diff --git a/.env.template b/.env.template index 25addf2b3e5..96dedddc8aa 100644 --- a/.env.template +++ b/.env.template @@ -1,12 +1,20 @@ # Your openai api key. (required) OPENAI_API_KEY=sk-xxxx +# DeepSeek Api Key. (Optional) +DEEPSEEK_API_KEY= + # Access password, separated by comma. (optional) CODE=your-password # You can start service behind a proxy. (optional) PROXY_URL=http://localhost:7890 +# Enable MCP functionality (optional) +# Default: Empty (disabled) +# Set to "true" to enable MCP functionality +ENABLE_MCP= + # (optional) # Default: Empty # Google Gemini Pro API key, set if you want to use Google Gemini Pro API. @@ -66,4 +74,16 @@ ANTHROPIC_API_VERSION= ANTHROPIC_URL= ### (optional) -WHITE_WEBDEV_ENDPOINTS= \ No newline at end of file +WHITE_WEBDAV_ENDPOINTS= + +### siliconflow Api key (optional) +SILICONFLOW_API_KEY= + +### siliconflow Api url (optional) +SILICONFLOW_URL= + +### 302.AI Api key (optional) +AI302_API_KEY= + +### 302.AI Api url (optional) +AI302_URL= diff --git a/.eslintignore b/.eslintignore index 08975255475..61e76e59ae5 100644 --- a/.eslintignore +++ b/.eslintignore @@ -1 +1,3 @@ -public/serviceWorker.js \ No newline at end of file +public/serviceWorker.js +app/mcp/mcp_config.json +app/mcp/mcp_config.default.json \ No newline at end of file diff --git a/.eslintrc.json b/.eslintrc.json index d229e86f250..5b5e88e67aa 100644 --- a/.eslintrc.json +++ b/.eslintrc.json @@ -1,4 +1,7 @@ { "extends": "next/core-web-vitals", - "plugins": ["prettier"] + "plugins": ["prettier", "unused-imports"], + "rules": { + "unused-imports/no-unused-imports": "warn" + } } diff --git a/.github/workflows/deploy_preview.yml b/.github/workflows/deploy_preview.yml index bdbb78c27c5..b988452433b 100644 --- a/.github/workflows/deploy_preview.yml +++ b/.github/workflows/deploy_preview.yml @@ -3,9 +3,7 @@ name: VercelPreviewDeployment on: pull_request_target: types: - - opened - - synchronize - - reopened + - review_requested env: VERCEL_TEAM: ${{ secrets.VERCEL_TEAM }} @@ -49,7 +47,7 @@ jobs: run: npm install --global vercel@latest - name: Cache dependencies - uses: actions/cache@v2 + uses: actions/cache@v4 id: cache-npm with: path: ~/.npm diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml new file mode 100644 index 00000000000..faf7205d9cb --- /dev/null +++ b/.github/workflows/test.yml @@ -0,0 +1,39 @@ +name: Run Tests + +on: + push: + branches: + - main + tags: + - "!*" + pull_request: + types: + - review_requested + +jobs: + test: + runs-on: ubuntu-latest + + steps: + - name: Checkout repository + uses: actions/checkout@v4 + + - name: Set up Node.js + uses: actions/setup-node@v3 + with: + node-version: 18 + cache: "yarn" + + - name: Cache node_modules + uses: actions/cache@v4 + with: + path: node_modules + key: ${{ runner.os }}-node_modules-${{ hashFiles('**/yarn.lock') }} + restore-keys: | + ${{ runner.os }}-node_modules- + + - name: Install dependencies + run: yarn install + + - name: Run Jest tests + run: yarn test:ci diff --git a/.gitignore b/.gitignore index 2ff556f646e..b1c2bfefad3 100644 --- a/.gitignore +++ b/.gitignore @@ -46,3 +46,6 @@ dev *.key.pub masks.json + +# mcp config +app/mcp/mcp_config.json diff --git a/Dockerfile b/Dockerfile index ae9a17cddbd..d3e4193eef2 100644 --- a/Dockerfile +++ b/Dockerfile @@ -34,12 +34,16 @@ ENV PROXY_URL="" ENV OPENAI_API_KEY="" ENV GOOGLE_API_KEY="" ENV CODE="" +ENV ENABLE_MCP="" COPY --from=builder /app/public ./public COPY --from=builder /app/.next/standalone ./ COPY --from=builder /app/.next/static ./.next/static COPY --from=builder /app/.next/server ./.next/server +RUN mkdir -p /app/app/mcp && chmod 777 /app/app/mcp +COPY --from=builder /app/app/mcp/mcp_config.default.json /app/app/mcp/mcp_config.json + EXPOSE 3000 CMD if [ -n "$PROXY_URL" ]; then \ diff --git a/LICENSE b/LICENSE index 047f9431e7d..4864ab00d2c 100644 --- a/LICENSE +++ b/LICENSE @@ -1,6 +1,6 @@ MIT License -Copyright (c) 2023-2024 Zhang Yifei +Copyright (c) 2023-2025 NextChat Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal diff --git a/README.md b/README.md index c8b158956b3..01a223d3b63 100644 --- a/README.md +++ b/README.md @@ -1,42 +1,66 @@
- - icon + + icon -

NextChat (ChatGPT Next Web)

+

NextChat

