@lobehub/chat 1.44.3 → 1.45.0

package/docs/self-hosting/server-database.mdx

@@ -47,58 +47,56 @@ Before deployment, make sure you have a Postgres database instance ready. You ca
 Since we support file-based conversations/knowledge base conversations, we need to install the `pgvector` plugin for Postgres. This plugin provides vector search capabilities and is a key component for LobeChat to implement RAG.
 
 <Steps>
-### `NEXT_PUBLIC_SERVICE_MODE`
+  ### `NEXT_PUBLIC_SERVICE_MODE`
 
-LobeChat supports both client-side and server-side databases, so we provide an environment variable for switching modes, which is `NEXT_PUBLIC_SERVICE_MODE`, with a default value of `client`.
+  LobeChat supports both client-side and server-side databases, so we provide an environment variable for switching modes, which is `NEXT_PUBLIC_SERVICE_MODE`, with a default value of `client`.
 
-For server-side database deployment scenarios, you need to set `NEXT_PUBLIC_SERVICE_MODE` to `server`.
+  For server-side database deployment scenarios, you need to set `NEXT_PUBLIC_SERVICE_MODE` to `server`.
 
-<Callout type={'info'}>
-  In the official `lobe-chat-database` Docker image, this environment variable is already set to
-  `server` by default. Therefore, if you deploy using the Docker image, you do not need to configure
-  this environment variable again.
-</Callout>
-
-<Callout type={'tip'}>
-Since environment variables starting with `NEXT_PUBLIC` take effect in the front-end code, they cannot be modified through container runtime injection. (Refer to the `next.js` documentation [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables)). This is why we chose to create a separate DB version image.
-
-If you need to modify variables with the `NEXT_PUBLIC` prefix in a Docker deployment, you must build the image yourself and inject your own `NEXT_PUBLIC` prefixed environment variables during the build.
+  <Callout type={'info'}>
+    In the official `lobe-chat-database` Docker image, this environment variable is already set to
+    `server` by default. Therefore, if you deploy using the Docker image, you do not need to configure
+    this environment variable again.
+  </Callout>
 
-</Callout>
+  <Callout type={'tip'}>
+    Since environment variables starting with `NEXT_PUBLIC` take effect in the front-end code, they cannot be modified through container runtime injection. (Refer to the `next.js` documentation [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables)). This is why we chose to create a separate DB version image.
 
-### `DATABASE_URL`
+    If you need to modify variables with the `NEXT_PUBLIC` prefix in a Docker deployment, you must build the image yourself and inject your own `NEXT_PUBLIC` prefixed environment variables during the build.
+  </Callout>
 
-The core of configuring the database is to add the `DATABASE_URL` environment variable and fill in the Postgres database connection URL you have prepared. The typical format of the database connection URL is `postgres://username:password@host:port/database`.
+  ### `DATABASE_URL`
 
-<Callout type={'info'}>
-  If you want to enable SSL when connecting to the database, please refer to the
-  [documentation](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)
-  for setup instructions.
-</Callout>
+  The core of configuring the database is to add the `DATABASE_URL` environment variable and fill in the Postgres database connection URL you have prepared. The typical format of the database connection URL is `postgres://username:password@host:port/database`.
 
-### `DATABASE_DRIVER`
+  <Callout type={'info'}>
+    If you want to enable SSL when connecting to the database, please refer to the
+    [documentation](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)
+    for setup instructions.
+  </Callout>
 
-The `DATABASE_DRIVER` environment variable is used to distinguish between the two types of Postgres database instances, with values of `node` or `neon`.
+  ### `DATABASE_DRIVER`
 
-To streamline deployment, we have set default values based on the characteristics of different platforms:
+  The `DATABASE_DRIVER` environment variable is used to distinguish between the two types of Postgres database instances, with values of `node` or `neon`.
 
-- On the Vercel platform, `DATABASE_DRIVER` defaults to `neon`;
-- In our provided Docker image `lobe-chat-database`, `DATABASE_DRIVER` defaults to `node`.
+  To streamline deployment, we have set default values based on the characteristics of different platforms:
 
-Therefore, if you follow the standard deployment methods below, you do not need to manually configure the `DATABASE_DRIVER` environment variable:
+  - On the Vercel platform, `DATABASE_DRIVER` defaults to `neon`;
+  - In our provided Docker image `lobe-chat-database`, `DATABASE_DRIVER` defaults to `node`.
 
-- Vercel + Serverless Postgres
-- Docker image + Node Postgres
+  Therefore, if you follow the standard deployment methods below, you do not need to manually configure the `DATABASE_DRIVER` environment variable:
 
-### `KEY_VAULTS_SECRET`
+  - Vercel + Serverless Postgres
+  - Docker image + Node Postgres
 
-Considering that users will store sensitive information such as their API Key and baseURL in the database, we need a key to encrypt this information to prevent leakage in case of a database breach. Hence, the `KEY_VAULTS_SECRET` environment variable is used to encrypt sensitive information like user-stored apikeys.
+  ### `KEY_VAULTS_SECRET`
 
-<Callout type={'info'}>
-  You can generate a random 32-character string as the value of `KEY_VAULTS_SECRET` using `openssl
-  rand -base64 32`.
-</Callout>
+  Considering that users will store sensitive information such as their API Key and baseURL in the database, we need a key to encrypt this information to prevent leakage in case of a database breach. Hence, the `KEY_VAULTS_SECRET` environment variable is used to encrypt sensitive information like user-stored apikeys.
 
