@lobehub/chat 1.0.0 → 1.0.2

package/docs/self-hosting/platform/vercel.mdx

@@ -0,0 +1,46 @@
+---
+title: Deploy LobeChat with Vercel
+description: >-
+  Learn how to deploy LobeChat on Vercel with ease. Follow the provided steps to
+  prepare your OpenAI API Key, deploy the project, and start using it
+  efficiently.
+tags:
+  - Deploy LobeChat
+  - Vercel Deployment
+  - OpenAI API Key
+  - Custom Domain Binding
+---
+
+# Deploy LobeChat with Vercel
+
+If you want to deploy LobeChat on Vercel, you can follow the steps below:
+
+## Vercel Deployment Process
+
+<Steps>
+  ### Prepare your OpenAI API Key
+
+Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+
+### Click the button below to deploy
+
+[![](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flobehub%2Flobe-chat&env=OPENAI_API_KEY,ACCESS_CODE&envDescription=Find%20your%20OpenAI%20API%20Key%20by%20click%20the%20right%20Learn%20More%20button.%20%7C%20Access%20Code%20can%20protect%20your%20website&envLink=https%3A%2F%2Fplatform.openai.com%2Faccount%2Fapi-keys&project-name=lobe-chat&repository-name=lobe-chat)
+
+Simply log in with your GitHub account, and remember to fill in `OPENAI_API_KEY` (required) and `ACCESS_CODE` (recommended) in the environment variables page.
+
+### After deployment, you can start using it
+
+### Bind a custom domain (optional)
+
+Vercel's assigned domain DNS may be polluted in some regions, so binding a custom domain can establish a direct connection.
+
+</Steps>
+
+## Automatic Synchronization of Updates
+
+If you have deployed your project using the one-click deployment steps mentioned above, you may find that you are always prompted with "updates available." This is because Vercel creates a new project for you by default instead of forking this project, which causes the inability to accurately detect updates.
+
+<Callout>
+  We recommend following the [Self-Hosting Upstream Sync](/docs/self-hosting/advanced/upstream-sync) steps to
+  Redeploy.
+</Callout>

package/docs/self-hosting/platform/vercel.zh-CN.mdx

@@ -0,0 +1,47 @@
+---
+title: 在 Vercel 上部署 LobeChat
+description: 学习如何在 Vercel 上一键部署 LobeChat，准备 OpenAI API Key，点击按钮进行部署，绑定自定义域名，自动同步更新等。
+tags:
+  - Vercel
+  - 部署指引
+  - LobeChat
+  - OpenAI API Key
+  - 自定义域名
+  - 自动同步更新
+---
+
+# Vercel 部署指引
+
+如果想在 Vercel 上部署 LobeChat，可以按照以下步骤进行操作：
+
+## Vercel 部署流程
+
+<Steps>
+  ### 准备好你的 OpenAI API Key
+
+前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+
+### 点击下方按钮进行部署
+
+[![][deploy-button-image]][deploy-link]
+
+直接使用 GitHub 账号登录即可，记得在环境变量页填入 `OPENAI_API_KEY` （必填） and `ACCESS_CODE`（推荐）；
+
+### 部署完毕后，即可开始使用
+
+### 绑定自定义域名（可选）
+
+Vercel 分配的域名 DNS 在某些区域被污染了，绑定自定义域名即可直连。
+
+</Steps>
+
+## 自动同步更新
+
+如果你根据上述中的一键部署步骤部署了自己的项目，你可能会发现总是被提示 “有可用更新”。这是因为 Vercel 默认为你创建新项目而非 fork 本项目，这将导致无法准确检测更新。
+
+<Callout>
+  我们建议按照 [📘 LobeChat 自部署保持更新](/docs/self-hosting/advanced/upstream-sync) 步骤重新部署。
+</Callout>
+
+[deploy-button-image]: https://vercel.com/button
+[deploy-link]: https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Flobehub%2Flobe-chat&env=OPENAI_API_KEY,ACCESS_CODE&envDescription=Find%20your%20OpenAI%20API%20Key%20by%20click%20the%20right%20Learn%20More%20button.%20%7C%20Access%20Code%20can%20protect%20your%20website&envLink=https%3A%2F%2Fplatform.openai.com%2Faccount%2Fapi-keys&project-name=lobe-chat&repository-name=lobe-chat

