NextChat (ChatGPT Next Web)

English / ??中文

One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4 & Gemini Pro support.

一?免?部署?的跨平台私人 ChatGPT ?用, 支持 GPT3, GPT4 & Gemini Pro 模型。

Web App / Desktop App / Discord / Twitter

??版 / 客?端 / 反?

• Deploy for free with one-click on Vercel in under 1 minute
• Compact client (~5MB) on Linux/Windows/MacOS, download it now
• Fully compatible with self-deployed LLMs, recommended for use with RWKV-Runner or LocalAI
• Privacy first, all data is stored locally in the browser
• Markdown support: LaTex, mermaid, code highlight, etc.
• Responsive design, dark mode and PWA
• Fast first screen loading speed (~100kb), support streaming response
• New in v2: create, share and debug your chat tools with prompt templates (mask)
• Awesome prompts powered by awesome-chatgpt-prompts-zh and awesome-chatgpt-prompts
• Automatically compresses chat history to support long conversations while also saving your tokens
• I18n: English, ??中文, 繁?中文, 日本語, Francais, Espanol, Italiano, Turkce, Deutsch, Ti?ng Vi?t, Русский, ?e?tina, 韓國語, Indonesia

• System Prompt: pin a user defined prompt as system prompt #138
• User Prompt: user can edit and save custom prompts to prompt list
• Prompt Template: create a new chat with pre-defined in-context prompts #993
• Share as image, share to ShareGPT #1741
• Desktop App with tauri
• Self-host Model: Fully compatible with RWKV-Runner , as well as server deployment of LocalAI : llama/gpt4all/rwkv/vicuna/koala/gpt4all-j/cerebras/falcon/dolly etc.
• Plugins: support network search, calculator, any other apis etc. #165

• ?? v2.10.1 support Google Gemini Pro model.
• ?? v2.9.11 you can use azure endpoint now.
• ?? v2.8 now we have a client that runs across all platforms!
• ?? v2.7 let's share conversations as image, or share to ShareGPT!
• ?? v2.0 is released, now you can create prompt templates, turn your ideas into reality! Read this: ChatGPT Prompt Engineering Tips: Zero, One and Few Shot Prompting .

• 在 1 分??使用 Vercel 免?一?部署
• 提供???小（~5MB）的跨平台客?端（Linux/Windows/MacOS）, 下?地址
• 完整的 Markdown 支持：LaTex 公式、Mermaid 流程?、代?高亮等等
• 精心??的 UI，??式??，支持深色模式，支持 PWA
• ?快的首?加?速度（~100kb），支持流式??
• ?私安全，所有?据保存在用???器本地
• ?制角色功能（面具），方便地?建、分享和???的?性化??
• 海量的?置 prompt 列表，?自 中文 和 英文
• 自???上下文聊天??，在?省 Token 的同?支持超???
• 多??言支持：English, ??中文, 繁?中文, 日本語, Espanol, Italiano, Turkce, Deutsch, Ti?ng Vi?t, Русский, ?e?tina, 韓國語, Indonesia
• ?有自己的域名？好上加好，?定后?可在任何地方 无障碍 快速??

• ?每????置系? Prompt #138
• 允?用?自行???置 Prompt 列表
• ?制角色：使用?制角色快速定制新?? #993
• 分享??片，分享到 ShareGPT ?接 #1741
• 使用 tauri 打包?面?用
• 支持自部署的大?言模型：?箱?用 RWKV-Runner ，服?端部署 LocalAI ?目 llama / gpt4all / rwkv / vicuna / koala / gpt4all-j / cerebras / falcon / dolly 等等，或者使用 api-for-open-llm
• ?件机制，支持??搜索、?算器、?用其他平台 api #165

• ?? v2.0 已??布，?在?可以使用面具功能快速?建?制??了！ 了解更多： ChatGPT 提示?高?技能：零次、一次和少?本提示 。
• ?? 想要更方便地???地使用本?目？可以?下?款?面?件： https://github.com/mushan0x0/AI0x0.com
• ?? v2.7 ?在可以???分享??片了，也可以分享到 ShareGPT 的在??接。
• ?? v2.8 ?布了?跨 Linux/Windows/MacOS 的???小的客?端。
• ?? v2.9.11 ?在可以使用自定? Azure 服?了。

??中文 > 如何?始使用

1. Get OpenAI API Key ;
2. Click , remember that CODE is your page password;
3. Enjoy :)

??中文 > 常???

English > FAQ

??中文 > 如何保持代?更新

If you have deployed your own project with just one click following the steps above, you may encounter the issue of "Updates Available" constantly showing up. This is because Vercel will create a new project for you by default instead of forking this project, resulting in the inability to detect updates correctly.

