@lobehub/chat 0.147.0 → 0.147.2

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

@@ -12,6 +12,7 @@ tags:
   - 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.
@@ -20,7 +21,12 @@ As the basic functional unit of LobeChat, adding and iterating assistants is ver
 
 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'} />
+<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
 
@@ -33,7 +39,8 @@ When you need to handle specific tasks, you need to consider creating a custom a
 </Cards>
 
 <Callout type={'tip'}>
-  **Quick Setup Tip**: You can conveniently modify the Prompt through the quick edit button in the sidebar.
+  **Quick Setup Tip**: You can conveniently modify the Prompt through the quick edit button in the
+  sidebar.
 </Callout>
 
 <Cards rows={2}>

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

@@ -10,6 +10,7 @@ tags:
   - 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
@@ -18,7 +19,12 @@ tags:
 
 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'} />
+<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
 
@@ -30,9 +36,7 @@ tags:
   <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>
+<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'} />

package/docs/usage/agents/model.mdx

@@ -44,11 +44,11 @@ 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 the
-  randomness of temperature.
+  Top\_p is similar to randomness, and it is generally not recommended to change it together with
+  the randomness of temperature.
 </Callout>
 
 <br />

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

@@ -10,6 +10,7 @@ tags:
   - LLM
   - 生成模型
 ---
+
 # 模型指南
 
 ## ChatGPT
@@ -41,7 +42,7 @@ 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>
 
@@ -67,8 +68,8 @@ 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

@@ -13,6 +13,7 @@ tags:
   - Structured Prompts
   - Improving AI Output
 ---
+
 # Guide to Using Prompts
 
 ## Basic Concepts of Prompts
@@ -29,7 +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.
 
@@ -53,16 +54,17 @@ 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

@@ -8,6 +8,7 @@ tags:
   - 撰写技巧
   - 逐步扩展
 ---
+
 # Prompt 使用指南
 
 ## Prompt 基本概念
@@ -23,7 +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。
 
@@ -49,16 +50,17 @@ 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

@@ -11,9 +11,17 @@ tags:
   - Topic List
   - Favorite Topics
 ---
+
 # Topic Usage Guide
 
-<Image alt={'Topic Usage Guide'} borderless cover src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'} />
+<Image
+  alt={'Topic Usage Guide'}
+  borderless
+  cover
+  src={
+    '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.
 - **Topic List:** Clicking on a topic in the list allows for quick switching of historical conversation records and continuing the conversation. You can also use the star icon <kbd>⭐️</kbd> to pin favorite topics to the top, or use the more button on the right to rename or delete topics.

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

@@ -9,9 +9,17 @@ tags:
   - 话题重命名
   - 话题删除
 ---
+
 # 话题使用指南
 
-<Image alt={'话题使用指南'} borderless cover src={'https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/279602496-fd72037a-735e-4cc2-aa56-2994bceaba81.png'} />
+<Image
+  alt={'话题使用指南'}
+  borderless
+  cover
+  src={
+    '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。
 - **话题列表：** 点击列表中的话题可以快速切换历史对话记录，并继续对话。你还可以通过点击星标图标 <kbd>⭐️</kbd> 将话题收藏置顶，或者通过右侧更多按钮对话题进行重命名和删除操作。

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

@@ -26,11 +26,11 @@ tags:
 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.
 
 <Callout type={'tip'}>
-  By [🤖/🏪 submitting agents](https://github.com/lobehub/lobe-chat-agents), you can easily submit your assistant works to
-  our platform. We particularly emphasize that LobeChat has established a sophisticated automated
-  internationalization (i18n) workflow, which excels in seamlessly converting your assistants into
-  multiple language versions. This means that regardless of the language your users are using, they
-  can seamlessly experience your assistant.
+  By [🤖/🏪 submitting agents](https://github.com/lobehub/lobe-chat-agents), you can easily submit
+  your assistant works to our platform. We particularly emphasize that LobeChat has established a
+  sophisticated automated internationalization (i18n) workflow, which excels in seamlessly
+  converting your assistants into multiple language versions. This means that regardless of the
+  language your users are using, they can seamlessly experience your assistant.
 </Callout>
 
 <Callout type={'important'}>

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

@@ -11,6 +11,7 @@ tags:
   - 自动化国际化
   - 多语言版本
 ---
+
 # 助手市场
 
 <Image

package/docs/usage/features/local-llm.mdx

@@ -15,7 +15,12 @@ tags:
 
 # Local Large Language Model (LLM) Support
 
-<Image alt={'Ollama Local Large Language Model (LLM) Support'} borderless cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c'} />
+<Image
+  alt={'Ollama Local Large Language Model (LLM) Support'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c'}
+/>
 