English / [简体中文](./README_CN.md) -One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4 & Gemini Pro support. +ChatGPTNextWeb%2FChatGPT-Next-Web | Trendshift -一键免费部署你的跨平台私人 ChatGPT 应用, 支持 GPT3, GPT4 & Gemini Pro 模型。 +✨ Light and Fast AI Assistant,with Claude, DeepSeek, GPT4 & Gemini Pro support. +[![Saas][Saas-image]][saas-url] [![Web][Web-image]][web-url] [![Windows][Windows-image]][download-url] [![MacOS][MacOS-image]][download-url] [![Linux][Linux-image]][download-url] -[Web App](https://app.nextchat.dev/) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Discord](https://discord.gg/YCkeafCafC) / [Enterprise Edition](#enterprise-edition) / [Twitter](https://twitter.com/NextChatDev) +[NextChatAI](https://nextchat.club?utm_source=readme) / [iOS APP](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [Web App Demo](https://app.nextchat.club) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Enterprise Edition](#enterprise-edition) -[网页版](https://app.nextchat.dev/) / [客户端](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [企业版](#%E4%BC%81%E4%B8%9A%E7%89%88) / [反馈](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) - -[web-url]: https://app.nextchat.dev/ +[saas-url]: https://nextchat.club?utm_source=readme +[saas-image]: https://img.shields.io/badge/NextChat-Saas-green?logo=microsoftedge +[web-url]: https://app.nextchat.club/ [download-url]: https://github.com/Yidadaa/ChatGPT-Next-Web/releases [Web-image]: https://img.shields.io/badge/Web-PWA-orange?logo=microsoftedge [Windows-image]: https://img.shields.io/badge/-Windows-blue?logo=windows [MacOS-image]: https://img.shields.io/badge/-MacOS-black?logo=apple [Linux-image]: https://img.shields.io/badge/-Linux-333?logo=ubuntu -[Deploy on Zeabur](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Deploy on Zeabur](https://zeabur.com/templates/ZBUEFA) [Open in Gitpod](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) +[Deploy on Zeabur](https://zeabur.com/templates/ZBUEFA) [Deploy on Vercel](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Open in Gitpod](https://gitpod.io/#https://github.com/ChatGPTNextWeb/NextChat) -[](https://monica.im/?utm=nxcrp) +[](https://monica.im/?utm=nxcrp)
+## ❤️ Sponsor AI API + + + icon + + +[302.AI](https://302.ai/) is a pay-as-you-go AI application platform that offers the most comprehensive AI APIs and online applications available. + +## 🥳 Cheer for NextChat iOS Version Online! + +> [👉 Click Here to Install Now](https://apps.apple.com/us/app/nextchat-ai/id6743085599) + +> [❤️ Source Code Coming Soon](https://github.com/ChatGPTNextWeb/NextChat-iOS) + +![Github iOS Image](https://github.com/user-attachments/assets/e0aa334f-4c13-4dc9-8310-e3b09fa4b9f3) + +## 🫣 NextChat Support MCP ! + +> Before build, please set env ENABLE_MCP=true + + + ## Enterprise Edition Meeting Your Company's Privatization and Customization Deployment Requirements: + - **Brand Customization**: Tailored VI/UI to seamlessly align with your corporate brand image. - **Resource Integration**: Unified configuration and management of dozens of AI resources by company administrators, ready for use by team members. - **Permission Control**: Clearly defined member permissions, resource permissions, and knowledge base permissions, all controlled via a corporate-grade Admin Panel. @@ -47,20 +71,11 @@ Meeting Your Company's Privatization and Customization Deployment Requirements: For enterprise inquiries, please contact: **business@nextchat.dev** -## 企业版 - -满足企业用户私有化部署和个性化定制需求: -- **品牌定制**:企业量身定制 VI/UI,与企业品牌形象无缝契合 -- **资源集成**:由企业管理人员统一配置和管理数十种 AI 资源,团队成员开箱即用 -- **权限管理**:成员权限、资源权限、知识库权限层级分明,企业级 Admin Panel 统一控制 -- **知识接入**:企业内部知识库与 AI 能力相结合,比通用 AI 更贴近企业自身业务需求 -- **安全审计**:自动拦截敏感提问,支持追溯全部历史对话记录,让 AI 也能遵循企业信息安全规范 -- **私有部署**:企业级私有部署,支持各类主流私有云部署,确保数据安全和隐私保护 -- **持续更新**:提供多模态、智能体等前沿能力持续更新升级服务,常用常新、持续先进 +## Screenshots -企业版咨询: **business@nextchat.dev** +![Settings](./docs/images/settings.png) - +![More](./docs/images/more.png) ## Features @@ -93,60 +108,23 @@ For enterprise inquiries, please contact: **business@nextchat.dev** - [x] Artifacts: Easily preview, copy and share generated content/webpages through a separate window [#5092](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/pull/5092) - [x] Plugins: support network search, calculator, any other apis etc. [#165](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/165) [#5353](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5353) - [x] network search, calculator, any other apis etc. [#165](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/165) [#5353](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5353) +- [x] Supports