## 1. Project Overview & Quickstart (chatboxai/chatbox)
## File: README.md
[English](README.md) |
[简体中文](./doc/README-CN.md)
Chatbox
(Community Edition)
---
This is the repository for the Chatbox Community Edition, open-sourced under the GPLv3 license.
[Chatbox is going open-source Again!](https://github.com/chatboxai/chatbox/issues/2266)
We regularly sync code from the pro repo to this repo, and vice versa.
## Download
### Desktop
| **Windows** | **MacOS** | **Linux** | |
| --- | --- | --- | --- |
| **Setup.exe** | **Intel** | Apple Silicon | **AppImage** |
### iOS/Android
.APK
For more information: [chatboxai.app](https://chatboxai.app/)
## Quick Start
### For End Users
1. Download the appropriate installer for your platform from the [releases page](https://github.com/chatboxai/chatbox/releases)
2. Install and launch Chatbox
3. Configure your AI provider (OpenAI, Claude, etc.) in settings
4. Start chatting!
### System Requirements
| Platform | Minimum Version | Architecture |
|----------|----------------|--------------|
| Windows | Windows 10 | x64 |
| macOS | macOS 11 (Big Sur) | Intel/Apple Silicon |
| Linux | Ubuntu 20.04+ / AppImage supported distros | x64 |
## Features
### 🤖 AI Model Support
- **Support for Multiple LLM Providers**
:gear: Seamlessly integrate with a variety of cutting-edge language models:
- OpenAI (ChatGPT)
- Azure OpenAI
- Claude
- Google Gemini Pro
- Ollama (enable access to local models like llama2, Mistral, Mixtral, codellama, vicuna, yi, and solar)
- ChatGLM-6B
- **Image Generation with Dall-E-3**
:art: Create the images of your imagination with Dall-E-3.
- **Enhanced Prompting**
:speech_balloon: Advanced prompting features to refine and focus your queries for better responses.
### 🖥️ User Experience
- **Local Data Storage**
:floppy_disk: Your data remains on your device, ensuring it never gets lost and maintains your privacy.
- **No-Deployment Installation Packages**
:package: Get started quickly with downloadable installation packages. No complex setup necessary!
- **Ergonomic UI & Dark Theme**
:new_moon: A user-friendly interface with a night mode option for reduced eye strain during extended use.
- **Keyboard Shortcuts**
:keyboard: Stay productive with shortcuts that speed up your workflow.
- **Streaming Reply**
:arrow_forward: Provide rapid responses to your interactions with immediate, progressive replies.
### 📄 Content & Formatting
- **Markdown, Latex & Code Highlighting**
:scroll: Generate messages with the full power of Markdown and Latex formatting, coupled with syntax highlighting for various programming languages, enhancing readability and presentation.
- **Prompt Library & Message Quoting**
:books: Save and organize prompts for reuse, and quote messages for context in discussions.
### 👥 Collaboration & Sharing
- **Team Collaboration**
:busts_in_silhouette: Collaborate with ease and share OpenAI API resources among your team. [Learn More](./team-sharing/README.md)
### 🌐 Platform Availability
- **Cross-Platform Desktop**
:computer: Chatbox is ready for Windows, Mac, and Linux users.
- **Web Version**
:globe_with_meridians: Use the web application on any device with a browser, anywhere.
- **Mobile Apps**
:phone: Native iOS and Android applications for on-the-go access.
### 🌍 Localization
- **Multilingual Support**
:earth_americas: Catering to a global audience by offering support in multiple languages:
- English
- 简体中文 (Simplified Chinese)
- 繁體中文 (Traditional Chinese)
- 日本語 (Japanese)
- 한국어 (Korean)
- Français (French)
- Deutsch (German)
- Русский (Russian)
- Español (Spanish)
### ✨ More Features
- **And More...**
:sparkles: Constantly enhancing the experience with new features!