+  <Callout type={'info'}>
+    You can generate a random 32-character string as the value of `KEY_VAULTS_SECRET` using `openssl
+                      rand -base64 32`.
+  </Callout>
 </Steps>
 
 ## Configuring Authentication Services
@@ -107,7 +105,7 @@ In the server-side database mode, we need an authentication service to distingui
 
 ### Clerk
 
-[Clerk](https://clerk.com?utm_source=lobehub&utm_medium=docs) is an authentication SaaS service that provides out-of-the-box authentication capabilities with high productization, low integration costs, and a great user experience. For those who offer SaaS products, Clerk is a good choice. Our official [LobeChat Cloud](https://lobechat.com) uses Clerk as the authentication service.
+[Clerk](https://clerk.com?utm_source=lobehub\&utm_medium=docs) is an authentication SaaS service that provides out-of-the-box authentication capabilities with high productization, low integration costs, and a great user experience. For those who offer SaaS products, Clerk is a good choice. Our official [LobeChat Cloud](https://lobechat.com) uses Clerk as the authentication service.
 
 The integration of Clerk is relatively simple, requiring only the configuration of these environment variables:
 

package/docs/self-hosting/server-database.zh-CN.mdx

@@ -15,7 +15,7 @@ tags:
 LobeChat 默认使用客户端数据库（IndexedDB），同时也支持使用服务端数据库（下简称 DB 版）。LobeChat 采用了 Postgres 作为后端存储数据库。
 
 <Callout>
-  PostgreSQL是一种强大的开源关系型数据库管理系统，具备高度扩展性和标准SQL支持。它提供了丰富的数据类型、并发处理、数据完整性、安全性及可编程性，适用于复杂应用和大规模数据管理。
+  PostgreSQL 是一种强大的开源关系型数据库管理系统，具备高度扩展性和标准 SQL 支持。它提供了丰富的数据类型、并发处理、数据完整性、安全性及可编程性，适用于复杂应用和大规模数据管理。
 </Callout>
 
 本文将从框架角度介绍在任何一个平台中部署 DB 版 LobeChat 的流程和原理，让你知其然也知其所以然，最后可以根据自己的实际情况进行部署。
@@ -41,59 +41,56 @@ LobeChat 默认使用客户端数据库（IndexedDB），同时也支持使用
 
 <Callout>两者的配置方式在环境变量的取值上会略有一点区别，其他方面是一样的。</Callout>
 
-同时，由于我们支持了文件对话/知识库对话的能力，因此我们需要为 Postgres 安装 `pgvector` 插件，该插件提供了向量搜索的能力，是 LobeChat 实现 RAG 的重要构件之一。
+同时，由于我们支持了文件对话 / 知识库对话的能力，因此我们需要为 Postgres 安装 `pgvector` 插件，该插件提供了向量搜索的能力，是 LobeChat 实现 RAG 的重要构件之一。
 
 <Steps>
+  ### `NEXT_PUBLIC_SERVICE_MODE`
 
-### `NEXT_PUBLIC_SERVICE_MODE`
+  LobeChat 同时支持了客户端数据库和服务端数据库，因此我们提供了一个环境变量用于切换模式，这个变量为 `NEXT_PUBLIC_SERVICE_MODE`，该值默认为 `client`。
 
-LobeChat 同时支持了客户端数据库和服务端数据库，因此我们提供了一个环境变量用于切换模式，这个变量为 `NEXT_PUBLIC_SERVICE_MODE`，该值默认为 `client`。
+  针对服务端数据库部署场景，你需要将 `NEXT_PUBLIC_SERVICE_MODE` 设置为 `server`。
 
-针对服务端数据库部署场景，你需要将 `NEXT_PUBLIC_SERVICE_MODE` 设置为 `server`。
+  <Callout type={'info'}>
+    在官方的 `lobe-chat-database` Docker 镜像中，已经默认将该环境变量设为 `server`，因此如果你使用
+    Docker 镜像部署，则无需再配置该环境变量。
+  </Callout>
 
-<Callout type={'info'}>
-  在官方的 `lobe-chat-database` Docker 镜像中，已经默认将该环境变量设为 `server`，因此如果你使用
-  Docker 镜像部署，则无需再配置该环境变量。
-</Callout>
+  <Callout type={'tip'}>
+    由于 `NEXT_PUBLIC` 开头的环境变量是在前端代码中生效的，而因此无法通过容器运行时注入进行修改。 （`next.js`的参考文档 [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables) ) 这也是为什么我们选择再打一个 DB 版镜像的原因。
 