Realtime Chat [#5672](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5672) - [ ] local knowledge base ## What's New +- 🚀 v2.15.8 Now supports Realtime Chat [#5672](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5672) +- 🚀 v2.15.4 The Application supports using Tauri fetch LLM API, MORE SECURITY! [#5379](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5379) - 🚀 v2.15.0 Now supports Plugins! Read this: [NextChat-Awesome-Plugins](https://github.com/ChatGPTNextWeb/NextChat-Awesome-Plugins) -- 🚀 v2.14.0 Now supports Artifacts & SD +- 🚀 v2.14.0 Now supports Artifacts & SD - 🚀 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](https://www.allabtai.com/prompt-engineering-tips-zero-one-and-few-shot-prompting/). -## 主要功能 - -- 在 1 分钟内使用 Vercel **免费一键部署** -- 提供体积极小(~5MB)的跨平台客户端(Linux/Windows/MacOS), [下载地址](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) -- 完整的 Markdown 支持:LaTex 公式、Mermaid 流程图、代码高亮等等 -- 精心设计的 UI,响应式设计,支持深色模式,支持 PWA -- 极快的首屏加载速度(~100kb),支持流式响应 -- 隐私安全,所有数据保存在用户浏览器本地 -- 预制角色功能(面具),方便地创建、分享和调试你的个性化对话 -- 海量的内置 prompt 列表,来自[中文](https://github.com/PlexPt/awesome-chatgpt-prompts-zh)和[英文](https://github.com/f/awesome-chatgpt-prompts) -- 自动压缩上下文聊天记录,在节省 Token 的同时支持超长对话 -- 多国语言支持:English, 简体中文, 繁体中文, 日本語, Español, Italiano, Türkçe, Deutsch, Tiếng Việt, Русский, Čeština, 한국어, Indonesia -- 拥有自己的域名?好上加好,绑定后即可在任何地方**无障碍**快速访问 - -## 开发计划 - -- [x] 为每个对话设置系统 Prompt [#138](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/138) -- [x] 允许用户自行编辑内置 Prompt 列表 -- [x] 预制角色:使用预制角色快速定制新对话 [#993](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/993) -- [x] 分享为图片,分享到 ShareGPT 链接 [#1741](https://github.com/Yidadaa/ChatGPT-Next-Web/pull/1741) -- [x] 使用 tauri 打包桌面应用 -- [x] 支持自部署的大语言模型:开箱即用 [RWKV-Runner](https://github.com/josStorer/RWKV-Runner) ,服务端部署 [LocalAI 项目](https://github.com/go-skynet/LocalAI) llama / gpt4all / rwkv / vicuna / koala / gpt4all-j / cerebras / falcon / dolly 等等,或者使用 [api-for-open-llm](https://github.com/xusenlinzy/api-for-open-llm) -- [x] Artifacts: 通过独立窗口,轻松预览、复制和分享生成的内容/可交互网页 [#5092](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/pull/5092) -- [x] 插件机制,支持`联网搜索`、`计算器`、调用其他平台 api [#165](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/165) [#5353](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5353) - - [x] 支持联网搜索、计算器、调用其他平台 api [#165](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/165) [#5353](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5353) - - [ ] 本地知识库 - -## 最新动态 - -- 🚀 v2.15.0 现在支持插件功能了!了解更多:[NextChat-Awesome-Plugins](https://github.com/ChatGPTNextWeb/NextChat-Awesome-Plugins) -- 🚀 v2.14.0 现在支持 Artifacts & SD 了。 -- 🚀 v2.10.1 现在支持 Gemini Pro 模型。 -- 🚀 v2.9.11 现在可以使用自定义 Azure 服务了。 -- 🚀 v2.8 发布了横跨 Linux/Windows/MacOS 的体积极小的客户端。 -- 🚀 v2.7 现在可以将会话分享为图片了,也可以分享到 ShareGPT 的在线链接。 -- 🚀 v2.0 已经发布,现在你可以使用面具功能快速创建预制对话了! 了解更多: [ChatGPT 提示词高阶技能:零次、一次和少样本提示](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/138)。 -- 💡 想要更方便地随时随地使用本项目?可以试下这款桌面插件:https://github.com/mushan0x0/AI0x0.com - ## Get Started -> [简体中文 > 如何开始使用](./README_CN.md#开始使用) - 1. Get [OpenAI API Key](https://platform.openai.com/account/api-keys); 2. Click [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FYidadaa%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=chatgpt-next-web&repository-name=ChatGPT-Next-Web), remember that `CODE` is your page password; @@ -154,14 +132,10 @@ For enterprise inquiries, please contact: **business@nextchat.dev** ## FAQ -[简体中文 > 常见问题](./docs/faq-cn.md) - [English > FAQ](./docs/faq-en.md) ## Keep Updated -> [简体中文 > 如何保持代码更新](./README_CN.md#保持更新) - 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: @@ -172,7 +146,7 @@ We recommend that you follow the steps below to re-deploy: ### Enable Automatic Updates -> If you encounter a failure of Upstream Sync execution, please manually sync fork once. +> If you encounter a failure of Upstream Sync execution, please [manually update code](./README.md#manually-updating-code). 