-compose up -d
+```
+
+### Crontab Automatic Update Script (Optional)
+
+Similarly, you can use the following script to automatically update Lobe Chat. When using `Docker Compose`, no additional configuration of environment variables is required.
+
+```bash
+#!/bin/bash
+# auto-update-lobe-chat.sh
+
+# Set proxy (optional)
+export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
+
+# Pull the latest image and store the output in a variable
+output=$(docker pull lobehub/lobe-chat:latest 2>&1)
+
+# Check if the pull command was executed successfully
+if [ $? -ne 0 ]; then
+  exit 1
+fi
+
+# Check if the output contains a specific string
+echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
+
+# If the image is already up to date, do nothing
+if [ $? -eq 0 ]; then
+  exit 0
+fi
+
+echo "Detected Lobe-Chat update"
+
+# Remove the old container
+echo "Removed: $(docker rm -f Lobe-Chat)"
+
+# You may need to navigate to the directory where `docker-compose.yml` is located first
+# cd /path/to/docker-compose-folder
+
+# Run the new container
+echo "Started: $(docker-compose up)"
+
+# Print the update time and version
+echo "Update time: $(date)"
+echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
+
+# Clean up unused images
+docker images | grep 'lobehub/lobe-chat' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
+echo "Removed old images."
+```
+
+This script can also be used in Crontab, but ensure that your Crontab can find the correct Docker command. It is recommended to use absolute paths.
+
+Configure Crontab to execute the script every 5 minutes:
+
+```bash
+*/5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
+```
+
+</Steps>
+
+[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square
+[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square

package/docs/self-hosting/docker-compose.zh-CN.mdx

@@ -0,0 +1,121 @@
+import { Callout, Steps, Tabs } from 'nextra/components';
+
+# Docker Compose 部署指引
+
+[![][docker-release-shield]][docker-release-link][![][docker-size-shield]][docker-size-link][![][docker-pulls-shield]][docker-pulls-link]
+
+我们提供了 [Docker 镜像][docker-release-link]，供你在自己的私有设备上部署 LobeChat 服务。
+
+[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square
+[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square
+
+<Steps>
+
+### 安装 Docker 容器环境
+
+（如果已安装，请跳过此步）
+
+<Tabs items={['Ubuntu', 'CentOS']}>
+  <Tabs.Tab>
+
+    ```fish
+    $ apt install docker.io
+    ```
+
+  </Tabs.Tab>
+  <Tabs.Tab>
+
+    ```fish
+    $ yum install docker
+    ```
+
+  </Tabs.Tab>
+
+</Tabs>
+
+### 运行 Docker Compose 部署指令
+
+使用 `docker-compose` 时配置文件如下:
+
+```yml
+version: '3.8'
+
+services:
+  lobe-chat:
+    image: lobehub/lobe-chat
+    container_name: lobe-chat
+    restart: always
+    ports:
+      - '3210:3210'
+    environment:
+      OPENAI_API_KEY: sk-xxxx
+      OPENAI_PROXY_URL: https://api-proxy.com/v1
+      ACCESS_CODE: lobe66
+```
+
+运行以下命令启动 Lobe Chat 服务：
+
+```bash
+$ docker-compose up -d
+```
+
+### Crontab 自动更新脚本（可选）
+
+类似地，你可以使用以下脚本来自动更新 Lobe Chat，使用 `Docker Compose` 时，环境变量无需额外配置。
+
+```bash
+#!/bin/bash
+# auto-update-lobe-chat.sh
+
+# 设置代理（可选）
+export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
+
+# 拉取最新的镜像并将输出存储在变量中
+output=$(docker pull lobehub/lobe-chat:latest 2>&1)
+
+# 检查拉取命令是否成功执行
+if [ $? -ne 0 ]; then
+  exit 1
+fi
+
+# 检查输出中是否包含特定的字符串
+echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
+
+# 如果镜像已经是最新的，则不执行任何操作
+if [ $? -eq 0 ]; then
+  exit 0
+fi
+
+echo "Detected Lobe-Chat update"
+
+# 删除旧的容器
+echo "Removed: $(docker rm -f Lobe-Chat)"
+
+# 也许需要先进入 `docker-compose.yml` 所在的目录
+# cd /path/to/docker-compose-folder
+
+# 运行新的容器
+echo "Started: $(docker-compose up)"
+
+# 打印更新的时间和版本
+echo "Update time: $(date)"
+echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
+
+# 清理不再使用的镜像
+docker images | grep 'lobehub/lobe-chat' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
+echo "Removed old images."
