@lobehub/chat 0.148.5 → 0.148.7

package/CHANGELOG.md

@@ -2,6 +2,64 @@
 
 # Changelog
 
+### [Version 0.148.7](https://github.com/lobehub/lobe-chat/compare/v0.148.6...v0.148.7)
+
+<sup>Released on **2024-04-23**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Fix qwen-1.5-chat-72B context window in togetherai.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Fix qwen-1.5-chat-72B context window in togetherai, closes [#2142](https://github.com/lobehub/lobe-chat/issues/2142) ([d0753cf](https://github.com/lobehub/lobe-chat/commit/d0753cf))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 0.148.6](https://github.com/lobehub/lobe-chat/compare/v0.148.5...v0.148.6)
+
+<sup>Released on **2024-04-22**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: Add Windows Phone, iPadOS, BlackBerry OS, Linux OS and Chrome OS sync icons.
+
+#### 💄 Styles
+
+- **misc**: Support more model Icons: dbrx, command-r, openchat, rwkv, Bert-vits2, Stable Diffusion, WizardLM, adobe firefly, skylark.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: Add Windows Phone, iPadOS, BlackBerry OS, Linux OS and Chrome OS sync icons, closes [#2139](https://github.com/lobehub/lobe-chat/issues/2139) ([8ed1f07](https://github.com/lobehub/lobe-chat/commit/8ed1f07))
+
+#### Styles
+
+- **misc**: Support more model Icons: dbrx, command-r, openchat, rwkv, Bert-vits2, Stable Diffusion, WizardLM, adobe firefly, skylark, closes [#2107](https://github.com/lobehub/lobe-chat/issues/2107) ([4268d8b](https://github.com/lobehub/lobe-chat/commit/4268d8b))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 0.148.5](https://github.com/lobehub/lobe-chat/compare/v0.148.4...v0.148.5)
 
 <sup>Released on **2024-04-22**</sup>

package/CONTRIBUTING.md

@@ -43,7 +43,7 @@ Choose a meaningful branch name related to your work. It makes collaboration eas
 🧙‍♀️ Time to work your magic! Write your code, fix bugs, or add new features. Be sure to follow our project's coding style. You can check if your code adheres to our style using:
 
 ```bash
-yarn lint
+pnpm lint
 ```
 
 This adds a bit of enchantment to your coding experience! ✨

package/docs/self-hosting/examples/ollama.mdx

@@ -37,8 +37,67 @@ For more information on using Ollama in LobeChat, please refer to [Ollama Usage]
 ## Accessing Ollama from Non-Local Locations
 
 When you first initiate Ollama, it is configured to allow access only from the local machine. To enable access from other domains and set up port listening, you will need to adjust the environment variables `OLLAMA_ORIGINS` and `OLLAMA_HOST` accordingly.
-```
-set OLLAMA_ORIGINS=*
-set OLLAMA_HOST=:11434
-```
+
+### Ollama Environment Variables
+
+    `OLLAMA_HOST`         The host:port to bind to (default "127.0.0.1:11434")
+    `OLLAMA_ORIGINS`      A comma separated list of allowed origins.
+    `OLLAMA_MODELS`       The path to the models directory (default is "~/.ollama/models")
+    `OLLAMA_KEEP_ALIVE`   The duration that models stay loaded in memory (default is "5m")
+    `OLLAMA_DEBUG`        Set to 1 to enable additional debug logging
+
+### Setting environment variables on Windows
+
+On Windows, Ollama inherits your user and system environment variables.
+
+1. First Quit Ollama by clicking on its tray icon and selecting Quit
+2. Edit system environment variables from the control panel
+3. Edit or create New variable(s) for your user account for `OLLAMA_HOST`, `OLLAMA_ORIGINS`, etc.
+4. Click OK/Apply to save
+5. Restart it
+
+### Setting environment variables on Mac
+
+If Ollama is run as a macOS application, environment variables should be set using `launchctl`:
+
+1. For each environment variable, call `launchctl setenv`.
+
+    ```bash
+    launchctl setenv OLLAMA_HOST "0.0.0.0"
+    launchctl setenv OLLAMA_ORIGINS "*"
+    ```
+
+2. Restart Ollama application.
+
+
+### Setting environment variables on Linux
+
+If Ollama is run as a systemd service, environment variables should be set using `systemctl`:
+
+1. Edit the systemd service by calling `sudo systemctl edit ollama.service`.
+
+    ```bash
+    sudo systemctl edit ollama.service
+    ```
+
+2. For each environment variable, add a line `Environment` under section `[Service]`:
+
+    ```bash
+    [Service]
+    Environment="OLLAMA_HOST=0.0.0.0"
+    Environment="OLLAMA_ORIGINS=*"
+    ```
+
+3. Save and exit.
+4. Reload `systemd` and restart Ollama:
+
+    ```bash
+    sudo systemctl daemon-reload
+    sudo systemctl restart ollama
+    ```
+
+### Setting environment variables on Docker
+
+If Ollama is run as a Docker container, you can add the environment variables to the `docker run` command.
+
 For further guidance on configuration, consult the [Ollama Official Documentation](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-configure-ollama-server).