-<Callout type={'tip'}>
-  由于 `NEXT_PUBLIC` 开头的环境变量是在前端代码中生效的，而因此无法通过容器运行时注入进行修改。 （`next.js`的参考文档 [Configuring: Environment Variables | Next.js (nextjs.org)](https://nextjs.org/docs/pages/building-your-application/configuring/environment-variables) ) 这也是为什么我们选择再打一个 DB 版镜像的原因。
+    如果你需要在 Docker 部署中修改 `NEXT_PUBLIC` 前缀的变量，你必须自行构建镜像，在 build 时就把自己的 `NEXT_PUBLIC` 开头的环境变量打进去。
+  </Callout>
 
-如果你需要在 Docker 部署中修改 `NEXT_PUBLIC` 前缀的变量，你必须自行构建镜像，在 build 时就把自己的 `NEXT_PUBLIC` 开头的环境变量打进去。
+  ### `DATABASE_URL`
 
-</Callout>
+  配置数据库，核心是添加 `DATABASE_URL` 环境变量，将你准备好的 Postgres 数据库连接 URL 填入其中。数据库连接 URL 的通常格式为 `postgres://username:password@host:port/database`。
 
-### `DATABASE_URL`
+  <Callout type={'info'}>
+    如果希望连接数据库时启用 SSL
+    ，请自行参考[文档](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)进行设置
+  </Callout>
 
-配置数据库，核心是添加 `DATABASE_URL` 环境变量，将你准备好的 Postgres 数据库连接 URL 填入其中。数据库连接 URL 的通常格式为 `postgres://username:password@host:port/database`。
+  ### `DATABASE_DRIVER`
 
-<Callout type={'info'}>
-  如果希望连接数据库时启用 SSL
-  ，请自行参考[文档](https://stackoverflow.com/questions/14021998/using-psql-to-connect-to-postgresql-in-ssl-mode)进行设置
-</Callout>
+  `DATABASE_DRIVER` 环境变量用于区分两种 Postgres 数据库实例，`DATABASE_DRIVER` 的取值为 `node` 或 `neon`。
 
-### `DATABASE_DRIVER`
+  为提升部署便捷性，我们根据不同的平台特点设置了默认值：
 
-`DATABASE_DRIVER` 环境变量用于区分两种 Postgres 数据库实例，`DATABASE_DRIVER` 的取值为 `node` 或 `neon`。
+  - 在 Vercel 平台下，`DATABASE_DRIVER` 默认为 `neon`；
+  - 在我们提供的 Docker 镜像 `lobe-chat-database` 中，`DATABASE_DRIVER` 默认为 `node`。
 
-为提升部署便捷性，我们根据不同的平台特点设置了默认值：
+  因此如果你采用了以下标准的部署方式，你无需手动配置 `DATABASE_DRIVER` 环境变量：
 
-- 在 Vercel 平台下，`DATABASE_DRIVER` 默认为 `neon`；
-- 在我们提供的 Docker 镜像 `lobe-chat-database` 中，`DATABASE_DRIVER` 默认为 `node`。
+  - Vercel + Serverless Postgres
+  - Docker 镜像 + Node Postgres
 
-因此如果你采用了以下标准的部署方式，你无需手动配置 `DATABASE_DRIVER` 环境变量：
+  ### `KEY_VAULTS_SECRET`
 
-- Vercel + Serverless Postgres
-- Docker 镜像 + Node Postgres
-
-### `KEY_VAULTS_SECRET`
-
-考虑到用户会存储自己的 API Key 和 baseURL 等敏感信息到数据库中，因此我们需要一个密钥来加密这些信息，避免数据库被爆破/脱库时这些关键信息被泄露。 因此有了 `KEY_VAULTS_SECRET` 环境变量，用于加密用户存储的 apikey 等敏感信息。
-
-<Callout type={'info'}>
-  你可以使用 `openssl rand -base64 32` 生成一个随机的 32 位字符串作为 `KEY_VAULTS_SECRET` 的值。
-</Callout>
+  考虑到用户会存储自己的 API Key 和 baseURL 等敏感信息到数据库中，因此我们需要一个密钥来加密这些信息，避免数据库被爆破 / 脱库时这些关键信息被泄露。 因此有了 `KEY_VAULTS_SECRET` 环境变量，用于加密用户存储的 apikey 等敏感信息。
 
+  <Callout type={'info'}>
+    你可以使用 `openssl rand -base64 32` 生成一个随机的 32 位字符串作为 `KEY_VAULTS_SECRET` 的值。
+  </Callout>
 </Steps>
 
 ## 配置身份验证服务
@@ -102,7 +99,7 @@ LobeChat 同时支持了客户端数据库和服务端数据库，因此我们
 
 ### Clerk
 
-[Clerk](https://clerk.com?utm_source=lobehub&utm_medium=docs) 是一个身份验证 SaaS 服务，提供了开箱即用的身份验证能力，产品化程度很高，集成成本较低，体验很好。对于提供 SaaS 化产品的诉求来说，Clerk 是一个不错的选择。我们官方提供的 [LobeChat Cloud](https://lobechat.com)，就是使用了 Clerk 作为身份验证服务。
+[Clerk](https://clerk.com?utm_source=lobehub\&utm_medium=docs) 是一个身份验证 SaaS 服务，提供了开箱即用的身份验证能力，产品化程度很高，集成成本较低，体验很好。对于提供 SaaS 化产品的诉求来说，Clerk 是一个不错的选择。我们官方提供的 [LobeChat Cloud](https://lobechat.com)，就是使用了 Clerk 作为身份验证服务。
 