## FAQ
- [Frequently Asked Questions](./doc/FAQ.md)
## How to Contribute
We welcome contributions from the community! Here's how you can help make Chatbox better:
### 🐛 Reporting Issues
- Use [GitHub Issues](https://github.com/chatboxai/chatbox/issues) to report bugs or request features
- Before creating a new issue, please search existing issues to avoid duplicates
- Provide detailed information including steps to reproduce, expected behavior, and screenshots if applicable
### 🔧 Pull Requests
1. Fork the repository and create your branch from `main`
2. Make your changes and ensure the code follows our coding standards
3. Test your changes thoroughly
4. Update documentation if needed
5. Submit a pull request with a clear description of the changes
### 🌍 Translations
Help make Chatbox accessible to more people by contributing translations:
- Translation files are located in the `src/locales` directory
- Follow the existing translation format
- Submit a PR with your translation improvements
### 📖 Documentation
- Improve README, API documentation, or user guides
- Fix typos or clarify unclear instructions
- Add examples and tutorials
### 🌟 Other Ways to Contribute
- Star the repository to show your support
- Share Chatbox with others
- Answer questions in [GitHub Discussions](https://github.com/chatboxai/chatbox/discussions)
- Provide feedback and suggestions
**Thank you for contributing! 🙏**
## Development
### Prerequisites
Before you begin, ensure you have the following installed:
- **Node.js** (v20.x – v22.x) - [Download here](https://nodejs.org/)
- **pnpm** (v10.x or later) - Install via `corepack enable && corepack prepare pnpm@latest --activate`
- **Git** - [Download here](https://git-scm.com/)
### Quick Setup
1. **Clone the repository**
```bash
git clone https://github.com/chatboxai/chatbox.git
cd chatbox
```
2. **Install dependencies**
```bash
pnpm install
```
3. **Start development server**
```bash
pnpm run dev
```
The application will start in development mode with hot-reload enabled.
### Build Commands
| Command | Description |
|---------|-------------|
| `pnpm run dev` | Start development server with hot-reload |
| `pnpm run package` | Build and package for current platform |
| `pnpm run package:all` | Build and package for all platforms |
| `pnpm run build` | Build for production without packaging |
| `pnpm run lint` | Run Biome to check code quality |
| `pnpm run test` | Run Vitest test suite |
### Project Structure
```
chatbox/
├── src/
│ ├── main/ # Electron main process
│ ├── renderer/ # React renderer (UI)
│ ├── preload/ # Electron preload scripts
│ └── shared/ # Shared utilities
├── doc/ # Documentation and assets
├── resources/ # App resources and icons
├── team-sharing/ # Team collaboration features
└── package.json # Project configuration
```
### Development Tips
- Use `pnpm run lint` before committing to ensure code quality
- Follow the existing code style and patterns
- Test your changes on both light and dark themes
- Ensure cross-platform compatibility when making UI changes
### Troubleshooting
**Issue**: `pnpm install` fails
- **Solution**: Ensure you're using pnpm (not npm or yarn) and Node.js version is within the required range. Run `corepack enable` if pnpm is not found.
**Issue**: Build fails on Windows
- **Solution**: Run `pnpm config set script-shell "C:\\Program Files\\git\\bin\\bash.exe"` if using Git Bash
**Issue**: Changes not reflecting in development
- **Solution**: Stop the dev server, delete `node_modules/.vite`, and restart
## Star History
[](https://star-history.dera.page/#chatboxai/chatbox&Date)
## Contact
[Email](mailto:hi@chatboxai.com)
## License
[LICENSE](./LICENSE)
---
## File: doc/FAQ.md
# Frequently Asked Questions
If you still haven't found the answer you're looking for, feel free to submit an [Issue](https://github.com/Bin-Huang/chatbox/issues/new/choose) as well.
### 1001
#### Message sending failed, showing `Failed to fetch`?
This issue occurs when Chatbox cannot connect to the AI model server you've set up. Please check your current network environment and make sure it can connect properly to the AI model server.
For OpenAI API users, if you've chosen OpenAI API as the AI model provider (meaning you've selected `OpenAI API` in the AI Provider settings), it's typically because Chatbox cannot access the `API HOST` you've set. By default, Chatbox uses `https://api.openai.com` as the API HOST. Please make sure your current network can access this service.