We recommend that you follow the steps below to re-deploy:

• Delete the original repository;
• Use the fork button in the upper right corner of the page to fork this project;
• Choose and deploy in Vercel again, please see the detailed tutorial .

If you encounter a failure of Upstream Sync execution, please manually sync fork once.

After forking the project, due to the limitations imposed by GitHub, you need to manually enable Workflows and Upstream Sync Action on the Actions page of the forked project. Once enabled, automatic updates will be scheduled every hour:

If you want to update instantly, you can check out the GitHub documentation to learn how to synchronize a forked project with upstream code.

You can star or watch this project or follow author to get release notifications in time.

??中文 > 如何增加??密?

This project provides limited access control. Please add an environment variable named CODE on the vercel environment variables page. The value should be passwords separated by comma like this:

code1,code2,code3

After adding or modifying this environment variable, please redeploy the project for the changes to take effect.

??中文 > 如何配置 api key、??密?、接口代理

Access password, separated by comma.

Your openai api key, join multiple api keys with comma.

Default: https://api.openai.com

Examples: http://your-openai-proxy.com

Override openai api request base url.

Specify OpenAI organization ID.

Example: https://{azure-resource-url}/openai/deployments/{deploy-name}

Azure deploy url.

Azure Api Key.

Azure Api Version, find it at Azure Documentation .

Google Gemini Pro Api Key.

Google Gemini Pro Api Url.

anthropic claude Api Key.

anthropic claude Api version.

anthropic claude Api Url.

Default: Empty

If you do not want users to input their own API key, set this value to 1.

Default: Empty

If you do not want users to use GPT-4, set this value to 1.

Default: Empty

If you do want users to query balance, set this value to 1.

Default: Empty

If you want to disable parse settings from url, set this to 1.

Default: Empty Example: +llama,+claude-2,-gpt-3.5-turbo,gpt-4-1106-preview=gpt-4-turbo means add llama, claude-2 to model list, and remove gpt-3.5-turbo from list, and display gpt-4-1106-preview as gpt-4-turbo .

To control custom models, use + to add a custom model, use - to hide a model, use name=displayName to customize model name, separated by comma.

User -all to disable all default models, +all to enable all default models.

You can use this option if you want to increase the number of webdav service addresses you are allowed to access, as required by the format：

• Each address must be a complete endpoint

https://xxxx/yyy

• Multiple addresses are connected by ', '

Customize the default template used to initialize the User Input Preprocessing configuration item in Settings.

NodeJS >= 18, Docker >= 20

??中文 > 如何?行二次??

Before starting development, you must create a new .env.local file at project root, and place your api key into it:

OPENAI_API_KEY=<your api key here>

# if you are not able to access openai service, use this BASE_URL
BASE_URL=https://chatgpt1.nextweb.fun/api/proxy

#
 1. install nodejs and yarn first

#
 2. config local env vars in `.env.local`

#
 3. run

yarn install
yarn dev

??中文 > 如何部署到私人服?器

docker pull yidadaa/chatgpt-next-web

docker run -d -p 3000:3000 \
   -e OPENAI_API_KEY=sk-xxxx \
   -e CODE=your-password \
   yidadaa/chatgpt-next-web

You can start service behind a proxy:

docker run -d -p 3000:3000 \
   -e OPENAI_API_KEY=sk-xxxx \
   -e CODE=your-password \
   -e PROXY_URL=http://localhost:7890 \
   yidadaa/chatgpt-next-web

If your proxy needs password, use:

-e PROXY_URL=
"
http://127.0.0.1:7890 user pass
"

bash 
<(
curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/scripts/setup.sh
)

| ??中文 | English | Italiano | 日本語 | 韓國語

Please go to the [docs][./docs] directory for more documentation instructions.

• Deploy with cloudflare (Deprecated)
• Frequent Ask Questions
• How to add a new translation
• How to use Vercel (No English)
• User Manual (Only Chinese, WIP)

If you want to add a new translation, read this document .

Buy Me a Coffee

?列出捐?金? >= 100RMB 的用?。

@mushan0x0 @ClarenceDan @zhangjia @hoochanlon @relativequantum @desenmeng @webees @chazzhou @hauy @Corwin006 @yankunsong @ypwhs @fxxxchao @hotic @WingCH @jtung4 @micozhu @jhansion @Sha1rholder @AnsonHyq @synwith @piksonGit @ouyangzhiping @wenjiavv @LeXwDeX @Licoy @shangmin2009

MIT