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: @@ -188,8 +162,6 @@ You can star or watch this project or follow author to get release notifications ## Access Password -> [简体中文 > 如何增加访问密码](./README_CN.md#配置页面访问密码) - 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: ``` @@ -200,8 +172,6 @@ After adding or modifying this environment variable, please redeploy the project ## Environment Variables -> [简体中文 > 如何配置 api key、访问密码、接口代理](./README_CN.md#环境变量) - ### `CODE` (optional) Access password, separated by comma. @@ -296,6 +266,22 @@ iflytek Api Key. iflytek Api Secret. +### `CHATGLM_API_KEY` (optional) + +ChatGLM Api Key. + +### `CHATGLM_URL` (optional) + +ChatGLM Api Url. + +### `DEEPSEEK_API_KEY` (optional) + +DeepSeek Api Key. + +### `DEEPSEEK_URL` (optional) + +DeepSeek Api Url. + ### `HIDE_USER_API_KEY` (optional) > Default: Empty @@ -329,22 +315,32 @@ To control custom models, use `+` to add a custom model, use `-` to hide a model User `-all` to disable all default models, `+all` to enable all default models. -For Azure: use `modelName@azure=deploymentName` to customize model name and deployment name. -> Example: `+gpt-3.5-turbo@azure=gpt35` will show option `gpt35(Azure)` in model list. -> If you only can use Azure model, `-all,+gpt-3.5-turbo@azure=gpt35` will `gpt35(Azure)` the only option in model list. +For Azure: use `modelName@Azure=deploymentName` to customize model name and deployment name. + +> Example: `+gpt-3.5-turbo@Azure=gpt35` will show option `gpt35(Azure)` in model list. +> If you only can use Azure model, `-all,+gpt-3.5-turbo@Azure=gpt35` will `gpt35(Azure)` the only option in model list. For ByteDance: use `modelName@bytedance=deploymentName` to customize model name and deployment name. + > Example: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx` will show option `Doubao-lite-4k(ByteDance)` in model list. ### `DEFAULT_MODEL` (optional) Change default model -### `WHITE_WEBDEV_ENDPOINTS` (optional) +### `VISION_MODELS` (optional) + +> Default: Empty +> Example: `gpt-4-vision,claude-3-opus,my-custom-model` means add vision capabilities to these models in addition to the default pattern matches (which detect models containing keywords like "vision", "claude-3", "gemini-1.5", etc). + +Add additional models to have vision capabilities, beyond the default pattern matching. Multiple models should be separated by commas. + +### `WHITE_WEBDAV_ENDPOINTS` (optional) 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` + +- Each address must be a complete endpoint + > `https://xxxx/yyy` - Multiple addresses are connected by ', ' ### `DEFAULT_INPUT_TEMPLATE` (optional) @@ -359,14 +355,32 @@ Stability API key. Customize Stability API url. +### `ENABLE_MCP` (optional) + +Enable MCP(Model Context Protocol)Feature + +### `SILICONFLOW_API_KEY` (optional) + +SiliconFlow API Key. + +### `SILICONFLOW_URL` (optional) + +SiliconFlow API URL. + +### `AI302_API_KEY` (optional) + +302.AI API Key. + +### `AI302_URL` (optional) + +302.AI API URL. + ## Requirements NodeJS >= 18, Docker >= 20 ## Development -> [简体中文 > 如何进行二次开发](./README_CN.md#开发) - [![Open in Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) Before starting development, you must create a new `.env.local` file at project root, and place your api key into it: @@ -390,8 +404,6 @@ yarn dev ## Deployment -> [简体中文 > 如何部署到私人服务器](./README_CN.md#部署) - ### Docker (Recommended) ```shell @@ -419,6 +431,16 @@ If your proxy needs password, use: -e PROXY_URL="http://127.0.0.1:7890 user pass" ``` +If enable MCP, use: + +``` +docker run -d -p 3000:3000 \ + -e OPENAI_API_KEY=sk-xxxx \ + -e CODE=your-password \ + -e ENABLE_MCP=true \ + yidadaa/chatgpt-next-web +``` + ### Shell ```shell @@ -439,12 +461,6 @@ bash <(curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/s - [How to use Vercel (No English)](./docs/vercel-cn.md) - [User Manual (Only Chinese, WIP)](./docs/user-manual-cn.md) -## Screenshots - -![Settings](./docs/images/settings.png) - -![More](./docs/images/more.png) - ## Translation If you want to add a new translation, read this [document](./docs/translation.md). @@ -455,38 +471,6 @@ If you want to add a new translation, read this [document](./docs/translation.md ## Special Thanks -### Sponsor - -> 仅列出捐赠金额 >= 100RMB 的用户。 - -[@mushan0x0](https://github.com/mushan0x0) -[@ClarenceDan](https://github.com/ClarenceDan) -[@zhangjia](https://github.com/zhangjia) -[@hoochanlon](https://github.com/hoochanlon) -[@relativequantum](https://github.com/relativequantum) -[@desenmeng](https://github.com/desenmeng) -[@webees](https://github.com/webees) -[@chazzhou](https://github.com/chazzhou) -[@hauy](https://github.com/hauy) -[@Corwin006](https://github.com/Corwin006) -[@yankunsong](https://github.com/yankunsong) -[@ypwhs](https://github.com/ypwhs) -[@fxxxchao](https://github.com/fxxxchao) -[@hotic](https://github.com/hotic) -[@WingCH](https://github.com/WingCH) -[@jtung4](https://github.com/jtung4) -[@micozhu](https://github.com/micozhu) -[@jhansion](https://github.com/jhansion) -[@Sha1rholder](https://github.com/Sha1rholder) -[@AnsonHyq](https://github.com/AnsonHyq) -[@synwith](https://github.com/synwith) -[@piksonGit](https://github.com/piksonGit) -[@ouyangzhiping](https://github.com/ouyangzhiping) -[@wenjiavv](https://github.com/wenjiavv) -[@LeXwDeX](https://github.com/LeXwDeX) -[@Licoy](https://github.com/Licoy) -[@shangmin2009](https://github.com/shangmin2009) - ### Contributors diff --git a/README_CN.md b/README_CN.md index beed396c5aa..f4c441ad006 100644 --- a/README_CN.md +++ b/README_CN.md @@ -6,17 +6,26 @@

NextChat

-一键免费部署你的私人 ChatGPT 网页应用,支持 GPT3, GPT4 & Gemini Pro 模型。 +一键免费部署你的私人 ChatGPT 网页应用,支持 Claude, GPT4 & Gemini Pro 模型。 -[企业版](#%E4%BC%81%E4%B8%9A%E7%89%88) /[演示 Demo](https://chat-gpt-next-web.vercel.app/) / [反馈 Issues](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) / [加入 Discord](https://discord.gg/zrhvHCr79N) +[NextChatAI](https://nextchat.club?utm_source=readme) / [企业版](#%E4%BC%81%E4%B8%9A%E7%89%88) / [演示 Demo](https://chat-gpt-next-web.vercel.app/) / [反馈 Issues](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) / [加入 Discord](https://discord.gg/zrhvHCr79N) -[Deploy on Zeabur](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Deploy on Zeabur](https://zeabur.com/templates/ZBUEFA) [Open in Gitpod](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) +[Deploy on Zeabur](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Deploy on Zeabur](https://zeabur.com/templates/ZBUEFA) [Open in Gitpod](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) +## Sponsor AI API + +
+ icon + + +[302.AI](https://302.ai/) 是一个按需付费的AI应用平台,提供市面上最全的AI API和AI在线应用。 + ## 企业版 满足您公司私有化部署和定制需求 + - **品牌定制**:企业量身定制 VI/UI,与企业品牌形象无缝契合 - **资源集成**:由企业管理人员统一配置和管理数十种 AI 资源,团队成员开箱即用 - **权限管理**:成员权限、资源权限、知识库权限层级分明,企业级 Admin Panel 统一控制 @@ -27,7 +36,7 @@ 企业版咨询: **business@nextchat.dev** - + ## 开始使用 @@ -54,7 +63,7 @@ ### 打开自动更新 -> 如果你遇到了 Upstream Sync 执行错误,请手动 Sync Fork 一次! +> 如果你遇到了 Upstream Sync 执行错误,请[手动 Sync Fork 一次](./README_CN.md#手动更新代码)! 当你 fork 项目之后,由于 Github 的限制,需要手动去你 fork 后的项目的 Actions 页面启用 Workflows,并启用 Upstream Sync Action,启用之后即可开启每小时定时自动更新: @@ -88,7 +97,7 @@ code1,code2,code3 ### `OPENAI_API_KEY` (必填项) -OpanAI 密钥,你在 openai 账户页面申请的 api key,使用英文逗号隔开多个 key,这样可以随机轮询这些 key。 +OpenAI 密钥,你在 openai 账户页面申请的 api key,使用英文逗号隔开多个 key,这样可以随机轮询这些 key。 ### `CODE` (可选) @@ -184,7 +193,21 @@ ByteDance Api Url. 讯飞星火Api Secret. +### `CHATGLM_API_KEY` (可选) + +ChatGLM Api Key. + +### `CHATGLM_URL` (可选) + +ChatGLM Api Url. + +### `DEEPSEEK_API_KEY` (可选) + +DeepSeek Api Key. +### `DEEPSEEK_URL` (可选) + +DeepSeek Api Url. ### `HIDE_USER_API_KEY` (可选) @@ -202,11 +225,12 @@ ByteDance Api Url. 如果你想禁用从链接解析预制设置,将此环境变量设置为 1 即可。 -### `WHITE_WEBDEV_ENDPOINTS` (可选) +### `WHITE_WEBDAV_ENDPOINTS` (可选) 如果你想增加允许访问的webdav服务地址,可以使用该选项,格式要求: + - 每一个地址必须是一个完整的 endpoint -> `https://xxxx/xxx` + > `https://xxxx/xxx` - 多个地址以`,`相连 ### `CUSTOM_MODELS` (可选) @@ -216,18 +240,26 @@ ByteDance Api Url. 用来控制模型列表,使用 `+` 增加一个模型,使用 `-` 来隐藏一个模型,使用 `模型名=展示名` 来自定义模型的展示名,用英文逗号隔开。 -在Azure的模式下,支持使用`modelName@azure=deploymentName`的方式配置模型名称和部署名称(deploy-name) -> 示例:`+gpt-3.5-turbo@azure=gpt35`这个配置会在模型列表显示一个`gpt35(Azure)`的选项。 -> 如果你只能使用Azure模式,那么设置 `-all,+gpt-3.5-turbo@azure=gpt35` 则可以让对话的默认使用 `gpt35(Azure)` +在Azure的模式下,支持使用`modelName@Azure=deploymentName`的方式配置模型名称和部署名称(deploy-name) + +> 示例:`+gpt-3.5-turbo@Azure=gpt35`这个配置会在模型列表显示一个`gpt35(Azure)`的选项。 +> 如果你只能使用Azure模式,那么设置 `-all,+gpt-3.5-turbo@Azure=gpt35` 则可以让对话的默认使用 `gpt35(Azure)` 在ByteDance的模式下,支持使用`modelName@bytedance=deploymentName`的方式配置模型名称和部署名称(deploy-name) -> 示例: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx`这个配置会在模型列表显示一个`Doubao-lite-4k(ByteDance)`的选项 +> 示例: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx`这个配置会在模型列表显示一个`Doubao-lite-4k(ByteDance)`的选项 ### `DEFAULT_MODEL` (可选) 更改默认模型 +### `VISION_MODELS` (可选) + +> 默认值:空 +> 示例:`gpt-4-vision,claude-3-opus,my-custom-model` 表示为这些模型添加视觉能力,作为对默认模式匹配的补充(默认会检测包含"vision"、"claude-3"、"gemini-1.5"等关键词的模型)。 + +在默认模式匹配之外,添加更多具有视觉能力的模型。多个模型用逗号分隔。 + ### `DEFAULT_INPUT_TEMPLATE` (可选) 自定义默认的 template,用于初始化『设置』中的『用户输入预处理』配置项 @@ -240,6 +272,25 @@ Stability API密钥 自定义的Stability API请求地址 +### `ENABLE_MCP` (optional) + +启用MCP(Model Context Protocol)功能 + +### `SILICONFLOW_API_KEY` (optional) + +SiliconFlow API Key. + +### `SILICONFLOW_URL` (optional) + +SiliconFlow API URL. + +### `AI302_API_KEY` (optional) + +302.AI API Key. + +### `AI302_URL` (optional) + +302.AI API URL. ## 开发 @@ -264,6 +315,10 @@ BASE_URL=https://b.nextweb.fun/api/proxy ## 部署 +### 宝塔面板部署 + +> [简体中文 > 如何通过宝塔一键部署](./docs/bt-cn.md) + ### 容器部署 (推荐) > Docker 版本需要在 20 及其以上,否则会提示找不到镜像。 @@ -290,6 +345,16 @@ docker run -d -p 3000:3000 \ yidadaa/chatgpt-next-web ``` +如需启用 MCP 功能,可以使用: + +```shell +docker run -d -p 3000:3000 \ + -e OPENAI_API_KEY=sk-xxxx \ + -e CODE=页面访问密码 \ + -e ENABLE_MCP=true \ + yidadaa/chatgpt-next-web +``` + 如果你的本地代理需要账号密码,可以使用: ```shell diff --git a/README_JA.md b/README_JA.md index 6b8caadae6c..917cc1262c0 100644 --- a/README_JA.md +++ b/README_JA.md @@ -5,16 +5,24 @@ ワンクリックで無料であなた専用の ChatGPT ウェブアプリをデプロイ。GPT3、GPT4 & Gemini Pro モデルをサポート。 -[企業版](#企業版) / [デモ](https://chat-gpt-next-web.vercel.app/) / [フィードバック](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) / [Discordに参加](https://discord.gg/zrhvHCr79N) - -[Zeaburでデプロイ](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Zeaburでデプロイ](https://zeabur.com/templates/ZBUEFA) [Gitpodで開く](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) +[NextChatAI](https://nextchat.club?utm_source=readme) / [企業版](#企業版) / [デモ](https://chat-gpt-next-web.vercel.app/) / [フィードバック](https://github.com/Yidadaa/ChatGPT-Next-Web/issues) / [Discordに参加](https://discord.gg/zrhvHCr79N) +[Zeaburでデプロイ](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Zeaburでデプロイ](https://zeabur.com/templates/ZBUEFA) [Gitpodで開く](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) +## Sponsor AI API + + + icon + + +[302.AI](https://302.ai/) は、オンデマンドで支払うAIアプリケーションプラットフォームで、最も安全なAI APIとAIオンラインアプリケーションを提供します。 + ## 企業版 あなたの会社のプライベートデプロイとカスタマイズのニーズに応える + - **ブランドカスタマイズ**:企業向けに特別に設計された VI/UI、企業ブランドイメージとシームレスにマッチ - **リソース統合**:企業管理者が数十種類のAIリソースを統一管理、チームメンバーはすぐに使用可能 - **権限管理**:メンバーの権限、リソースの権限、ナレッジベースの権限を明確にし、企業レベルのAdmin Panelで統一管理 @@ -25,7 +33,6 @@ 企業版のお問い合わせ: **business@nextchat.dev** - ## 始めに 1. [OpenAI API Key](https://platform.openai.com/account/api-keys)を準備する; @@ -40,7 +47,6 @@ - ## 更新を維持する もし上記の手順に従ってワンクリックでプロジェクトをデプロイした場合、「更新があります」というメッセージが常に表示されることがあります。これは、Vercel がデフォルトで新しいプロジェクトを作成するためで、本プロジェクトを fork していないことが原因です。そのため、正しく更新を検出できません。 @@ -51,10 +57,9 @@ - ページ右上の fork ボタンを使って、本プロジェクトを fork する - Vercel で再度選択してデプロイする、[詳細な手順はこちらを参照してください](./docs/vercel-ja.md)。 - ### 自動更新を開く -> Upstream Sync の実行エラーが発生した場合は、手動で Sync Fork してください! +> Upstream Sync の実行エラーが発生した場合は、[手動で Sync Fork](./README_JA.md#手動でコードを更新する) してください! プロジェクトを fork した後、GitHub の制限により、fork 後のプロジェクトの Actions ページで Workflows を手動で有効にし、Upstream Sync Action を有効にする必要があります。有効化後、毎時の定期自動更新が可能になります: @@ -62,15 +67,12 @@ ![自動更新を有効にする](./docs/images/enable-actions-sync.jpg) - ### 手動でコードを更新する 手動で即座に更新したい場合は、[GitHub のドキュメント](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork)を参照して、fork したプロジェクトを上流のコードと同期する方法を確認してください。 このプロジェクトをスターまたはウォッチしたり、作者をフォローすることで、新機能の更新通知をすぐに受け取ることができます。 - - ## ページアクセスパスワードを設定する > パスワードを設定すると、ユーザーは設定ページでアクセスコードを手動で入力しない限り、通常のチャットができず、未承認の状態であることを示すメッセージが表示されます。 @@ -85,7 +87,6 @@ code1,code2,code3 この環境変数を追加または変更した後、**プロジェクトを再デプロイ**して変更を有効にしてください。 - ## 環境変数 > 本プロジェクトのほとんどの設定は環境変数で行います。チュートリアル:[Vercel の環境変数を変更する方法](./docs/vercel-ja.md)。 @@ -193,11 +194,12 @@ ByteDance API の URL。 リンクからのプリセット設定解析を無効にしたい場合は、この環境変数を 1 に設定します。 -### `WHITE_WEBDEV_ENDPOINTS` (オプション) +### `WHITE_WEBDAV_ENDPOINTS` (オプション) アクセス許可を与える WebDAV サービスのアドレスを追加したい場合、このオプションを使用します。フォーマット要件: + - 各アドレスは完全なエンドポイントでなければなりません。 -> `https://xxxx/xxx` + > `https://xxxx/xxx` - 複数のアドレスは `,` で接続します。 ### `CUSTOM_MODELS` (オプション) @@ -207,20 +209,36 @@ ByteDance API の URL。 モデルリストを管理します。`+` でモデルを追加し、`-` でモデルを非表示にし、`モデル名=表示名` でモデルの表示名をカスタマイズし、カンマで区切ります。 -Azure モードでは、`modelName@azure=deploymentName` 形式でモデル名とデプロイ名(deploy-name)を設定できます。 -> 例:`+gpt-3.5-turbo@azure=gpt35` この設定でモデルリストに `gpt35(Azure)` のオプションが表示されます。 +Azure モードでは、`modelName@Azure=deploymentName` 形式でモデル名とデプロイ名(deploy-name)を設定できます。 + +> 例:`+gpt-3.5-turbo@Azure=gpt35` この設定でモデルリストに `gpt35(Azure)` のオプションが表示されます。 ByteDance モードでは、`modelName@bytedance=deploymentName` 形式でモデル名とデプロイ名(deploy-name)を設定できます。 + > 例: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx` この設定でモデルリストに `Doubao-lite-4k(ByteDance)` のオプションが表示されます。 ### `DEFAULT_MODEL` (オプション) デフォルトのモデルを変更します。 +### `VISION_MODELS` (オプション) + +> デフォルト:空 +> 例:`gpt-4-vision,claude-3-opus,my-custom-model` は、これらのモデルにビジョン機能を追加します。