+```
+
+此脚本亦可以在 Crontab 中使用，但请确认你的 Crontab 可以找到正确的 Docker 命令。建议使用绝对路径。
+
+配置 Crontab，每 5 分钟执行一次脚本：
+
+```bash
+*/5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
+```
+
+</Steps>

package/docs/self-hosting/docker.mdx

@@ -0,0 +1,152 @@
+import { Callout, Steps, Tabs } from 'nextra/components';
+
+# Docker Deployment Guide
+
+[![][docker-release-shield]][docker-release-link][![][docker-size-shield]][docker-size-link][![][docker-pulls-shield]][docker-pulls-link]
+
+We provide a [Docker image][docker-release-link] for you to deploy the LobeChat service on your private device.
+
+<Steps>
+
+### Install Docker Container Environment
+
+(If already installed, skip this step)
+
+<Tabs items={['Ubuntu', 'CentOS']}>
+  <Tabs.Tab>
+
+```fish
+$ apt install docker.io
+```
+
+</Tabs.Tab>
+  <Tabs.Tab>
+
+```fish
+$ yum install docker
+```
+
+</Tabs.Tab>
+</Tabs>
+
+### Docker Command Deployment
+
+Use the following command to start the LobeChat service with one click:
+
+```fish
+$ docker run -d -p 3210:3210 \
+  -e OPENAI_API_KEY=sk-xxxx \
+  -e ACCESS_CODE=lobe66 \
+  --name lobe-chat \
+  lobehub/lobe-chat
+```
+
+Command explanation:
+
+- The default port mapping is `3210`, please ensure it is not occupied or manually change the port mapping.
+
+- Replace `sk-xxxx` in the above command with your OpenAI API Key.
+
+- For the complete list of environment variables supported by LobeChat, please refer to the [Environment Variables](/zh/self-hosting/environment-ariable) section.
+
+<Callout>
+  Since the official Docker image build takes about half an hour, if you see the "update available"
+  prompt after deployment, you can wait for the image to finish building before deploying again.
+</Callout>
+
+<Callout type="warning">
+  The official Docker image does not have a password set. It is strongly recommended to add a
+  password to enhance security, otherwise you may encounter situations like [My API Key was
+  stolen!!!](https://github.com/lobehub/lobe-chat/issues/1123).
+</Callout>
+
+<Callout type="info">
+  Note that when the **deployment architecture is inconsistent with the image**, you need to
+  cross-compile **Sharp**, see [Sharp
+  Cross-Compilation](https://sharp.pixelplumbing.com/install#cross-platform) for details.
+</Callout>
+
+#### Using a Proxy Address
+
+If you need to use the OpenAI service through a proxy, you can configure the proxy address using the `OPENAI_PROXY_URL` environment variable:
+
+```fish
+$ docker run -d -p 3210:3210 \
+  -e OPENAI_API_KEY=sk-xxxx \
+  -e OPENAI_PROXY_URL=https://api-proxy.com/v1 \
+  -e ACCESS_CODE=lobe66 \
+  --name lobe-chat \
+  lobehub/lobe-chat
+```
+
+### Crontab Automatic Update Script (Optional)
+
+If you want to automatically obtain the latest image, you can follow these steps.