### 1002
#### Everything was working fine before, but now I keep getting an error: `{"error":{"message":"You exceeded your current quota, please check your plan and billing details`?
If everything was working fine before and now you're unable to use the service, with each message sending attempt resulting in the following error:
```
{"error":{"message":"You exceeded your current quota, please check your plan and billing details.","type":"insufficient_quota","param":null,"code":null}}
```
Please note that this issue is not related to Chatbox. In this situation, it's likely that you're using your own OpenAI API account and your free quota has either been used up or expired (usually due to expiration). You need to log in to your OpenAI account's dashboard and link a credit card to continue using the service. The OpenAI API account has many requirements for credit cards. If your card doesn't meet these requirements, you'll need to resolve this issue yourself (it can be quite frustrating).
**Consider using `Chatbox AI`:** If you don't want to deal with these issues, you can also use Chatbox's built-in `Chatbox AI` service. This service allows you to enjoy AI capabilities without any hassle. Go to the settings page and set the AI Provider to `Chatbox AI`, and you'll see the corresponding options.
### 1003
#### Unable to use GPT-4?
If you select GPT-4 and receive a similar error message when sending messages:
```
{"error":{"message":"The model: gpt-4-32k does not exist","type":"invalid_request_error","param":null,"code":"model_not_found"}}
```
This issue often occurs when you're using your own OpenAI account and have selected the GPT-4 model, but your OpenAI API account does not support GPT-4. As of July 4, 2023, all OpenAI API accounts require a request to be submitted to OpenAI before the GPT-4 model can be used. Here's the application link: https://openai.com/waitlist/gpt-4-api. Please note that even if you're a ChatGPT Plus user, you still need to apply for access to use the GPT-4 API model.
---
## File: doc/FAQ-CN.md
# 常见问题
这里列举了一些最常见的问题和解决方案。如果你依然没有找到答案，也可以提交一个 [Issue](https://github.com/Bin-Huang/chatbox/issues/new/choose)。
### 1001
#### 消息发送失败，提示 `Failed to fetch`？
这是因为 Chatbox 无法连接到你设置的 AI 模型服务器，请检查你当前的网络环境，确保可以正常连接到 AI 模型服务器。
对于 OpenAI API 的用户，如果你选择了 OpenAI API 作为 AI 模型提供方（即设置页的 AI Provider 中选择了 `OpenAI API`），那么一般是 Chatbox 无法访问设置的 `API HOST`。在默认设置下，Chatbox 会使用 `https://api.openai.com` 作为 API HOST，请确保你的当前网络可以访问这个服务。注意，在某些国家和地区是无法直接访问的。
### 1002
#### 以前用的好好的，突然报错 `{"error":{"message":"You exceeded your current quota, please check your plan and billing details.`？
如果你以前使用一切正常，某天之后突然无法使用过，并且每次发送消息都报错：
```
{"error":{"message":"You exceeded your current quota, please check your plan and billing details.","type":"insufficient_quota","param":null,"code":null}}
```
请注意，这个问题和 Chatbox 没有任何关系。这个情况中往往是因为你正在使用自己的 OpenAI API 账户，而你账户中的免费额度已经全部用完或过期了（一般都是因为过期导致的）。你需要自行登录 OpenAI 账户的控制台，绑定一张海外信用卡才能继续使用。OpenAI API 账户对信用卡有很多要求，如果你的信用卡不符合要求，那么你需要自行解决（非常折腾）。