これはデフォルトのパターンマッチング("vision"、"claude-3"、"gemini-1.5"などのキーワードを含むモデルを検出)に加えて適用されます。 + +デフォルトのパターンマッチングに加えて、追加のモデルにビジョン機能を付与します。複数のモデルはカンマで区切ります。 + ### `DEFAULT_INPUT_TEMPLATE` (オプション) 『設定』の『ユーザー入力前処理』の初期設定に使用するテンプレートをカスタマイズします。 +### `AI302_API_KEY` (オプション) + +302.AI API キー. + +### `AI302_URL` (オプション) + +302.AI API の URL. ## 開発 @@ -234,14 +252,12 @@ ByteDance モードでは、`modelName@bytedance=deploymentName` 形式でモデ OPENAI_API_KEY= ``` - ### ローカル開発 1. Node.js 18 と Yarn をインストールします。具体的な方法は ChatGPT にお尋ねください。 2. `yarn install && yarn dev` を実行します。⚠️ 注意:このコマンドはローカル開発用であり、デプロイには使用しないでください。 3. ローカルでデプロイしたい場合は、`yarn install && yarn build && yarn start` コマンドを使用してください。プロセスを守るために pm2 を使用することもできます。詳細は ChatGPT にお尋ねください。 - ## デプロイ ### コンテナデプロイ(推奨) @@ -278,7 +294,6 @@ docker run -d -p 3000:3000 \ 他の環境変数を指定する必要がある場合は、上記のコマンドに `-e 環境変数=環境変数値` を追加して指定してください。 - ### ローカルデプロイ コンソールで以下のコマンドを実行します: @@ -289,7 +304,6 @@ bash <(curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/s ⚠️ 注意:インストール中に問題が発生した場合は、Docker を使用してデプロイしてください。 - ## 謝辞 ### 寄付者 @@ -304,7 +318,6 @@ bash <(curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/s - [one-api](https://github.com/songquanpeng/one-api): 一つのプラットフォームで大規模モデルのクォータ管理を提供し、市場に出回っているすべての主要な大規模言語モデルをサポートします。 - ## オープンソースライセンス [MIT](https://opensource.org/license/mit/) diff --git a/README_KO.md b/README_KO.md new file mode 100644 index 00000000000..40ba5a6a1c4 --- /dev/null +++ b/README_KO.md @@ -0,0 +1,492 @@ +
+ + + icon + + +

NextChat

+ +영어 / [简体中文](./README_CN.md) + + + ChatGPTNextWeb%2FChatGPT-Next-Web | Trendshift + + +✨ 빠르고 가벼운 AI 어시스턴트, Claude, DeepSeek, GPT-4, Gemini Pro 지원 + +[![Saas][Saas-image]][saas-url] +[![Web][Web-image]][web-url] +[![Windows][Windows-image]][download-url] +[![MacOS][MacOS-image]][download-url] +[![Linux][Linux-image]][download-url] + +[NextChatAI 웹사이트](https://nextchat.club?utm_source=readme) / [iOS 앱](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [웹 데모](https://app.nextchat.club) / [데스크톱 앱](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [엔터프라이즈 버전](#enterprise-edition) + +[saas-url]: https://nextchat.club?utm_source=readme +[saas-image]: https://img.shields.io/badge/NextChat-Saas-green?logo=microsoftedge +[web-url]: https://app.nextchat.club/ +[download-url]: https://github.com/Yidadaa/ChatGPT-Next-Web/releases +[Web-image]: https://img.shields.io/badge/Web-PWA-orange?logo=microsoftedge +[Windows-image]: https://img.shields.io/badge/-Windows-blue?logo=windows +[MacOS-image]: https://img.shields.io/badge/-MacOS-black?logo=apple +[Linux-image]: https://img.shields.io/badge/-Linux-333?logo=ubuntu + +[Deploy on Zeabur](https://zeabur.com/templates/ZBUEFA) [Deploy on Vercel](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [Open in Gitpod](https://gitpod.io/#https://github.com/ChatGPTNextWeb/NextChat) + +[](https://monica.im/?utm=nxcrp) + +
+ +## ❤️ AI API 후원사 + + + icon + + +[302.AI](https://302.ai/)는 사용한 만큼만 비용을 지불하는 AI 애플리케이션 플랫폼으로, 다양한 AI API 및 온라인 애플리케이션을 제공합니다. + +## 🥳 NextChat iOS 버전 출시! + +> 👉 [지금 설치하기](https://apps.apple.com/us/app/nextchat-ai/id6743085599) + +> ❤️ [소스 코드 곧 공개 예정](https://github.com/ChatGPTNextWeb/NextChat-iOS) + +![Github iOS Image](https://github.com/user-attachments/assets/e0aa334f-4c13-4dc9-8310-e3b09fa4b9f3) + +## 🫣 NextChat, MCP 지원! + +> 빌드 전 환경 변수(env) `ENABLE_MCP=true` 설정 필요 + + + +## 엔터프라이즈 버전 + +회사 내부 시스템에 맞춘 프라이빗 배포 및 맞춤형 커스터마이징 지원: + +- **브랜드 커스터마이징**: 기업 이미지에 맞는 UI/UX 테마 적용 +- **리소스 통합 관리**: 다양한 AI 모델을 통합하여 팀원이 손쉽게 사용 가능 +- **권한 제어**: 관리자 패널을 통한 멤버·리소스·지식 베이스 권한 설정 +- **지식 통합**: 사내 문서 및 데이터와 AI를 결합한 맞춤형 답변 제공 +- **보안 감사**: 민감한 질문 차단 및 모든 기록 추적 가능 +- **프라이빗 배포 지원**: 주요 클라우드 서비스에 맞춘 배포 옵션 +- **지속적 업데이트**: 멀티모달 등 최신 AI 기능 지속 반영 + +엔터프라이즈 문의: **business@nextchat.dev** + +## 🖼️ 스크린샷 + +![설정](./docs/images/settings.png) +![기타](./docs/images/more.png) + +## 주요 기능 소개 + +- Vercel에서 원클릭 무료 배포 (1분 내 완성) +- 모든 OS(Linux/Windows/MacOS)에서 사용 가능한 클라이언트 (~5MB) [지금 다운 받기](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) +- 자체 LLM 서버와 완벽 호환. [RWKV-Runner](https://github.com/josStorer/RWKV-Runner) 또는 [LocalAI](https://github.com/go-skynet/LocalAI)와 함께 사용하는 것을 추천 +- 개인 정보 보호: 모든 대화 기록은 브라우저에만 저장 +- Markdown 지원: LaTex, Mermaid, 코드 하이라이팅 등 +- 반응형 디자인, 다크 모드, PWA 지원 +- 빠른 초기 로딩 속도 (~100kb), 스트리밍 응답 +- 프롬프트 템플릿 생성/공유/디버깅 지원 (v2) +- v2: 프롬프트 템플릿 기반 도구 생성, 공유, 디버깅 가능 +- 고급 프롬프트 내장 [awesome-chatgpt-prompts-zh](https://github.com/PlexPt/awesome-chatgpt-prompts-zh) and [awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts) +- 긴 대화 내용 자동 압축 저장으로 토큰 절약 +- I18n: English, 简体中文, 繁体中文, 日本語, Français, Español, Italiano, Türkçe, Deutsch, Tiếng Việt, Русский, Čeština, 한국어, Indonesia + +