package/docs/self-hosting/examples/ollama.zh-CN.mdx

@@ -35,8 +35,69 @@ docker run -d -p 3210:3210 -e OLLAMA_PROXY_URL=http://host.docker.internal:11434
 ## 非本地访问 Ollama
 
 由于 Ollama 默认参数在启动时设置了仅本地访问，所以跨域访问以及端口监听需要进行额外的环境变量设置 `OLLAMA_ORIGINS` 和 `OLLAMA_HOST`。
-```
-set OLLAMA_ORIGINS=*
-set OLLAMA_HOST=:11434
-```
+
+### Ollama 环境变量
+
+    `OLLAMA_HOST`         绑定的主机:端口 (默认 "127.0.0.1:11434")
+    `OLLAMA_ORIGINS`      允许的源的逗号分隔列表。
+    `OLLAMA_MODELS`       模型目录的路径 (默认是 "~/.ollama/models")
+    `OLLAMA_KEEP_ALIVE`   模型在内存中保持加载的持续时间 (默认是 "5m")
+    `OLLAMA_DEBUG`        设置为 1 以启用额外的调试日志
+
+### 在 Windows 上设置环境变量
+
+在 Windows 上，Ollama 继承了您的用户和系统环境变量。
+
+1. 首先通过 Windows 任务栏点击 Ollama 退出程序。
+2. 从控制面板编辑系统环境变量。
+3. 为您的用户账户编辑或新建 Ollama 的环境变量，比如`OLLAMA_HOST`、`OLLAMA_ORIGINS`等。
+4. 点击`OK/应用`保存。
+5. 重新运行`Ollama`。
+
+
+### 在 Mac 上设置环境变量
+
+如果 Ollama 作为 macOS 应用程序运行，你需要使用 `launchctl` 设置环境变量：
+
+1. 对于每个环境变量，调用 `launchctl setenv`。
+
+    ```bash
+    launchctl setenv OLLAMA_HOST "0.0.0.0"
+    launchctl setenv OLLAMA_ORIGINS "*"
+    ```
+
+2. 重启 Ollama 应用程序。
+
+
+### 在 Linux 上设置环境变量
+
+如果 Ollama 作为 systemd 服务运行，应该使用`systemctl`设置环境变量：
+
+1. 通过调用`sudo systemctl edit ollama.service`编辑 systemd 服务。
+
+    ```bash
+    sudo systemctl edit ollama.service
+    ```
+
+2. 对于每个环境变量，在`[Service]`部分下添加`Environment`：
+
+    ```bash
+    [Service]
+    Environment="OLLAMA_HOST=0.0.0.0"
+    Environment="OLLAMA_ORIGINS=*"
+    ```
+
+3. 保存并退出。
+4. 重载`systemd`并重启 Ollama：
+
+    ```bash
+    sudo systemctl daemon-reload
+    sudo systemctl restart ollama
+    ```
+
+### 在 Docker 上设置环境变量
+
+如果 Ollama 作为 Docker 容器运行，你可以将环境变量添加到 `docker run` 命令中。
+
 详细配置方法可以参考 [Ollama 官方文档](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-configure-ollama-server)。
+

package/docs/usage/features/pwa.mdx

@@ -25,8 +25,15 @@ We understand the importance of providing a seamless experience for users in tod
 
 If you are unfamiliar with the installation process of PWA, you can follow the steps below to add LobeChat as a desktop app (also applicable to mobile devices):
 
+## Running on Chrome / Edge
+
+<Callout type={'important'}>
+  On macOS, when using a Chrome-installed PWA, it is required that Chrome be open, otherwise Chrome will automatically open and then launch the PWA app.
+</Callout>
+
 <Steps>
-  ### Run Chrome or Edge browser on your computer
+
+### Run Chrome or Edge browser on your computer
 
 ### Visit the LobeChat webpage
 
@@ -35,3 +42,32 @@ If you are unfamiliar with the installation process of PWA, you can follow the s
 ### Follow the on-screen instructions to complete the PWA installation
 