package/docs/self-hosting/platform/zeabur.mdx

@@ -0,0 +1,85 @@
+---
+title: Deploy LobeChat on Zeabur
+description: >-
+  Learn how to deploy LobeChat on Zeabur with ease. Follow the provided steps to
+  set up your chat application seamlessly.
+tags:
+  - Deploy LobeChat
+  - Zeabur Deployment
+  - OpenAI API Key
+  - Custom Domain Binding
+---
+
+# Deploy LobeChat with Zeabur
+
+If you want to deploy LobeChat on Zeabur, you can follow the steps below:
+
+## Zeabur Deployment Process
+
+<Steps>
+  ### Prepare your OpenAI API Key
+
+Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+
+### Click the button below to deploy
+
+[![][deploy-button-image]][deploy-link]
+
+### Once deployed, you can start using it
+
+### Bind a custom domain (optional)
+
+You can use the subdomain provided by Zeabur, or choose to bind a custom domain. Currently, the domains provided by Zeabur have not been contaminated, and most regions can connect directly.
+
+</Steps>
+
+[deploy-button-image]: https://zeabur.com/button.svg
+[deploy-link]: https://zeabur.com/templates/VZGGTI
+
+# Deploy LobeChat with Zeabur as serverless function
+
+>Note: There are still issues with [middlewares and rewrites of next.js on Zeabur](https://github.com/lobehub/lobe-chat/pull/2775?notification_referrer_id=NT_kwDOAdi2DrQxMDkyODQ4MDc2NTozMDk3OTU5OA#issuecomment-2146713899), use at your own risk! 
+
+Since Zeabur does NOT officially support FREE users deploy containerized service, you may wish to deploy LobeChat as a serverless function service.
+To deploy LobeChat as a serverless function service on Zeabur, you can follow the steps below:
+
+## Zeabur Deployment Process
+
+<Steps>
+
+### Fork LobeChat
+
+### Add Zeabur pack config file
+
+Add a `zbpack.json` configuration file with the following content to the root dir of your fork:
+```json
+{
+  "serverless": true,
+  "ignore_dockerfile": true
+}
+```
+
+### Prepare your OpenAI API Key
+
+Go to [OpenAI API Key](https://platform.openai.com/account/api-keys) to get your OpenAI API Key.
+
+### Login to your [Zeabur dashboard](https://dash.zeabur.com)
+
+If you do not already have an account, you will need to register one.
+
+### Create a project and service
+
+Create a project, then create a service under this project.
+
+### Link your fork of LobeChat to the just created Zeabur service.
+
+When adding service, choose github.
+This may triger a oAuth depend on varies factors like how you login to Zeabur and if you have already authorized Zeabur to access all your repos
+
+### Bind a custom domain (optional)
+
+You can create a subdomain provided by Zeabur, or choose to bind a custom domain. Currently, the domains provided by Zeabur have not been contaminated, and most regions can connect directly.
+
+### Zeabur shall start auto build and you should be able to access it by the domain of your choice after a while.
+
+</Steps>