 Clerk 的集成也相对简单，只需要配置 `NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY` 、 `CLERK_SECRET_KEY` 和 `CLERK_WEBHOOK_SECRET` 环境变量即可，这三个环境变量可以在 Clerk 控制台中获取。
 
@@ -132,7 +129,7 @@ NextAuth 是一个开源的身份验证库，支持多种身份验证提供商
 
 LobeChat 在 [很早以前](https://x.com/lobehub/status/1724289575672291782) 就支持了多模态的 AI 会话，其中涉及到图片上传给大模型的功能。在客户端数据库方案中，图片文件直接以二进制数据存储在浏览器 IndexedDB 数据库，但在服务端数据库中这个方案并不可行。因为在 Postgres 中直接存储文件类二进制数据会大大浪费宝贵的数据库存储空间，并拖慢计算性能。
 
-这块最佳实践是使用文件存储服务（S3）来存储图片文件，同时 S3 也是文件上传/知识库功能所依赖的大容量静态文件存储方案。
+这块最佳实践是使用文件存储服务（S3）来存储图片文件，同时 S3 也是文件上传 / 知识库功能所依赖的大容量静态文件存储方案。
 
 <Callout type={'info'}>
   在本文档库中，S3 所指代的是指兼容 S3 存储方案，即支持 Amazon S3 API 的对象存储系统，常见例如

package/docs/self-hosting/start.mdx

@@ -35,8 +35,5 @@ You can follow the guide below for quick deployment of LobeChat:
 For users who are already familiar with LobeChat or need cross-device synchronization, you can deploy a version with a server-side database to access a more complete and powerful LobeChat.
 
 <Cards>
-  <Card
-    href={'/docs/self-hosting/server-database'}
-    title={'Server-Side Database Deployment Guide'}
-  />
+  <Card href={'/docs/self-hosting/server-database'} title={'Server-Side Database Deployment Guide'} />
 </Cards>

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

@@ -19,7 +19,7 @@ LobeChat 支持多种部署平台，包括 Vercel、Docker、 Docker Compose 和
 
 ## 快速部署
 
-对于第一次了解 LobeChat 的用户，我们推荐使用客户端数据库的模式快速部署，该模式的优势是一行指令/一个按钮即可快捷完成部署，便于你快速上手与体验 LobeChat。
+对于第一次了解 LobeChat 的用户，我们推荐使用客户端数据库的模式快速部署，该模式的优势是一行指令 / 一个按钮即可快捷完成部署，便于你快速上手与体验 LobeChat。
 
 你可以通过以下指南快速部署 LobeChat：
 

package/docs/usage/agents/agent-organization.mdx

@@ -14,11 +14,7 @@ tags:
 
 # Assistant Organization Guide
 
-<Image
-  alt={'Assistant Organization'}
-  cover
-  src={'https://github.com/user-attachments/assets/5e04b71a-4c25-4f3d-ae7d-9237ffcb37be'}
-/>
+<Image alt={'Assistant Organization'} cover src={'https://github.com/user-attachments/assets/5e04b71a-4c25-4f3d-ae7d-9237ffcb37be'} />
 
 LobeChat provides a rich variety of AI assistant resources. Users can easily add various assistants through the assistant market, offering a wide range of application scenarios for AI applications.
 
@@ -30,39 +26,27 @@ Firstly, LobeChat's AI assistants support organization through grouping. You can
 
 ### Assistant Settings
 
-<Image
-  alt={'Assistant Grouping'}
-  src={'https://github.com/user-attachments/assets/97a9d713-f4c1-4170-a707-d2060eeab35c'}
-/>
+<Image alt={'Assistant Grouping'} src={'https://github.com/user-attachments/assets/97a9d713-f4c1-4170-a707-d2060eeab35c'} />
 
 - In the menu of an individual assistant, selecting the `Move to Group` option can quickly categorize the assistant into the specified group.
 - If you don't find the group you want, you can choose `Add Group` to quickly create a new group.
 
 ### Group Settings
 
-<Image
-  alt={'Group Menu'}
-  src={'https://github.com/user-attachments/assets/b9ca37db-0f0b-449f-b3b7-f147bec3a735'}
-/>
+<Image alt={'Group Menu'} src={'https://github.com/user-attachments/assets/b9ca37db-0f0b-449f-b3b7-f147bec3a735'} />
 
 - In the group menu, you can quickly create a new assistant under that group.
 - Clicking the `Group Management` button allows you to `rename`, `delete`, `sort`, and perform other operations on all groups.
 
 ## Assistant Search
 
-<Image
-  alt={'Assistant Search'}
-  src={'https://github.com/user-attachments/assets/816ad463-e1ef-478b-9930-c40948247288'}
-/>
+<Image alt={'Assistant Search'} src={'https://github.com/user-attachments/assets/816ad463-e1ef-478b-9930-c40948247288'} />
 
 - At the top of the assistant list, you can use the assistant search function to easily locate the assistant you need using keywords.
 