 </Steps>
+
+## Running on Safari
+
+Safari PWA requires macOS Ventura or later. The PWA installed by Safari does not require Safari to be open; you can directly open the PWA app.
+
+<Steps>
+
+### Run Safari browser on your computer
+
+### Visit the LobeChat webpage
+
+### In the top right corner of the address bar, click the <kbd>Share</kbd> icon
+
+### Click <kbd>Add to Dock</kbd>
+
+### Follow the on-screen instructions to complete the PWA installation
+
+</Steps>
+
+<Callout type={'tip'}>
+  The default installed LobeChat PWA icon has a black background, you can use <kbd>cmd</kbd> + <kbd>i</kbd> to paste the following image to replace it with a white background.
+</Callout>
+
+<Image
+  alt={'PWA White Icon'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/36695271/16ce82cb-49be-4d4d-ac86-4403a1536917'}
+/>

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

@@ -25,8 +25,15 @@ tags:
 
 若您未熟悉 PWA 的安装过程，您可以按照以下步骤将 LobeChat 添加为您的桌面应用（也适用于移动设备）：
 
+## Chrome / Edge 浏览器上运行
+
+<Callout type={'important'}>
+  macOS 下，使用 Chrome 安装的 PWA 时，必须要求 Chrome 是打开状态，否则会自动打开 Chrome 再打开 PWA 应用。
+</Callout>
+
 <Steps>
-  ### 在电脑上运行 Chrome 或 Edge 浏览器
+
+### 在电脑上运行 Chrome 或 Edge 浏览器
 
 ### 访问 LobeChat 网页
 
@@ -35,3 +42,32 @@ tags:
 ### 根据屏幕上的指示完成 PWA 的安装
 
 </Steps>
+
+## Safari 浏览器上运行
+
+Safari PWA 需要 macOS Ventura 或更高版本。Safari 安装的 PWA 并不要求 Safari 是打开状态，可以直接打开 PWA 应用。
+
+<Steps>
+
+### 在电脑上运行 Safari 浏览器
+
+### 访问 LobeChat 网页
+
+### 在地址栏的右上角，单击 <kbd>分享</kbd> 图标
+
+### 点选 <kbd>添加到程序坞</kbd>
+
+### 根据屏幕上的指示完成 PWA 的安装
+
+</Steps>
+
+<Callout type={'tip'}>
+  默认安装的 LobeChat PWA 图标是黑色背景的，您可以在自行使用 <kbd>cmd</kbd> + <kbd>i</kbd> 粘贴如下图片替换为白色背景的。
+</Callout>
+
+<Image
+  alt={'PWA White Icon'}
+  borderless
+  cover
+  src={'https://github.com/lobehub/lobe-chat/assets/36695271/16ce82cb-49be-4d4d-ac86-4403a1536917'}
+/>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "0.148.5",
+  "version": "0.148.7",
   "description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",

package/src/app/settings/sync/components/SystemIcon.tsx

@@ -1,4 +1,4 @@
-import { SiAndroid, SiApple, SiWindows11 } from '@icons-pack/react-simple-icons';
+import {SiAndroid, SiApple, SiBlackberry, SiGooglechrome, SiLinux, SiWindows11} from '@icons-pack/react-simple-icons';
 import { memo } from 'react';
 
 // TODO: 等 simple icons 修复类型，移除 ignore
@@ -7,14 +7,23 @@ const SystemIcon = memo<{ title?: string }>(({ title }) => {
   if (!title) return;
 
   // @ts-ignore
-  if (['Mac OS', 'iOS'].includes(title)) return <SiApple size={32} />;
+  if (['Mac OS', 'iOS', 'iPadOS'].includes(title)) return <SiApple size={32} />;
 
   // @ts-ignore
-  if (title === 'Windows') return <SiWindows11 size={32} />;
+  if (['Windows'].includes(title))return <SiWindows11 size={32} />;
 
   // @ts-ignore
   if (title === 'Android') return <SiAndroid size={32} />;
 