+
+First, create a `lobe.env` configuration file with various environment variables, for example:
+
+```env
+OPENAI_API_KEY=sk-xxxx
+OPENAI_PROXY_URL=https://api-proxy.com/v1
+ACCESS_CODE=arthals2333
+CUSTOM_MODELS=-gpt-4,-gpt-4-32k,-gpt-3.5-turbo-16k,gpt-3.5-turbo-1106=gpt-3.5-turbo-16k,gpt-4-0125-preview=gpt-4-turbo,gpt-4-vision-preview=gpt-4-vision
+```
+
+Then, you can use the following script to automate the update:
+
+```bash
+#!/bin/bash
+# auto-update-lobe-chat.sh
+
+# Set up proxy (optional)
+export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
+
+# Pull the latest image and store the output in a variable
+output=$(docker pull lobehub/lobe-chat:latest 2>&1)
+
+# Check if the pull command was executed successfully
+if [ $? -ne 0 ]; then
+  exit 1
+fi
+
+# Check if the output contains a specific string
+echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
+
+# If the image is already up to date, do nothing
+if [ $? -eq 0 ]; then
+  exit 0
+fi
+
+echo "Detected Lobe-Chat update"
+
+# Remove the old container
+echo "Removed: $(docker rm -f Lobe-Chat)"
+
+# Run the new container
+echo "Started: $(docker run -d --network=host --env-file /path/to/lobe.env --name=Lobe-Chat --restart=always lobehub/lobe-chat)"
+
+# Print the update time and version
+echo "Update time: $(date)"
+echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
+
+# Clean up unused images
+docker images | grep 'lobehub/lobe-chat' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
+echo "Removed old images."
+```
+
+This script can be used in Crontab, but please ensure that your Crontab can find the correct Docker command. It is recommended to use absolute paths.
+
+Configure Crontab to execute the script every 5 minutes:
+
+```bash
+*/5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
+```
+
+[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square
+[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square
+
+</Steps>

package/docs/self-hosting/docker.zh-CN.mdx

@@ -0,0 +1,149 @@
+import { Callout, Steps, Tabs } from 'nextra/components';
+
+# Docker 部署指引
+
+[![][docker-release-shield]][docker-release-link][![][docker-size-shield]][docker-size-link][![][docker-pulls-shield]][docker-pulls-link]
+
+我们提供了 [Docker 镜像][docker-release-link]，供你在自己的私有设备上部署 LobeChat 服务。
+
+[docker-pulls-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-pulls-shield]: https://img.shields.io/docker/pulls/lobehub/lobe-chat?color=45cc11&labelColor=black&style=flat-square
+[docker-release-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-release-shield]: https://img.shields.io/docker/v/lobehub/lobe-chat?color=369eff&label=docker&labelColor=black&logo=docker&logoColor=white&style=flat-square
+[docker-size-link]: https://hub.docker.com/r/lobehub/lobe-chat
+[docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat?color=369eff&labelColor=black&style=flat-square
+
+<Steps>
+