 ## Assistant Pinning
 
-<Image
-  alt={'Assistant Pinning'}
-  src={'https://github.com/user-attachments/assets/d574b08e-ab93-4723-9d1b-9e9be2bff7ee'}
-/>
+<Image alt={'Assistant Pinning'} src={'https://github.com/user-attachments/assets/d574b08e-ab93-4723-9d1b-9e9be2bff7ee'} />
 
 - In the assistant menu, you can use the `Pin` function to pin the assistant to the top.
 - After pinning an assistant, a pinned area will appear at the top of the assistant list, displaying all pinned assistants.

package/docs/usage/agents/agent-organization.zh-CN.mdx

@@ -12,11 +12,7 @@ tags:
 
 # 助手组织指南
 
-<Image
-  alt={'助手组织'}
-  cover
-  src={'https://github.com/user-attachments/assets/5e04b71a-4c25-4f3d-ae7d-9237ffcb37be'}
-/>
+<Image alt={'助手组织'} cover src={'https://github.com/user-attachments/assets/5e04b71a-4c25-4f3d-ae7d-9237ffcb37be'} />
 
 LobeChat 提供了丰富的 AI 助手资源，用户可以通过助手市场方便地添加各类助手，为 AI 应用提供了广泛的应用场景。
 
@@ -28,39 +24,27 @@ LobeChat 提供了丰富的 AI 助手资源，用户可以通过助手市场方
 
 ### 助手设置
 
-<Image
-  alt={'助手分组'}
-  src={'https://github.com/user-attachments/assets/97a9d713-f4c1-4170-a707-d2060eeab35c'}
-/>
+<Image alt={'助手分组'} src={'https://github.com/user-attachments/assets/97a9d713-f4c1-4170-a707-d2060eeab35c'} />
 
 - 在单个助手的菜单中，选择`移动到分组`选项可以快速将该助手归类到指定分组。
 - 如果没有你想要的分组，可以选择`添加分组`，快速创建一个新的分组。
 
 ### 分组设置
 
-<Image
-  alt={'分组菜单'}
-  src={'https://github.com/user-attachments/assets/b9ca37db-0f0b-449f-b3b7-f147bec3a735'}
-/>
+<Image alt={'分组菜单'} src={'https://github.com/user-attachments/assets/b9ca37db-0f0b-449f-b3b7-f147bec3a735'} />
 
 - 在分组菜单中，可以快速在该分组下新建助手
 - 点击`分组管理`按钮可以对所有分组进行`重命名`、`删除`、`排序`等操作。
 
 ## 助手搜索
 
-<Image
-  alt={'助手搜索'}
-  src={'https://github.com/user-attachments/assets/816ad463-e1ef-478b-9930-c40948247288'}
-/>
+<Image alt={'助手搜索'} src={'https://github.com/user-attachments/assets/816ad463-e1ef-478b-9930-c40948247288'} />
 
 - 在助手列表的顶部，您可以通过助手搜索功能，方便地使用关键词定位到您所需的助手。
 
 ## 助手固定
 
-<Image
-  alt={'助手固定'}
-  src={'https://github.com/user-attachments/assets/d574b08e-ab93-4723-9d1b-9e9be2bff7ee'}
-/>
+<Image alt={'助手固定'} src={'https://github.com/user-attachments/assets/d574b08e-ab93-4723-9d1b-9e9be2bff7ee'} />
 
 - 在助手菜单中，你可以使用`固定`功能将该助手固定在顶部。
 - 固定助手后，助手列表的上方将出现一个固定区域，显示所有已固定的助手列表。

package/docs/usage/agents/concepts.mdx

@@ -21,8 +21,8 @@ In the official ChatGPT application, there is only the concept of "topics." As s
 <Image
   alt={'ChatGPT and Topics'}
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602474-fe7cb3f3-8eb7-40d3-a69f-6615393bbd4e.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602474-fe7cb3f3-8eb7-40d3-a69f-6615393bbd4e.png'
+}
 />
 
 However, in our usage, we have found that this model has many issues. For example, the information indexing of historical conversations is too scattered. Additionally, when dealing with repetitive tasks, it is difficult to have a stable entry point. For instance, if I want ChatGPT to help me translate a document, in this model, I would need to constantly create new topics and then set up the translation prompt I had previously created. When there are high-frequency tasks, this will result in a very inefficient interaction format.
@@ -34,8 +34,8 @@ Therefore, in LobeChat, we have introduced the concept of **Agents**. An agent i
 <Image
   alt={'Topics and Agent'}
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602489-89893e61-2791-4083-9b57-ed80884ad58b.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602489-89893e61-2791-4083-9b57-ed80884ad58b.png'
+}
 />
 
 At the same time, we have integrated topics into each agent. The benefit of this approach is that each agent has an independent topic list. You can choose the corresponding agent based on the current task and quickly switch between historical conversation records. This method is more in line with users' habits in common chat software, improving interaction efficiency.

package/docs/usage/agents/concepts.zh-CN.mdx

@@ -18,8 +18,8 @@ tags:
 <Image
   alt={'ChatGPT 与「话题」'}
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602474-fe7cb3f3-8eb7-40d3-a69f-6615393bbd4e.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602474-fe7cb3f3-8eb7-40d3-a69f-6615393bbd4e.png'
+}
 />
 