package/docs/self-hosting/platform/zeabur.zh-CN.mdx

@@ -0,0 +1,84 @@
+---
+title: 在 Zeabur 上部署 LobeChat
+description: 按照指南准备 OpenAI API Key 并点击按钮进行部署。在部署完成后，即可开始使用 LobeChat 并选择是否绑定自定义域名。
+tags:
+  - Zeabur
+  - LobeChat
+  - OpenAI API Key
+  - 部署流程
+  - 自定义域名
+---
+
+# 使用 Zeabur 部署
+
+如果想在 Zeabur 上部署 LobeChat，可以按照以下步骤进行操作：
+
+## Zeabur 部署流程
+
+<Steps>
+  ### 准备好你的 OpenAI API Key
+
+前往 [OpenAI API Key](https://platform.openai.com/account/api-keys) 获取你的 OpenAI API Key
+
+### 点击下方按钮进行部署
+
+[![][deploy-button-image]][deploy-link]
+
+### 部署完毕后，即可开始使用
+
+### 绑定自定义域名（可选）
+
+你可以使用 Zeabur 提供的子域名，也可以选择绑定自定义域名。目前 Zeabur 提供的域名还未被污染，大多数地区都可以直连。
+
+</Steps>
+
+[deploy-button-image]: https://zeabur.com/button.svg
+[deploy-link]: https://zeabur.com/templates/VZGGTI
+
+# 使用 Zeabur 将 LobeChat 部署为无服务器函数
+
+>**注意：** 仍然存在关于 [Zeabur 上 next.js 的中间件和重写问题](https://github.com/lobehub/lobe-chat/pull/2775?notification_referrer_id=NT_kwDOAdi2DrQxMDkyODQ4MDc2NTozMDk3OTU5OA#issuecomment-2146713899)，请自担风险！
+
+由于 Zeabur 并未官方支持免费用户部署容器化服务，您可能希望将 LobeChat 部署为无服务器函数服务。
+要在 Zeabur 上将 LobeChat 部署为无服务器函数服务，您可以按照以下步骤操作：
+
+## Zeabur 部署流程
+
+<Steps>
+
+### Fork LobeChat
+
+### 添加 Zeabur 打包配置文件
+
+在您的分支的根目录下添加一个 `zbpack.json` 配置文件，内容如下：
+```json
+{
+  "serverless": true,
+  "ignore_dockerfile": true
+}
+```
+
+### 准备您的 OpenAI API 密钥
+
+前往 [OpenAI API 密钥](https://platform.openai.com/account/api-keys) 获取您的 OpenAI API 密钥。
+
+### 登录到您的 [Zeabur 仪表板](https://dash.zeabur.com)
+
+如果您尚未拥有一个账号，您需要注册一个。
+
+### 创建项目与服务。
+
+创建一个项目，并再这个项目下新建一个服务。
+
+### 将您的 LobeChat 分支链接到刚创建的 Zeabur 服务。
+
+在添加服务时，选择 github。
+这可能会触发一个 oAuth，取决于诸如您如何登录到 Zeabur以及您是否已经授权 Zeabur 访问所有您的存储库等各种因素。
+
+### 绑定自定义域名（可选）
+
+您可以创建 Zeabur 提供的子域名，或选择绑定自定义域名。目前，Zeabur 提供的域名尚未受到污染，大多数地区可以直接连接。
+
+### Zeabur 将开始自动构建，您应该可以在一段时间后通过您选择的域名访问它。
+
+</Steps>

package/docs/self-hosting/start.mdx

@@ -0,0 +1,31 @@
+---
+title: Build Your Own LobeChat - Choose Your Deployment Platform
+description: >-
+  Explore multiple deployment platforms like Vercel, Docker, Docker Compose, and
+  more to deploy LobeChat. Choose the platform that best suits your needs.
+tags:
+  - Lobe Chat
+  - Deployment Platform
+  - Vercel
+  - Docker
+  - Docker Compose
+---
+
+# Build your own Lobe Chat
+
+Choose your favorite platform to get started.
+
+## Choose your deployment platform
+
+LobeChat support multiple deployment platforms, including Vercel, Docker, and Docker Compose and so on, you can choose the deployment platform that suits you.
+
+<PlatformCards
+  docker={'Docker'}
+  dockerCompose={'Docker Compose'}
+  netlify={'Netlify'}
+  railway={'Railway'}
+  repocloud={'RepoCloud'}
+  sealos={'SealOS'}
+  vercel={'Vercel'}
+  zeabur={'Zeabur'}
+/>