**更推荐使用 `Chatbox AI`：** 如果你不想折腾这些问题，也可以使用 Chatbox 内置的 `Chatbox AI` 服务。这个服务可以让你无需折腾、什么都不用管、轻松使用 AI 能力。前往配置页，将 AI Provider 设置为 `Chatbox AI`，你将看到相应的设置。
### 1003
#### 无法使用 GPT-4？
如果你选择 GPT-4，然后发送消息时得到类似的报错：
```
{"error":{"message":"The model: gpt-4-32k does not exist","type":"invalid_request_error","param":null,"code":"model_not_found"}}
```
这个情况往往是因为你正在使用自己的 OpenAI 账户，你在模型中选择了 GPT-4，但 OpenAI API 账户不支持 GPT-4。截止到 2023 年 07 月 04 日，所有 OpenAI API 账户都需要向 OpenAI 填写申请后才能使用 GPT-4 模型。这里是申请链接： https://openai.com/waitlist/gpt-4-api 。请注意，即使你是 ChatGPT Plus 用户，你也需要申请后才能使用 GPT-4 的 API 模型。
---
## File: doc/README-CN.md
[English](../README.md) |
[简体中文](README-CN.md)
这里是 Chatbox 社区版的代码仓库，以 GPLv3 许可证开源。
[Chatbox 再次开源！](https://github.com/chatboxai/chatbox/issues/2266)
我们定期从专业版仓库同步代码到这个仓库，反之亦然。
### 下载电脑端
| **Windows** | **MacOS** | **Linux** | |
| --- | --- | --- | --- |
| **Setup.exe** | **Intel** | Apple Silicon | **AppImage** |
### 下载移动端
.APK
更多信息请访问: [chatboxai.app](https://chatboxai.app/)
---
Chatbox
(Community Edition)
[](https://www.producthunt.com/posts/chatbox?utm_source=badge-featured&utm_medium=badge&utm_souce=badge-chatbox)
## 特性
- **本地数据存储**
:floppy_disk: 您的数据保留在您的设备上，确保数据永不丢失并保护您的隐私。
- **无需部署、直接安装的安装包**
:package: 通过可下载的安装包快速开始使用。无需复杂设置！
- **支持多个 LLM 提供商**
:gear: 无缝集成多种 AI 模型：
- OpenAI (ChatGPT)
- Azure OpenAI
- Claude
- Google Gemini Pro
- Ollama (启用对本地模型的访问，如 llama2、Mistral、Mixtral、codellama、vicuna、yi 和 solar)
- ChatGLM-6B
- **使用 Dall-E-3 生成图像**
:art: 使用 Dall-E-3 创建您想象中的图像。
- **增强提示**
:speech_balloon: 高级提示功能，精炼并聚焦您的查询以获得更好的响应。
- **键盘快捷键**
:keyboard: 使用加速您工作流程的快捷键保持高效。
- **Markdown、Latex 和代码高亮**
:scroll: 使用 Markdown 和 Latex 的全部功能生成消息，并结合各种编程语言的语法高亮，提高可读性和呈现效果。
- **提示库和消息引用**
:books: 保存和组织提示以供重复使用，并引用消息以在讨论中提供上下文。
- **流式回复**
:arrow_forward: 通过即时、渐进式回复快速响应您的互动。
- **人体工程学 UI 和深色主题**
:new_moon: 用户友好的界面，带有夜间模式选项，减少长时间使用时的眼睛疲劳。
- **团队协作**
:busts_in_silhouette: 轻松协作并在团队中共享 OpenAI API 资源。[了解更多](../team-sharing/README.md)
- **跨平台可用性**
:computer: 聊天盒已为 Windows、Mac、Linux 用户准备就绪。
- **通过 Web 版本随处访问**
:globe_with_meridians: 在任何设备上使用带有浏览器的 Web 应用程序，随时随地。
- **iOS 和 Android**
:phone: 使用移动应用程序，随时随地在您的指尖上带来这种能力。
- **多语言支持**
:earth_americas: 通过提供多种语言的支持，迎合全球受众：
- English
- 简体中文 (Simplified Chinese)
- 繁體中文 (Traditional Chinese)
- 日本語 (Japanese)
- 한국어 (Korean)
- Français (French)
- Deutsch (German)
- Русский (Russian)
- **更多...**
:sparkles: 不断增强体验，加入新功能！
## 常见问题解答
- [常见问题](./FAQ-CN.md)
## 如何贡献
欢迎任何形式的贡献，包括但不限于：
- 提交问题
- 提交拉取请求
- 提交功能请求
- 提交错误报告
- 提交文档修订
- 提交翻译
- 提交任何其他形式的贡献
## 构建指南
1. 从 Github 克隆仓库
```bash
git clone https://github.com/chatboxai/chatbox.git
```
2. 安装所需的依赖
```bash
npm install
```
3. 启动应用程序（开发模式）
```bash
npm run dev
```
4. 构建应用程序，为当前平台打包安装程序
```bash
npm run package
```
5. 构建应用程序，为所有平台打包安装程序
```bash
npm run package:all
```
## Star History
[](https://star-history.dera.page/#chatboxai/chatbox&Date)
## 联系方式
[Twitter](https://x.com/ChatboxAI_HQ) | [电子邮件](mailto:hi@chatboxai.com)
---
## File: team-sharing/README.md
# Chatbox Team Sharing
English | [中文介绍](./README-CN.md)
Chatbox allows your team members to share the resources of the same OpenAI API account without exposing your API KEY.