 <Callout>Available in >=0.127.0, currently only supports Docker deployment</Callout>
 

package/docs/usage/features/local-llm.zh-CN.mdx

@@ -7,7 +7,12 @@ tags:
 
 # 支持本地大语言模型（LLM）
 
-<Image alt={'Ollama 支持本地大语言模型'} borderless cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c'} />
+<Image
+  alt={'Ollama 支持本地大语言模型'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c'}
+/>
 
 <Callout>在 >=v0.127.0 版本中可用，目前仅支持 Docker 部署</Callout>
 

package/docs/usage/features/mobile.mdx

@@ -13,7 +13,11 @@ tags:
 
 # Mobile Device Adaptation
 
-<Image alt={'Mobile Device Adaptation'} cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/11110732-8d5a-4049-b556-c2561cb66182'} />
+<Image
+  alt={'Mobile Device Adaptation'}
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/11110732-8d5a-4049-b556-c2561cb66182'}
+/>
 
 LobeChat has undergone a series of optimized designs for mobile devices to enhance the user's mobile experience.
 

package/docs/usage/features/mobile.zh-CN.mdx

@@ -9,9 +9,14 @@ tags:
   - GitHub
   - 反馈
 ---
+
 # 移动设备适配
 
-<Image alt={'移动端设备适配'} cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/11110732-8d5a-4049-b556-c2561cb66182'} />
+<Image
+  alt={'移动端设备适配'}
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/11110732-8d5a-4049-b556-c2561cb66182'}
+/>
 
 LobeChat 针对移动设备进行了一系列的优化设计，以提升用户的移动体验。
 

package/docs/usage/features/more.mdx

@@ -11,6 +11,7 @@ tags:
   - Privacy
   - Custom Domain
 ---
+
 # More Features
 
 In addition to the above features, our design and technical capabilities will provide you with more assurance in usage:

package/docs/usage/features/more.zh-CN.mdx

@@ -8,6 +8,7 @@ tags:
   - 隐私安全
   - 自定义域名
 ---
+
 # 更多特性
 
 除了上述功能特性以外，我们的所具有的设计和技术能力将为你带来了更多使用保障：

package/docs/usage/features/multi-ai-providers.mdx

@@ -17,7 +17,12 @@ tags:
 
 # Multi-Model Service Provider Support
 
-<Image alt={'Multi-Model Service Provider Support'} borderless cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/b164bc54-8ba2-4c1e-b2f2-f4d7f7e7a551'} />
+<Image
+  alt={'Multi-Model Service Provider Support'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/b164bc54-8ba2-4c1e-b2f2-f4d7f7e7a551'}
+/>
 
 <Callout>Available in version 0.123.0 and later</Callout>
 
@@ -38,6 +43,10 @@ At the same time, we are also planning to support more model service providers,
 
 ## Local Model Support
 
-<Image alt={'Local Model Support'} borderless src={'https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c'} />
+<Image
+  alt={'Local Model Support'}
+  borderless
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c'}
+/>
 
 To meet the specific needs of users, LobeChat also supports the use of local models based on [Ollama](https://ollama.ai), allowing users to flexibly use their own or third-party models. For more details, see [Local Model Support](/en/usage/features/local-llm).

package/docs/usage/features/multi-ai-providers.zh-CN.mdx

@@ -14,9 +14,15 @@ tags:
   - 01 AI
   - Ollama
 ---
+
 # 多模型服务商支持
 
-<Image alt={'多模型服务商支持'} borderless cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/b164bc54-8ba2-4c1e-b2f2-f4d7f7e7a551'} />
+<Image
+  alt={'多模型服务商支持'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/b164bc54-8ba2-4c1e-b2f2-f4d7f7e7a551'}
+/>
 
 <Callout>在 0.123.0 及以后版本中可用</Callout>
 
@@ -38,6 +44,10 @@ tags:
 
 ## 本地模型支持
 
-<Image alt={'本地模型支持'} borderless src={'https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c'} />
+<Image
+  alt={'本地模型支持'}
+  borderless
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c'}
+/>
 
 为了满足特定用户的需求，LobeChat 还基于 [Ollama](https://ollama.ai) 支持了本地模型的使用，让用户能够更灵活地使用自己的或第三方的模型，详见 [本地模型支持](/zh/usage/features/local-llm)。

package/docs/usage/features/plugin-system.mdx

@@ -67,19 +67,20 @@ The plugin system of LobeChat has now entered a stable stage, and we have basica
 <Steps>
   ### ✅ Phase One of Plugins
 
-  Implementing the separation of plugins from the main body, splitting the plugins into independent repositories for maintenance, and implementing dynamic loading of plugins. [**#73**](https://github.com/lobehub/lobe-chat/issues/73)
+Implementing the separation of plugins from the main body, splitting the plugins into independent repositories for maintenance, and implementing dynamic loading of plugins. [**#73**](https://github.com/lobehub/lobe-chat/issues/73)
 