 但在我们的使用过程中其实会发现这种模式存在很多问题，比如历史对话的信息索引过于分散问题，同时当处理一些重复任务时很难有一个稳定的入口，比如我希望有一个稳定的入口可以让 ChatGPT 帮助我翻译文档，在这个模式下，我需要不断新建新的话题同时再设置我之前创建好的翻译 Prompt 设定，当有高频任务存在时，这将是一个效率很低的交互形式。
@@ -31,8 +31,8 @@ tags:
 <Image
   alt={'「话题」与「助手」'}
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602489-89893e61-2791-4083-9b57-ed80884ad58b.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602489-89893e61-2791-4083-9b57-ed80884ad58b.png'
+}
 />
 
 与此同时，我们将话题索引到每个助手内部。这样做的好处是，每个助手都有一个独立的话题列表，你可以根据当前任务选择对应的助手，并快速切换历史对话记录。这种方式更符合用户对常见聊天软件的使用习惯，提高了交互的效率。

package/docs/usage/agents/custom-agent.mdx

@@ -24,8 +24,8 @@ If you are a beginner in Prompt writing, you might want to browse the assistant
 <Image
   alt={'Add through the role market'}
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279588466-4c32041b-a8e6-4703-ba4a-f91b7800e359.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279588466-4c32041b-a8e6-4703-ba4a-f91b7800e359.png'
+}
 />
 
 ## `B` Create a custom assistant

package/docs/usage/agents/custom-agent.zh-CN.mdx

@@ -22,8 +22,8 @@ tags:
 <Image
   alt={'通过角色市场添加'}
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279588466-4c32041b-a8e6-4703-ba4a-f91b7800e359.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279588466-4c32041b-a8e6-4703-ba4a-f91b7800e359.png'
+}
 />
 
 ## `B` 通过新建自定义助手

package/docs/usage/agents/model.mdx

@@ -43,10 +43,10 @@ This parameter controls the randomness of the model's output. The higher the val
 
 ### `top_p`
 
-Top_p is also a sampling parameter, but it differs from temperature in its sampling method. Before outputting, the model generates a bunch of tokens, and these tokens are ranked based on their quality. In the top-p sampling mode, the candidate word list is dynamic, and tokens are selected from the tokens based on a percentage. Top_p introduces randomness in token selection, allowing other high-scoring tokens to have a chance of being selected, rather than always choosing the highest-scoring one.
+`top_p` is also a sampling parameter, but it differs from temperature in its sampling method. Before outputting, the model generates a bunch of tokens, and these tokens are ranked based on their quality. In the top-p sampling mode, the candidate word list is dynamic, and tokens are selected from the tokens based on a percentage. Top\_p introduces randomness in token selection, allowing other high-scoring tokens to have a chance of being selected, rather than always choosing the highest-scoring one.
 
 <Callout>
-  Top\_p is similar to randomness, and it is generally not recommended to change it together with
+  `top_p` is similar to randomness, and it is generally not recommended to change it together with
   the randomness of temperature.
 </Callout>
 
@@ -75,5 +75,5 @@ It is a mechanism that penalizes frequently occurring new vocabulary in the text
 - `-2.0` When the morning news started broadcasting, I found that my TV now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now now **(The highest frequency word is "now", accounting for 44.79%)**
 - `-1.0` He always watches the news in the early morning, in front of the TV watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch watch **(The highest frequency word is "watch", accounting for 57.69%)**
 - `0.0` When the morning sun poured into the small diner, a tired postman appeared at the door, carrying a bag of letters in his hands. The owner warmly prepared a breakfast for him, and he started sorting the mail while enjoying his breakfast. **(The highest frequency word is "of", accounting for 8.45%)**
-- `1.0` A girl in deep sleep was woken up by a warm ray of sunshine, she saw the first ray of morning light, surrounded by birdsong and flowers, everything was full of vitality. \_ (The highest frequency word is "of", accounting for 5.45%)
-- `2.0` Every morning, he would sit on the balcony to have breakfast. Under the soft setting sun, everything looked very peaceful. However, one day, when he was about to pick up his breakfast, an optimistic little bird flew by, bringing him a good mood for the day. \_ (The highest frequency word is "of", accounting for 4.94%)
+- `1.0` A girl in deep sleep was woken up by a warm ray of sunshine, she saw the first ray of morning light, surrounded by birdsong and flowers, everything was full of vitality. (The highest frequency word is "of", accounting for 5.45%)
+- `2.0` Every morning, he would sit on the balcony to have breakfast. Under the soft setting sun, everything looked very peaceful. However, one day, when he was about to pick up his breakfast, an optimistic little bird flew by, bringing him a good mood for the day.  (The highest frequency word is "of", accounting for 4.94%)

package/docs/usage/agents/model.zh-CN.mdx

@@ -41,9 +41,9 @@ LLM 看似很神奇，但本质还是一个概率问题，神经网络根据输
 
 ### `top_p`
 
-核采样 top_p 也是采样参数，跟 temperature 不一样的采样方式。模型在输出之前，会生成一堆 token，这些 token 根据质量高低排名，核采样模式中候选词列表是动态的，从 tokens 里按百分比选择候选词。 top_p 为选择 token 引入了随机性，让其他高分的 token 有被选择的机会，不会总是选最高分的。
+核采样 `top_p` 也是采样参数，跟 temperature 不一样的采样方式。模型在输出之前，会生成一堆 token，这些 token 根据质量高低排名，核采样模式中候选词列表是动态的，从 tokens 里按百分比选择候选词。 top\_p 为选择 token 引入了随机性，让其他高分的 token 有被选择的机会，不会总是选最高分的。
 