The following tutorial will help you quickly set up a shared server. It may involve server login, command-line input, etc. If you are not familiar with these operations, you can ask your technical colleague for help or inquire with ChatGPT. Trust me, it's not difficult.
## 1. Prepare a Server
You can launch a cloud server on platforms such as AWS, Google Cloud, Digital Ocean, Vultr, Oracle Cloud, etc. Please note that the server's network must be able to access openai.com.
## 2. Environment Installation
Log into your server and execute the following command:
```shell
curl -fsSL https://get.docker.com -o get-docker.sh
sh get-docker.sh
```
## 3. Start the Chatbox Shared Server (HTTP)
- Replace `` with your OpenAI API KEY.
- Run the following command to start the server.
```shell
docker run -p 80:80 -p 443:443 \
-v ./caddy_config:/config -v ./caddy_data:/data \
-e KEY= \
bensdocker/chatbox-team
```
Example:
```
docker run -p 80:80 -p 443:443 \
-v ./caddy_config:/config -v ./caddy_data:/data \
-e KEY=sk-xxxxxxxxxxxxxxxxxxx \
bensdocker/chatbox-team
```
## 4. Start the Chatbox Shared Server (HTTPS, recommended)
If you have a domain name, you can use HTTPS to start the server, so that all conversation messages are encrypted as ciphertext during network transmission, which is more secure in terms of privacy.
- Map the domain to this server (and wait for five minutes for it to take effect);
- Replace `` with your domain name;
- Replace `` with your OpenAI API KEY;
- Execute the following command to start the server.
```shell
docker run -p 80:80 -p 443:443 \
-v ./caddy_config:/config -v ./caddy_data:/data \
-e HOST= \
-e KEY= \
bensdocker/chatbox-team
```
Example:
```
docker run -p 80:80 -p 443:443 \
-v ./caddy_config:/config -v ./caddy_data:/data \
-e HOST=proxy.chatbox.run \
-e KEY=sk-xxxxxxxxxxxxxxxxxx \
bensdocker/chatbox-team
```
## 5. Share the Server Address
- If you run with HTTP, the address is `http://:80`;
- If you run with HTTPS, the address is `https://`;
Share the server address with your team members. They only need to fill in this address in the API Host field in Chatbox settings, without filling in the API KEY, to share the OpenAI API resources.