+### 安装 Docker 容器环境
+
+（如果已安装，请跳过此步）
+
+<Tabs items={['Ubuntu', 'CentOS']}>
+  <Tabs.Tab>
+
+```fish
+$ apt install docker.io
+```
+
+  </Tabs.Tab>
+  <Tabs.Tab>
+
+```fish
+$ yum install docker
+```
+
+  </Tabs.Tab>
+</Tabs>
+
+### Docker 指令部署
+
+使用以下命令即可使用一键启动 LobeChat 服务：
+
+```fish
+$ docker run -d -p 3210:3210 \
+  -e OPENAI_API_KEY=sk-xxxx \
+  -e ACCESS_CODE=lobe66 \
+  --name lobe-chat \
+  lobehub/lobe-chat
+```
+
+指令说明：
+
+- 默认映射端口为 `3210`, 请确保未被占用或手动更改端口映射
+- 使用你的 OpenAI API Key 替换上述命令中的 `sk-xxxx`
+
+- LobeChat 支持的完整环境变量列表请参考 [环境变量](/zh/self-hosting/environment-ariable) 部分
+
+<Callout>
+  由于官方的 Docker
+  镜像构建大约需要半小时左右，如果在更新部署后会出现「存在更新」的提示，可以等待镜像构建完成后再次部署。
+</Callout>
+
+<Callout type="warning">
+  官方 Docker 镜像中未设定密码，强烈建议添加密码以提升安全性，否则你可能会遇到 [My API Key was
+  stolen!!!](https://github.com/lobehub/lobe-chat/issues/1123) 这样的情况
+</Callout>
+
+<Callout type="info">
+  注意，当**部署架构与镜像的不一致时**，需要对 **Sharp** 进行交叉编译，详见 [Sharp
+  交叉编译](https://sharp.pixelplumbing.com/install#cross-platform)
+</Callout>
+
+#### 使用代理地址
+
+如果你需要通过代理使用 OpenAI 服务，你可以使用 `OPENAI_PROXY_URL` 环境变量来配置代理地址：
+
+```fish
+$ docker run -d -p 3210:3210 \
+  -e OPENAI_API_KEY=sk-xxxx \
+  -e OPENAI_PROXY_URL=https://api-proxy.com/v1 \
+  -e ACCESS_CODE=lobe66 \
+  --name lobe-chat \
+  lobehub/lobe-chat
+```
+
+### Crontab 自动更新脚本（可选）
+
+如果你想自动获得最新的镜像，你可以如下操作。
+
+首先，新建一个 `lobe.env` 配置文件，内容为各种环境变量，例如：
+
+```env
+OPENAI_API_KEY=sk-xxxx
+OPENAI_PROXY_URL=https://api-proxy.com/v1
+ACCESS_CODE=arthals2333
+CUSTOM_MODELS=-gpt-4,-gpt-4-32k,-gpt-3.5-turbo-16k,gpt-3.5-turbo-1106=gpt-3.5-turbo-16k,gpt-4-0125-preview=gpt-4-turbo,gpt-4-vision-preview=gpt-4-vision
+```
+
+然后，你可以使用以下脚本来自动更新：
+
+```bash
+#!/bin/bash
+# auto-update-lobe-chat.sh
+
+# 设置代理（可选）
+export https_proxy=http://127.0.0.1:7890 http_proxy=http://127.0.0.1:7890 all_proxy=socks5://127.0.0.1:7890
+
+# 拉取最新的镜像并将输出存储在变量中
+output=$(docker pull lobehub/lobe-chat:latest 2>&1)
+
+# 检查拉取命令是否成功执行
+if [ $? -ne 0 ]; then
+  exit 1
+fi
+
+# 检查输出中是否包含特定的字符串
+echo "$output" | grep -q "Image is up to date for lobehub/lobe-chat:latest"
+
+# 如果镜像已经是最新的，则不执行任何操作
+if [ $? -eq 0 ]; then
+  exit 0
+fi
+
+echo "Detected Lobe-Chat update"
+
+# 删除旧的容器
+echo "Removed: $(docker rm -f Lobe-Chat)"
+
+# 运行新的容器
+echo "Started: $(docker run -d --network=host --env-file /path/to/lobe.env --name=Lobe-Chat --restart=always lobehub/lobe-chat)"
+
+# 打印更新的时间和版本
+echo "Update time: $(date)"
+echo "Version: $(docker inspect lobehub/lobe-chat:latest | grep 'org.opencontainers.image.version' | awk -F'"' '{print $4}')"
+
+# 清理不再使用的镜像
+docker images | grep 'lobehub/lobe-chat' | grep -v 'latest' | awk '{print $3}' | xargs -r docker rmi > /dev/null 2>&1
+echo "Removed old images."
+```
+
+此脚本可以在 Crontab 中使用，但请确认你的 Crontab 可以找到正确的 Docker 命令。建议使用绝对路径。
+
+配置 Crontab，每 5 分钟执行一次脚本：
+
+```bash
+*/5 * * * * /path/to/auto-update-lobe-chat.sh >> /path/to/auto-update-lobe-chat.log 2>&1
+```
+
+</Steps>