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

@@ -0,0 +1,32 @@
+---
+title: 构建属于自己的 LobeChat - 自选部署平台
+description: >-
+  选择适合自己的部署平台，构建个性化的 Lobe Chat。支持 Docker、Docker
+  Compose、Netlify、Railway、Repocloud、SealOS、Vercel 和 Zeabur 部署。
+tags:
+  - Lobe Chat
+  - 部署平台
+  - Docker
+  - Netlify
+  - Vercel
+  - 个性化
+---
+
+# 构建属于自己的 Lobe Chat
+
+选择自己喜爱的平台，构建属于自己的 Lobe Chat。
+
+## 选择部署平台
+
+LobeChat 支持多种部署平台，包括 Vercel、Docker 和 Docker Compose 等，你可以选择适合自己的部署平台进行部署。
+
+<PlatformCards
+  docker={'Docker 部署'}
+  dockerCompose={'Docker Compose 部署'}
+  netlify={'Netlify 部署'}
+  railway={'Railway 部署'}
+  repocloud={'Repocloud 部署'}
+  sealos={'SealOS 部署'}
+  vercel={'Vercel 部署'}
+  zeabur={'Zeabur 部署'}
+/>

package/docs/usage/agents/concepts.mdx

@@ -0,0 +1,41 @@
+---
+title: Improving User Interaction Efficiency with Agents in LobeChat
+description: >-
+  Discover how LobeChat's innovative approach with Agents enhances user
+  experience by providing dedicated functional modules for efficient task
+  handling and quick access to historical conversations.
+tags:
+  - LobeChat
+  - Agents
+  - User Interaction Efficiency
+  - Task Handling
+  - Historical Conversations
+---
+
+# Topics and Assistants
+
+## ChatGPT and "Topics"
+
+In the official ChatGPT application, there is only the concept of "topics." As shown in the image, the user's historical conversation topics are listed in the sidebar.
+
+<Image
+  alt={'ChatGPT and Topics'}
+  src={
+    '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.
+
+## Topics and "Agent"
+
+Therefore, in LobeChat, we have introduced the concept of **Agents**. An agent is a complete functional module, each with its own responsibilities and tasks. Assistants can help you handle various tasks and provide professional advice and guidance.
+
+<Image
+  alt={'Topics and Agent'}
+  src={
+    '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

@@ -0,0 +1,38 @@
+---
+title: 在 LobeChat 中进行话题与助手的革新
+description: 了解 LobeChat 中的话题与助手概念，如何提高用户交互效率并解决历史对话信息索引分散的问题。
+tags:
+  - LobeChat
+  - 话题与助手
+  - 交互效率
+  - 历史对话记录
+  - 信息索引
+---
+
+# 话题与助手
+
+## ChatGPT 与「话题」
+
+在 ChatGPT 官方应用中，只存在话题的概念，如图所示，在侧边栏中是用户的历史对话话题列表。
+
+<Image
+  alt={'ChatGPT 与「话题」'}
+  src={
+    '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。
+
+## 「话题」与「助手」
+
+因此在 LobeChat 中，我们引入了 **助手** 的概念。助手是一个完整的功能模块，每个助手都有自己的职责和任务。助手可以帮助你处理各种任务，并提供专业的建议和指导。
+
+<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'
+  }
+/>
+
+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