+  // @ts-ignore
+  if (['BlackBerry'].includes(title))return <SiBlackberry size={32} />;
+
+  // @ts-ignore
+  if (title === 'Linux') return <SiLinux size={32} />;
+
+  // @ts-ignore
+  if (title === 'Chrome OS') return <SiGooglechrome size={32} />;
+
   return null;
 });
 

package/src/components/ModelIcon/index.tsx

@@ -1,9 +1,15 @@
 import {
+  Adobe,
+  Ai21,
   Aws,
+  Azure,
   Baichuan,
+  ByteDance,
   ChatGLM,
   Claude,
   Cohere,
+  Dbrx,
+  FishAudio,
   Gemini,
   Gemma,
   Hunyuan,
@@ -13,9 +19,12 @@ import {
   Mistral,
   Moonshot,
   OpenAI,
+  OpenChat,
   OpenRouter,
   Perplexity,
+  Rwkv,
   Spark,
+  Stability,
   Tongyi,
   Wenxin,
   Yi,
@@ -33,33 +42,63 @@ const ModelIcon = memo<ModelProviderIconProps>(({ model: originModel, size = 12
   // lower case the origin model so to better match more model id case
   const model = originModel.toLowerCase();
 
+  // currently supported models, maybe not in its own provider
   if (model.includes('gpt-3')) return <OpenAI.Avatar size={size} type={'gpt3'} />;
   if (model.includes('gpt-4')) return <OpenAI.Avatar size={size} type={'gpt4'} />;
-  if (model.startsWith('glm') || model.includes('chatglm')) return <ChatGLM.Avatar size={size} />;
+  if (model.startsWith('glm') ||
+    model.includes('chatglm'))
+    return <ChatGLM.Avatar size={size} />;
   if (model.includes('claude')) return <Claude.Avatar size={size} />;
   if (model.includes('titan')) return <Aws.Avatar size={size} />;
   if (model.includes('llama')) return <Meta.Avatar size={size} />;
   if (model.includes('llava')) return <LLaVA.Avatar size={size} />;
   if (model.includes('gemini')) return <Gemini.Avatar size={size} />;
   if (model.includes('gemma')) return <Gemma.Avatar size={size} />;
+  if (model.includes('moonshot')) return <Moonshot.Avatar size={size} />;
   if (model.includes('qwen')) return <Tongyi.Avatar background={Tongyi.colorPrimary} size={size} />;
   if (model.includes('minmax')) return <Minimax.Avatar size={size} />;
-  if (model.includes('moonshot')) return <Moonshot.Avatar size={size} />;
-  if (model.includes('baichuan'))
-    return <Baichuan.Avatar background={Baichuan.colorPrimary} size={size} />;
-
-  if (model.includes('mistral') || model.includes('mixtral')) return <Mistral.Avatar size={size} />;
-
-  if (model.includes('pplx') || model.includes('sonar')) return <Perplexity.Avatar size={size} />;
-
+  if (model.includes('mistral') ||
+    model.includes('mixtral'))
+    return <Mistral.Avatar size={size} />;
+  if (model.includes('pplx') ||
+    model.includes('sonar'))
+    return <Perplexity.Avatar size={size} />;
   if (model.includes('yi-')) return <Yi.Avatar size={size} />;
-  if (model.includes('openrouter')) return <OpenRouter.Avatar size={size} />;
-  if (model.includes('command')) return <Cohere.Color size={size} />;
+  if (model.startsWith('openrouter')) return <OpenRouter.Avatar size={size} />; // only for Cinematika and Auto
+  if (model.startsWith('openchat')) return <OpenChat.Avatar size={size} />;
+  if (model.includes('command')) return <Cohere.Avatar size={size} />;
+  if (model.includes('dbrx')) return <Dbrx.Avatar size={size} />;
 
-  if (model.includes('ernie')) return <Wenxin.Avatar size={size} />;
+  // below: To be supported in providers, move up if supported
+  if (model.includes('baichuan'))
+    return <Baichuan.Avatar background={Baichuan.colorPrimary} size={size} />;
+  if (model.includes('rwkv')) return <Rwkv.Avatar size={size} />;
+  if (model.includes('ernie'))
+    return <Wenxin.Avatar size={size} />;
   if (model.includes('spark')) return <Spark.Avatar size={size} />;
   if (model.includes('hunyuan')) return <Hunyuan.Avatar size={size} />;
-  if (model.includes('abab')) return <Minimax.Avatar size={size} />;
+  // ref https://github.com/fishaudio/Bert-VITS2/blob/master/train_ms.py#L702
+  if (model.startsWith('d_') ||
+    model.startsWith('g_') || model.startsWith('wd_'))
+    return <FishAudio.Avatar size={size} />;
+  if (model.includes('skylark')) return <ByteDance.Avatar size={size} />;
+
+  if (
+    model.includes('stable-diffusion') ||
+    model.includes('stable-video') ||
+    model.includes('stable-cascade') ||
+    model.includes('sdxl') ||
+    model.includes('stablelm') ||
+    model.startsWith('stable-') ||
+    model.startsWith('sd3')
+  )
+    return <Stability.Avatar size={size} />;
+
+  if (model.includes('wizardlm')) return <Azure.Avatar size={size} />;
+  if (model.includes('firefly')) return <Adobe.Avatar size={size} />;
+  if (model.includes('jamba') ||
+    model.includes('j2-'))
+    return <Ai21.Avatar size={size} />;
 });
 