-  ### ✅ Phase Two of Plugins
+### ✅ Phase Two of Plugins
 
-  The security and stability of plugin usage, more accurate presentation of abnormal states, maintainability and developer-friendliness of the plugin architecture. [**#97**](https://github.com/lobehub/lobe-chat/issues/97)
+The security and stability of plugin usage, more accurate presentation of abnormal states, maintainability and developer-friendliness of the plugin architecture. [**#97**](https://github.com/lobehub/lobe-chat/issues/97)
 
-  ### ✅ Phase Three of Plugins
+### ✅ Phase Three of Plugins
 
-  Higher-level and improved customization capabilities, support for OpenAPI schema invocation, compatibility with ChatGPT plugins, and the addition of Midjourney plugins. [**#411**](https://github.com/lobehub/lobe-chat/discussions/#411)
+Higher-level and improved customization capabilities, support for OpenAPI schema invocation, compatibility with ChatGPT plugins, and the addition of Midjourney plugins. [**#411**](https://github.com/lobehub/lobe-chat/discussions/#411)
 
-  ### 💭 Phase Four of Plugins
+### 💭 Phase Four of Plugins
+
+Comprehensive authentication, visual configuration of plugin definitions, Plugin SDK CLI, Python language development template, any other ideas? Join the discussion: [**#1310**](https://github.com/lobehub/lobe-chat/discussions/#1310)
 
-  Comprehensive authentication, visual configuration of plugin definitions, Plugin SDK CLI, Python language development template, any other ideas? Join the discussion: [**#1310**](https://github.com/lobehub/lobe-chat/discussions/#1310)
 </Steps>
 
 [chat-plugin-sdk]: https://github.com/lobehub/chat-plugin-sdk

package/docs/usage/features/plugin-system.zh-CN.mdx

@@ -7,6 +7,7 @@ tags:
   - 开发资源
   - 插件开发指南
 ---
+
 # 插件系统
 
 <Image
@@ -54,19 +55,20 @@ LobeChat 的插件系统目前已初步进入一个稳定阶段，我们已基
 <Steps>
   ### ✅ 插件一期
 
-  实现插件与主体分离，将插件拆分为独立仓库维护，并实现插件的动态加载。 [**#73**](https://github.com/lobehub/lobe-chat/issues/73)
+实现插件与主体分离，将插件拆分为独立仓库维护，并实现插件的动态加载。 [**#73**](https://github.com/lobehub/lobe-chat/issues/73)
+
+### ✅ 插件二期
 
-  ### ✅ 插件二期
+插件的安全性与使用的稳定性，更加精准地呈现异常状态，插件架构的可维护性与开发者友好。[**#97**](https://github.com/lobehub/lobe-chat/issues/97)
 
-  插件的安全性与使用的稳定性，更加精准地呈现异常状态，插件架构的可维护性与开发者友好。[**#97**](https://github.com/lobehub/lobe-chat/issues/97)
+### ✅ 插件三期
 
-  ### ✅ 插件三期
+更高阶与完善的自定义能力，支持 OpenAPI schema 调用、兼容 ChatGPT 插件、新增 Midjourney 插件。 [**#411**](https://github.com/lobehub/lobe-chat/discussions/#411)
 
-  更高阶与完善的自定义能力，支持 OpenAPI schema 调用、兼容 ChatGPT 插件、新增 Midjourney 插件。 [**#411**](https://github.com/lobehub/lobe-chat/discussions/#411)
+### 💭 插件四期
 
-  ### 💭 插件四期
+完善的鉴权、可视化配置插件定义、 Plugin SDK CLI 、 Python 语言研发模板、还有什么想法？欢迎参与讨论： [**#1310**](https://github.com/lobehub/lobe-chat/discussions/#1310)
 
-  完善的鉴权、可视化配置插件定义、 Plugin SDK CLI 、 Python 语言研发模板、还有什么想法？欢迎参与讨论： [**#1310**](https://github.com/lobehub/lobe-chat/discussions/#1310)
 </Steps>
 
 [chat-plugin-sdk]: https://github.com/lobehub/chat-plugin-sdk

package/docs/usage/features/pwa.mdx

@@ -14,7 +14,12 @@ tags:
 
 # Progressive Web App (PWA)
 
-<Image alt={'Progressive Web App (PWA)'} borderless cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/ecc8364a-cfc4-4a3d-b6fd-68b2d9bc5f0d'} />
+<Image
+  alt={'Progressive Web App (PWA)'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/ecc8364a-cfc4-4a3d-b6fd-68b2d9bc5f0d'}
+/>
 
 We understand the importance of providing a seamless experience for users in today's multi-device environment. To achieve this, we have adopted Progressive Web App [PWA](https://support.google.com/chrome/answer/9658361) technology, which is a modern web technology that elevates web applications to a near-native app experience. Through PWA, LobeChat is able to provide a highly optimized user experience on both desktop and mobile devices, while maintaining lightweight and high performance characteristics. Visually and perceptually, we have also carefully designed it to ensure that its interface is indistinguishable from a native app, providing smooth animations, responsive layouts, and adaptation to different screen resolutions of various devices.
 