@@ -0,0 +1,58 @@
+---
+title: Custom LobeChat Assistant Guide - Adding and Iterating Assistants
+description: >-
+  Learn how to add assistants to your favorites list in LobeChat through the
+  role market or by creating custom assistants. Explore detailed steps for
+  creating custom assistants and quick setup tips.
+tags:
+  - LobeChat
+  - Adding Assistants
+  - Custom Assistant
+  - Role Market
+  - Creating Assistants
+  - Assistant Configuration
+---
+
+# Custom Assistant Guide
+
+As the basic functional unit of LobeChat, adding and iterating assistants is very important. Now you can add assistants to your favorites list in two ways.
+
+## `A` Add through the role market
+
+If you are a beginner in Prompt writing, you might want to browse the assistant market of LobeChat first. Here, you can find commonly used assistants submitted by others and easily add them to your list with just one click, which is very convenient.
+
+<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'
+  }
+/>
+
+## `B` Create a custom assistant
+
+When you need to handle specific tasks, you need to consider creating a custom assistant to help you solve the problem. You can add and configure the assistant in detail in the following ways.
+
+<Cards rows={2}>
+  <Image alt={'Create a custom assistant S1'} src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279587283-a3ea8dfd-70fb-47ee-ab00-e3911ac6a939.png'} />
+
+  <Image alt={'Create a custom assistant S2'} src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279587292-a3d102c6-f61e-4578-91f1-c0a4c97588e1.png'} />
+</Cards>
+
+<Callout type={'tip'}>
+  **Quick Setup Tip**: You can conveniently modify the Prompt through the quick edit button in the
+  sidebar.
+</Callout>
+
+<Cards rows={2}>
+  <Image alt={'Create a custom assistant S3'} src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279587294-388d1877-193e-4a50-9fe8-8fbcc3ccefa0.png'} />
+
+  <Image alt={'Create a custom assistant S4'} src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279587298-333da153-13b8-4557-a0a2-cff55e7bc1c0.png'} />
+</Cards>
+
+If you want to understand Prompt writing tips and common model parameter settings, you can continue to view:
+
+<Cards>
+  <Card href={'/docs/usage/agents/prompt'} title={'Prompt User Guide'} />
+
+  <Card href={'/docs/usage/agents/model'} title={'Large Language Model User Guide'} />
+</Cards>

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

@@ -0,0 +1,53 @@
+---
+title: LobeChat 自定义助手指南 - 添加和配置助手的最佳方法
+description: 了解如何通过角色市场或新建自定义助手将助手添加到你的常用列表中。快捷设置技巧和常见的模型参数设置也包括在内。
+tags:
+  - 自定义助手
+  - LobeChat
+  - 添加助手
+  - 配置助手
+  - 角色市场
+  - 快捷设置
+  - 模型参数设置
+---
+
+# 自定义助手指南
+
+作为 LobeChat 的基础职能单位，助手的添加和迭代是非常重要的。现在你可以通过两种方式将助手添加到你的常用列表中
+
+## `A` 通过角色市场添加
+
+如果你是一个 Prompt 编写的新手，不妨先浏览一下 LobeChat 的助手市场。在这里，你可以找到其他人提交的常用助手，并且只需一键添加到你的列表中，非常方便。
+
+<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'
+  }
+/>
+
+## `B` 通过新建自定义助手
+
+当你需要处理一些特定的任务时，你就需要考虑创建一个自定义助手来帮助你解决问题。可以通过以下方式添加并进行助手的详细配置
+
+<Cards rows={2}>
+  <Image alt={'通过新建自定义助手 S1'} src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279587283-a3ea8dfd-70fb-47ee-ab00-e3911ac6a939.png'} />
+
+  <Image alt={'通过新建自定义助手 S2'} src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279587292-a3d102c6-f61e-4578-91f1-c0a4c97588e1.png'} />
+</Cards>
+
+<Callout type={'tip'}>**快捷设置技巧**: 可以通过侧边栏的快捷编辑按钮进行 Prompt 的便捷修改</Callout>
+
+<Cards rows={2}>
+  <Image alt={'通过新建自定义助手 S3'} src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279587294-388d1877-193e-4a50-9fe8-8fbcc3ccefa0.png'} />
+
+  <Image alt={'通过新建自定义助手 S4'} inStep src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279587298-333da153-13b8-4557-a0a2-cff55e7bc1c0.png'} />
+</Cards>
+
+如果你希望理解 Prompt 编写技巧和常见的模型参数设置，可以继续查看：
+
+<Cards>
+  <Card href={'/docs/usage/agents/prompt'} title={'Prompt 使用指南'} />
+
+  <Card href={'/docs/usage/agents/model'} title={'大语言模型使用指南'} />
+</Cards>