-<Callout>top\_p 与随机性类似，一般来说不建议和随机性 temperature 一起更改</Callout>
+<Callout>`top_p` 与随机性类似，一般来说不建议和随机性 temperature 一起更改</Callout>
 
 <br />
 
@@ -67,8 +67,8 @@ Presence Penalty 参数可以看作是对生成文本中重复内容的一种惩
 
 是一种机制，通过对文本中频繁出现的新词汇施加惩罚，以减少模型重复同一词语的可能性，值越大，越有可能降低重复字词。
 
-- `-2.0` 当早间新闻开始播出，我发现我家电视现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在 _（频率最高的词是 “现在”，占比 44.79%）_
-- `-1.0` 他总是在清晨看新闻，在电视前看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看 _（频率最高的词是 “看”，占比 57.69%）_
+- `-2.0` 当早间新闻开始播出，我发现我家电视现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在现在 *（频率最高的词是 “现在”，占比 44.79%）*
+- `-1.0` 他总是在清晨看新闻，在电视前看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看看 *（频率最高的词是 “看”，占比 57.69%）*
 - `0.0` 当清晨的阳光洒进小餐馆时，一名疲倦的邮递员出现在门口，他的手中提着一袋信件。店主热情地为他准备了一份早餐，他在享用早餐的同时开始整理邮件。**（频率最高的词是 “的”，占比 8.45%）**
-- `1.0` 一个深度睡眠的女孩被一阵温暖的阳光唤醒，她看到了早晨的第一缕阳光，周围是鸟语花香，一切都充满了生机。_（频率最高的词是 “的”，占比 5.45%）_
-- `2.0` 每天早上，他都会在阳台上坐着吃早餐。在柔和的夕阳照耀下，一切看起来都非常宁静。然而有一天，当他准备端起早餐的时候，一只乐观的小鸟飞过，给他带来了一天的好心情。 _（频率最高的词是 “的”，占比 4.94%）_
+- `1.0` 一个深度睡眠的女孩被一阵温暖的阳光唤醒，她看到了早晨的第一缕阳光，周围是鸟语花香，一切都充满了生机。*（频率最高的词是 “的”，占比 5.45%）*
+- `2.0` 每天早上，他都会在阳台上坐着吃早餐。在柔和的夕阳照耀下，一切看起来都非常宁静。然而有一天，当他准备端起早餐的时候，一只乐观的小鸟飞过，给他带来了一天的好心情。 *（频率最高的词是 “的”，占比 4.94%）*

package/docs/usage/agents/prompt.mdx

@@ -30,7 +30,7 @@ Generative AI is very useful, but it requires human guidance. In most cases, gen
 
 Let's look at a basic discussion prompt example:
 
-> _"What are the most urgent environmental issues facing our planet, and what actions can individuals take to help address these issues?"_
+> *"What are the most urgent environmental issues facing our planet, and what actions can individuals take to help address these issues?"*
 
 We can convert it into a simple prompt for the assistant to answer the following questions: placed at the front.
 
@@ -54,17 +54,16 @@ The second prompt generates longer output and better structure. The use of the t
 <Callout type={'tip'}>
   There are several ways to improve the quality and effectiveness of prompts:
 
-- **Be Clear About Your Needs:** The model's output will strive to meet your needs, so if your needs are not clear, the output may not meet expectations.
-- **Use Correct Grammar and Spelling:** The model will try to mimic your language style, so if your language style is problematic, the output may also be problematic.
-- **Provide Sufficient Contextual Information:** The model will generate output based on the contextual information you provide, so if the information is insufficient, it may not produce the desired results.
-
+  - **Be Clear About Your Needs:** The model's output will strive to meet your needs, so if your needs are not clear, the output may not meet expectations.
+  - **Use Correct Grammar and Spelling:** The model will try to mimic your language style, so if your language style is problematic, the output may also be problematic.
+  - **Provide Sufficient Contextual Information:** The model will generate output based on the contextual information you provide, so if the information is insufficient, it may not produce the desired results.
 </Callout>
 
 After formulating effective prompts for discussing issues, you now need to refine the generated results. This may involve adjusting the output to fit constraints such as word count or combining concepts from different generated results.
 