---
## File: team-sharing/README-CN.md
# Chatbox 团队共享功能
[English](./README.md) | 中文介绍
Chatbox 可以让你的团队成员共享同一个 OpenAI API 账号的资源，同时不会暴露你的 API KEY。
下面的教程将帮助你快速搭建一个共享服务器。
接下来可能涉及到服务器登录、命令行输入等操作，如果你不熟悉这些操作，可以请你的技术同事帮忙，或者询问 ChatGPT。相信我，这并不困难。
## 1. 准备一台服务器
你可以在 AWS、Google Cloud、Digital Ocean、或腾讯云海外等云平台上启动一个云服务器。
请注意服务器的网络环境必须可以正常访问 `openai.com`。
## 2. 环境安装
登陆你的服务器，执行下面的命令
```shell
curl -fsSL https://get.docker.com -o get-docker.sh
sh get-docker.sh
```
## 3. 启动 Chatbox 共享服务器（HTTP）
- 将下面 `` 替换成你的 OpenAI API KEY。
- 执行下面的命令，启动服务器。
```shell
docker run -p 80:80 -p 443:443 \
-v ./caddy_config:/config -v ./caddy_data:/data \
-e KEY= \
bensdocker/chatbox-team
```
示例：
```shell
docker run -p 80:80 -p 443:443 \
-v ./caddy_config:/config -v ./caddy_data:/data \
-e KEY=sk-xxxxxxxxxxxxxxxxxxx \
bensdocker/chatbox-team
```
## 4. 启动 Chatbox 共享服务器（HTTPS，推荐）
如果你有一个域名，那么可以使用 HTTPS 来启动服务器，这样所有的对话消息在网络传输时都以密文加密，在隐私上更安全。
- 让你的域名解析到这台服务器（并等待五分钟生效）；
- 将下面 `` 替换成你域名；
- 将下面 `` 替换成你的 OpenAI API KEY；
- 执行下面的命令，启动服务器。
```shell
docker run -p 80:80 -p 443:443 \
-v ./caddy_config:/config -v ./caddy_data:/data \
-e HOST= \
-e KEY= \
bensdocker/chatbox-team
```
示例：
```shell
docker run -p 80:80 -p 443:443 \
-v ./caddy_config:/config -v ./caddy_data:/data \
-e HOST=proxy.chatbox.run \
-e KEY=sk-xxxxxxxxxxxxxxxxxx \
bensdocker/chatbox-team
```
## 5. 分享服务器地址
- 如果你启动的是 HTTP，那么地址是 `http://<你的服务器IP>:80`；
- 如果你启动的是 HTTPS，那么地址是 `https://<你的域名>`。
向你的团队成员分享服务器地址。他们只需要在 Chatbox 设置中的 `API Host` 中填入地址，**不需要填写 API KEY**，就可以共享 OpenAI API 资源了。
## 2. Official Technical Reference & Guides (chatboxai/chatbox-docs)
---
icon: box
---
# 项目介绍
媒体账号：
* [小红书](https://www.xiaohongshu.com/user/profile/67b581b6000000000e01d11f)
* [Twitter](https://x.com/ChatboxAI_HQ)
***
Chatbox AI是一款集多模型对话、文件解析、AI绘图、代码生成等功能于一体的全能AI助手，支持Windows、Mac、Linux、iOS、Android 及网页全平台。凭借简洁直观的界面设计、强大的本地化处理能力和开箱即用的云端服务，Chatbox AI 已成为提升工作效率的首选工具。
## 核心功能与特色
### **1. 智能对话系统**
* **多模型对比**：支持同时连接 ChatGPT 4o/Claude 3.5/DeepSeek 等先进模型，自由切换体验不同 AI 风格
* **上下文记忆**：自动保存完整对话历史，支持 Markdown/HTML/TXT 多种格式导出
* **个性化设置**：可自定义温度、最大 token 等参数，精准控制 AI 输出
### **2. 生产力增强套件**
* **文件理解**：直接解析PDF/Word/Excel/图片中的内容
* **代码专家**：提供类 Claude Artifacts 的实时代码预览能力
* **实时联网**：一键获取最新资讯、股票行情等网络数据，回答始终与时俱进
### **3. 创意可视化工具**
* **AI绘图**：通过自然语言描述生成高质量图像（每月免费额度）
* **图表生成**：支持将数据转化为可视化图表，支持 LaTeX 公式渲染
* **多格式渲染**：完美呈现 Markdown、HTML、数学公式等专业内容
### **4. 企业级数据管理**
* **本地优先**：所有对话记录和文件默认存储在用户设备，保障数据主权
## 技术优势
* **零门槛体验**：无需技术背景，安装即可享受 AI 生产力
* **持续进化**：同步更新模型库和功能模块，保持技术前沿性
## 适用场景
* **学术研究**：快速解析论文/教材，生成文献综述
* **内容创作**：辅助写作、翻译、社交媒体文案生成
* **开发编程**：代码生成/调试/文档编写全流程支持
* **商业分析**：自动处理报表数据，生成可视化洞察