package/docs/usage/agents/model.mdx

@@ -0,0 +1,80 @@
+---
+title: LobeChat Model Config Guide
+description: >-
+  Explore the capabilities of ChatGPT models from gpt-3.5-turbo to gpt-4-32k,
+  understanding their speed, context limits, and cost. Learn about model
+  parameters like temperature and top-p for better output.
+tags:
+  - ChatGPT Models
+  - Model Parameters
+  - Neural Networks
+  - Language Understanding
+  - Generation Capabilities
+---
+
+# Model Guide
+
+## ChatGPT
+
+- **gpt-3.5-turbo**: Currently the fastest generating ChatGPT model, it is faster but may sacrifice some text quality, with a context length of 4k.
+- **gpt-3.5-turbo-16k**: Similar to gpt-4, the context limit is increased to 16k tokens, with a higher cost.
+- **gpt-4**: ChatGPT 4.0 has improved language understanding and generation capabilities compared to 3.5. It can better understand context and context, and generate more accurate and natural responses. This is thanks to improvements in the GPT-4 model, including better language modeling and deeper semantic understanding, but it may be slower than other models, with a context length of 8k.
+- **gpt-4-32k**: Similar to gpt-4, the context limit is increased to 32k tokens, with a higher cost.
+
+## Concept of Model Parameters
+
+LLM seems magical, but it is essentially a probability problem. The neural network generates a bunch of candidate words from the pre-trained model based on the input text and selects the high-probability ones as output. Most of the related parameters are associated with sampling (i.e., how to select the output from the candidate words).
+
+### `temperature`
+
+This parameter controls the randomness of the model's output. The higher the value, the greater the randomness. Generally, when the same prompt is input multiple times, the model's output varies each time.
+
+- Set to 0: Generates a fixed output for each prompt
+- Lower values: More concentrated and deterministic output
+- Higher values: More random output (more creative)
+
+<Callout>
+  Generally, the longer and clearer the prompt, the better the quality and confidence of the model's
+  output. In such cases, the temperature value can be adjusted appropriately. Conversely, if the
+  prompt is short and ambiguous, setting a relatively high temperature value will result in unstable
+  model output.
+</Callout>
+
+<br />
+
+### `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.
+
+<Callout>
+  Top\_p is similar to randomness, and it is generally not recommended to change it together with
+  the randomness of temperature.
+</Callout>
+
+<br />
+
+### `presence_penalty`
+
+The presence penalty parameter can be seen as a punishment for repetitive content in the generated text. When this parameter is set high, the generation model will try to avoid producing repeated words, phrases, or sentences. Conversely, if the presence penalty parameter is set low, the generated text may contain more repetitive content. By adjusting the value of the presence penalty parameter, control over the originality and diversity of the generated text can be achieved. The importance of this parameter is mainly reflected in the following aspects:
+
+- Enhancing the originality and diversity of the generated text: In certain applications, such as creative writing or generating news headlines, it is necessary for the generated text to have high originality and diversity. By increasing the value of the presence penalty parameter, the amount of repeated content in the generated text can be effectively reduced, thereby enhancing its originality and diversity.
+- Preventing the generation of loops and meaningless content: In some cases, the generation model may produce repetitive or meaningless text that usually fails to convey useful information. By appropriately increasing the value of the presence penalty parameter, the probability of generating such meaningless content can be reduced, thereby improving the readability and practicality of the generated text.
+
+<Callout>
+  It is worth noting that the presence penalty parameter, in conjunction with other parameters such
+  as temperature and top-p, collectively influences the quality of the generated text. Compared to
+  other parameters, the presence penalty parameter primarily focuses on the originality and
+  repetitiveness of the text, while the temperature and top-p parameters more significantly affect
+  the randomness and determinism of the generated text. By adjusting these parameters reasonably,
+  comprehensive control over the quality of the generated text can be achieved.
+</Callout>
+
+### `frequency_penalty`
+
+It is a mechanism that penalizes frequently occurring new vocabulary in the text to reduce the likelihood of the model repeating the same word. The larger the value, the more likely it is to reduce repeated words.
+
+- `-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%)