 A simple method of iteration is to generate multiple outputs and review them to understand the concepts and structures being used. Once the outputs have been evaluated, you can select the most suitable ones and combine them into a coherent response. Another iterative method is to start small and **gradually expand**. This requires more than one prompt: an initial prompt for drafting the initial one or two paragraphs, followed by additional prompts to expand on the content already written. Here is a potential philosophical discussion prompt:
 
-> _"Is mathematics an invention or a discovery? Use careful reasoning to explain your answer."_
+> *"Is mathematics an invention or a discovery? Use careful reasoning to explain your answer."*
 
 Add it to a simple prompt as follows:
 

package/docs/usage/agents/prompt.zh-CN.mdx

@@ -24,7 +24,7 @@ tags:
 
 让我们看一个基本的讨论问题的例子:
 
-> _"我们星球面临的最紧迫的环境问题是什么，个人可以采取哪些措施来帮助解决这些问题？"_
+> *"我们星球面临的最紧迫的环境问题是什么，个人可以采取哪些措施来帮助解决这些问题？"*
 
 我们可以将其转化为简单的助手提示，将回答以下问题：放在前面。
 
@@ -50,17 +50,16 @@ tags:
 <Callout type={'tip'}>
   提升 prompt 质量和效果的方法主要有以下几点：
 
-- **尽量明确你的需求：** 模型的输出会尽可能满足你的需求，所以如果你的需求不明确，输出可能会不如预期。
-- **使用正确的语法和拼写：** 模型会尽可能模仿你的语言风格，所以如果你的语言风格有问题，输出可能也会有问题。
-- **提供足够的上下文信息：** 模型会根据你提供的上下文信息生成输出，所以如果你提供的上下文信息不足，可能无法生成你想要的结果。
-
+  - **尽量明确你的需求：** 模型的输出会尽可能满足你的需求，所以如果你的需求不明确，输出可能会不如预期。
+  - **使用正确的语法和拼写：** 模型会尽可能模仿你的语言风格，所以如果你的语言风格有问题，输出可能也会有问题。
+  - **提供足够的上下文信息：** 模型会根据你提供的上下文信息生成输出，所以如果你提供的上下文信息不足，可能无法生成你想要的结果。
 </Callout>
 
 在为讨论问题制定有效的提示后，您现在需要细化生成的结果。这可能涉及到调整输出以符合诸如字数等限制，或将不同生成的结果的概念组合在一起。
 
 迭代的一个简单方法是生成多个输出并查看它们，以了解正在使用的概念和结构。一旦评估了输出，您就可以选择最合适的输出并将它们组合成一个连贯的回答。另一种迭代的方法是逐步开始，然后**逐步扩展**。这需要不止一个提示：一个起始提示，用于撰写最初的一两段，然后是其他提示，以扩展已经写过的内容。以下是一个潜在的哲学讨论问题:
 
-> _"数学是发明还是发现？用仔细的推理来解释你的答案。"_
+> *"数学是发明还是发现？用仔细的推理来解释你的答案。"*
 
 将其添加到一个简单的提示中，如下所示:
 

package/docs/usage/agents/topics.mdx

@@ -19,8 +19,8 @@ tags:
   borderless
   cover
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'
+}
 />
 
 - **Save Topic:** During a conversation, if you want to save the current context and start a new topic, you can click the save button next to the send button.

package/docs/usage/agents/topics.zh-CN.mdx

@@ -17,8 +17,8 @@ tags:
   borderless
   cover
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'
+}
 />
 
 - **保存话题：** 在聊天过程中，如果想要保存当前上下文并开启新的话题，可以点击发送按钮旁边的保存按钮。

package/docs/usage/features/agent-market.mdx

@@ -19,8 +19,8 @@ tags:
   borderless
   cover
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png'
+}
 />
 
 In LobeChat's Assistant Market, creators can discover a vibrant and innovative community that brings together numerous carefully designed assistants. These assistants not only play a crucial role in work scenarios but also provide great convenience in the learning process. Our market is not just a showcase platform, but also a collaborative space. Here, everyone can contribute their wisdom and share their personally developed assistants.

package/docs/usage/features/agent-market.zh-CN.mdx

@@ -18,8 +18,8 @@ tags:
   alt={'助手市场'}
   cover
   src={
-    'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png'
-  }
+'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png'
+}
 />
 
 在 LobeChat 的助手市场中，创作者们可以发现一个充满活力和创新的社区，它汇聚了众多精心设计的助手，这些助手不仅在工作场景中发挥着重要作用，也在学习过程中提供了极大的便利。我们的市场不仅是一个展示平台，更是一个协作的空间。在这里，每个人都可以贡献自己的智慧，分享个人开发的助手。

package/docs/usage/features/auth.mdx

@@ -17,11 +17,7 @@ tags:
 
 # Support Multi-User Management
 
-<Image
-  alt={'Identity Verification System'}
-  cover
-  src={'https://github.com/lobehub/lobe-chat/assets/17870709/8ce70e15-40df-451e-b700-66090fe5b8c2'}
-/>
+<Image alt={'Identity Verification System'} cover src={'https://github.com/lobehub/lobe-chat/assets/17870709/8ce70e15-40df-451e-b700-66090fe5b8c2'} />
 
 In modern applications, user management and identity verification are essential functions. To meet the diverse needs of different users, LobeChat provides two main user authentication and management solutions: `next-auth` and `Clerk`. Whether you are looking for simple user registration and login or need advanced multi-factor authentication and user management, LobeChat can flexibly accommodate your requirements.