@@ -23,9 +28,10 @@ If you are unfamiliar with the installation process of PWA, you can follow the s
 <Steps>
   ### Run Chrome or Edge browser on your computer
 
-  ### Visit the LobeChat webpage
+### Visit the LobeChat webpage
 
-  ### In the top right corner of the address bar, click the <kbd>Install</kbd> icon
+### In the top right corner of the address bar, click the <kbd>Install</kbd> icon
+
+### Follow the on-screen instructions to complete the PWA installation
 
-  ### Follow the on-screen instructions to complete the PWA installation
 </Steps>

package/docs/usage/features/pwa.zh-CN.mdx

@@ -11,9 +11,15 @@ tags:
   - 高性能
   - 响应式布局
 ---
+
 # 渐进式 Web 应用（PWA）
 
-<Image alt={'渐进式 Web 应用（PWA）'} borderless cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/ecc8364a-cfc4-4a3d-b6fd-68b2d9bc5f0d'} />
+<Image
+  alt={'渐进式 Web 应用（PWA）'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/ecc8364a-cfc4-4a3d-b6fd-68b2d9bc5f0d'}
+/>
 
 我们利深知在当今多设备环境下为用户提供无缝体验的重要性。为此，我们采用了渐进式 Web 应用 [PWA](https://support.google.com/chrome/answer/9658361) 技术，这是一种能够将网页应用提升至接近原生应用体验的现代 Web 技术。通过 PWA，LobeChat 能够在桌面和移动设备上提供高度优化的用户体验，同时保持轻量级和高性能的特点。在视觉和感觉上，我们也经过精心设计，以确保它的界面与原生应用无差别，提供流畅的动画、响应式布局和适配不同设备的屏幕分辨率。
 
@@ -22,9 +28,10 @@ tags:
 <Steps>
   ### 在电脑上运行 Chrome 或 Edge 浏览器
 
-  ### 访问 LobeChat 网页
+### 访问 LobeChat 网页
+
+### 在地址栏的右上角，单击 <kbd>安装</kbd> 图标
 
-  ### 在地址栏的右上角，单击 <kbd>安装</kbd> 图标
+### 根据屏幕上的指示完成 PWA 的安装
 
-  ### 根据屏幕上的指示完成 PWA 的安装
 </Steps>

package/docs/usage/features/text-to-image.zh-CN.mdx

@@ -11,6 +11,7 @@ tags:
   - Pollinations
   - AI工具
 ---
+
 # Text to Image 文生图
 
 <Image

package/docs/usage/features/theme.mdx

@@ -15,7 +15,12 @@ tags:
 
 # Custom Themes
 
-<Image alt={'Custom Themes'} borderless cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/9eca103c-9335-4a4c-8192-271a0b857b26'} />
+<Image
+  alt={'Custom Themes'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/9eca103c-9335-4a4c-8192-271a0b857b26'}
+/>
 
 LobeChat places a strong emphasis on personalized user experiences in its interface design, and thus introduces flexible and diverse theme modes, including a light mode for daytime and a dark mode for nighttime.
 

package/docs/usage/features/theme.zh-CN.mdx

@@ -9,9 +9,15 @@ tags:
   - 界面设计
   - 个性化体验
 ---
+
 # 自定义主题
 
-<Image alt={'自定义主题'} borderless cover src={'https://github.com/lobehub/lobe-chat/assets/28616219/9eca103c-9335-4a4c-8192-271a0b857b26'} />
+<Image
+  alt={'自定义主题'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/28616219/9eca103c-9335-4a4c-8192-271a0b857b26'}
+/>
 
 LobeChat 在界面设计上十分考虑用户的个性化体验，因此引入了灵活多变的主题模式，其中包括日间的亮色模式和夜间的深色模式。
 

package/docs/usage/features/tts.zh-CN.mdx

@@ -10,6 +10,7 @@ tags:
   - 文字转语音
   - 语音转文字
 ---
+
 # TTS & STT 语音会话
 
 <Image

package/docs/usage/features/vision.zh-CN.mdx

@@ -8,6 +8,7 @@ tags:
   - 智能对话
   - 大语言模型
 ---
+
 # 模型视觉识别
 
 <Image