 export default ModelIcon;

package/src/components/ModelTag/ModelIcon.tsx

@@ -1,18 +1,32 @@
 import {
+  AdobeFirefly,
+  Ai21,
   Aws,
+  Azure,
   Baichuan,
+  ByteDance,
   ChatGLM,
   Claude,
+  Cohere,
+  Dbrx,
+  FishAudio,
   Gemini,
   Gemma,
+  Hunyuan,
   LLaVA,
   Meta,
   Minimax,
   Mistral,
   Moonshot,
   OpenAI,
+  OpenChat,
+  OpenRouter,
   Perplexity,
+  Rwkv,
+  Spark,
+  Stability,
   Tongyi,
+  Wenxin,
   ZeroOne,
 } from '@lobehub/icons';
 import { memo } from 'react';
@@ -25,8 +39,9 @@ interface ModelIconProps {
 const ModelIcon = memo<ModelIconProps>(({ model, size = 12 }) => {
   if (!model) return;
 
+  // currently supported models, maybe not in its own provider
   if (model.startsWith('gpt')) return <OpenAI size={size} />;
-  if (model.startsWith('glm')) return <ChatGLM size={size} />;
+  if (model.startsWith('glm') || model.includes('chatglm')) return <ChatGLM size={size} />;
   if (model.includes('claude')) return <Claude size={size} />;
   if (model.includes('titan')) return <Aws size={size} />;
   if (model.includes('llama')) return <Meta size={size} />;
@@ -36,10 +51,39 @@ const ModelIcon = memo<ModelIconProps>(({ model, size = 12 }) => {
   if (model.includes('moonshot')) return <Moonshot size={size} />;
   if (model.includes('qwen')) return <Tongyi size={size} />;
   if (model.includes('minmax')) return <Minimax size={size} />;
-  if (model.includes('baichuan')) return <Baichuan size={size} />;
   if (model.includes('mistral') || model.includes('mixtral')) return <Mistral size={size} />;
-  if (model.includes('pplx')) return <Perplexity size={size} />;
-  if (model.startsWith('yi-')) return <ZeroOne size={size} />;
+  if (model.includes('pplx') || model.includes('sonar')) return <Perplexity size={size} />;
+  if (model.includes('yi-')) return <ZeroOne size={size} />;
+  if (model.startsWith('openrouter')) return <OpenRouter size={size} />; // only for Cinematika and Auto
+  if (model.startsWith('openchat')) return <OpenChat size={size} />;
+  if (model.includes('command')) return <Cohere size={size} />;
+  if (model.includes('dbrx')) return <Dbrx size={size} />;
+
+  // below: To be supported in providers, move up if supported
+  if (model.includes('baichuan')) return <Baichuan size={size} />;
+  if (model.includes('rwkv')) return <Rwkv size={size} />;
+  if (model.includes('ernie')) return <Wenxin size={size} />;
+  if (model.includes('spark')) return <Spark size={size} />;
+  if (model.includes('hunyuan')) return <Hunyuan size={size} />;
+  // ref https://github.com/fishaudio/Bert-VITS2/blob/master/train_ms.py#L702
+  if (model.startsWith('d_') || model.startsWith('g_') || model.startsWith('wd_'))
+    return <FishAudio size={size} />;
+  if (model.includes('skylark')) return <ByteDance size={size} />;
+
+  if (
+    model.includes('stable-diffusion') ||
+    model.includes('stable-video') ||
+    model.includes('stable-cascade') ||
+    model.includes('sdxl') ||
+    model.includes('stablelm') ||
+    model.startsWith('stable-') ||
+    model.startsWith('sd3')
+  )
+    return <Stability size={size} />;
+
+  if (model.includes('wizardlm')) return <Azure size={size} />;
+  if (model.includes('firefly')) return <AdobeFirefly size={size} />;
+  if (model.includes('jamba') || model.includes('j2-')) return <Ai21 size={size} />;
 });
 
 export default ModelIcon;

package/src/config/modelProviders/togetherai.ts

@@ -88,7 +88,7 @@ const TogetherAI: ModelProviderCard = {
       enabled: true,
       functionCall: false,
       id: 'Qwen/Qwen1.5-72B-Chat',
-      tokens: 4096,
+      tokens: 32_768,
       vision: false,
     },
   ],