+ +![主界面](./docs/images/cover.png) + +
+ +## 개발 로드맵 + +- [x] 시스템 프롬프트: 사용자가 정의한 프롬프트를 시스템 프롬프트로 고정하기 [#138](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/138) +- [x] 사용자 프롬프트: 사용자 정의 프롬프트를 편집 및 저장하여 리스트로 관리 가능 +- [x] 프롬프트 템플릿: 사전 정의된 인컨텍스트 프롬프트로 새 채팅 생성 [#993](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/993) +- [x] 이미지로 공유하거나 ShareGPT로 공유 [#1741](https://github.com/Yidadaa/ChatGPT-Next-Web/pull/1741) +- [x] Tauri 기반 데스크톱 앱 +- [x] 자체 모델 호스팅: [RWKV-Runner](https://github.com/josStorer/RWKV-Runner), [LocalAI](https://github.com/go-skynet/LocalAI) 등 서버 배포 모델들과 완벽 호환 (llama, gpt4all, rwkv, vicuna, koala, gpt4all-j, cerebras, falcon, dolly 등) +- [x] 아티팩트: 생성된 콘텐츠 및 웹페이지를 별도 창으로 미리보기, 복사, 공유 가능 [#5092](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/pull/5092) +- [x] 플러그인: 웹 검색, 계산기, 기타 외부 API 기능 지원 [#165](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/165) [#5353](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5353) +- [x] 실시간 채팅 지원 [#5672](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5672) +- [ ] 로컬 지식 베이스 지원 예정 + +## 🚀 최근 업데이트 + +- 🚀 v2.15.8 실시간 채팅 지원 [#5672](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5672) +- 🚀 v2.15.4 Tauri 기반 LLM API 호출 기능 추가 → 보안 강화 [#5379](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5379) +- 🚀 v2.15.0 플러그인 기능 추가 → [NextChat-Awesome-Plugins](https://github.com/ChatGPTNextWeb/NextChat-Awesome-Plugins) +- 🚀 v2.14.0 아티팩트 및 Stable Diffusion 기능 추가 +- 🚀 v2.10.1 Google Gemini Pro 모델 지원 +- 🚀 v2.9.11 Azure Endpoint 사용 가능 +- 🚀 v2.8 모든 플랫폼에서 실행 가능한 클라이언트 출시 +- 🚀 v2.7 대화 내용을 이미지로, 또는 ShareGPT로 공유 가능 +- 🚀 v2.0 릴리즈: 프롬프트 템플릿 생성 및 아이디어 구현 가능! → [ChatGPT Prompt Engineering Tips](https://www.allabtai.com/prompt-engineering-tips-zero-one-and-few-shot-prompting/) + +## 시작하기 + +1. [OpenAI API 키](https://platform.openai.com/account/api-keys)를 발급받습니다. +2. + [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FYidadaa%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=chatgpt-next-web&repository-name=ChatGPT-Next-Web) 버튼을 클릭해 Vercel에 배포합니다. `CODE`는 페이지 비밀번호라는 점을 기억하세요. + +3. Enjoy :) + +## FAQ + +[FAQ](./docs/faq-ko.md) + +## 최신 상태 유지 (Keep Updated) + +Vercel로 배포한 경우, "Updates Available" 메시지가 계속 나타날 수 있습니다. 이는 프로젝트를 포크하지 않고 새로 생성했기 때문입니다. + +다음 절차에 따라 다시 배포를 권장합니다: + +1. 기존 레포 삭제 +2. 우측 상단 "Fork" 버튼 클릭 → 포크 생성 +3. 포크된 프로젝트를 다시 Vercel에 배포 + → [자세한 튜토리얼 보기](./docs/vercel-ko.md) + +### 자동 업데이트 활성화 (Enable Automatic Updates) + +> Upstream Sync 오류 발생 시, [수동으로 코드 업데이트](./README_KO.md#manually-updating-code)하세요. + +프로젝트 포크 후에는 GitHub의 제약으로 인해 Actions 페이지에서 아래 항목들을 수동으로 활성화해야 합니다: + +- `Workflows` +- `Upstream Sync Action` + +이후 매 시간 자동으로 업데이트됩니다: + +![자동 업데이트 활성화](./docs/images/enable-actions.jpg) +![업스트림 동기화 활성화](./docs/images/enable-actions-sync.jpg) + +### 수동 업데이트 방법 (Manually Updating Code) + +즉시 업데이트가 필요한 경우, [깃헙 문서](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork)를 참고해 포크된 프로젝트를 upstream code와 동기화하세요. + +릴리스 알림을 원하시면 star 또는 watch를 눌러주세요. + +## 접근 비밀번호 설정 (Access Password) + +이 프로젝트는 제한된 접근 제어를 제공합니다. +Vercel 환경 변수에 `CODE`를 다음 형식으로 추가하세요. value는 ,를 통해 구분된 비밀번호여야 합니다.: + +``` +code1,code2,code3 +``` + +수정 후 반드시 다시 배포해야 적용됩니다. + +## 환경 변수 (Environment Variables) + +### `CODE` (선택 사항) + +접속 비밀번호. 쉼표로 구분합니다. + +### `OPENAI_API_KEY` (필수) + +당신의 OpenAI API 키, 여러 개를 사용하려면 쉼표로 연결합니다. + +### `BASE_URL` (선택 사항) + +> 기본값: `https://api.openai.com` + +> 예시: `http://your-openai-proxy.com` + +OpenAI API 요청의 기본 URL을 재정의합니다. + +### `OPENAI_ORG_ID` (선택 사항) + +OpenAI organization ID를 지정합니다. + +### `AZURE_URL` (선택 사항) + +> 예시: https://{azure-resource-url}/openai + +Azure 배포 URL입니다. + +### `AZURE_API_KEY` (선택 사항) + +Azure API 키입니다. + +### `AZURE_API_VERSION` (선택 사항) + +Azure API 버전입니다. [Azure 문서](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions)에서 확인할 수 있습니다. + +### `GOOGLE_API_KEY` (선택 사항) + +Google Gemini Pro API 키입니다. + +### `GOOGLE_URL` (선택 사항) + +Google Gemini Pro API URL입니다. + +### `ANTHROPIC_API_KEY` (선택 사항) + +Anthropic Claude API 키입니다. + +### `ANTHROPIC_API_VERSION` (선택 사항) + +Anthropic Claude API 버전입니다. + +### `ANTHROPIC_URL` (선택 사항) + +Anthropic Claude API URL입니다. + +### `BAIDU_API_KEY` (선택 사항) + +Baidu API 키입니다. + +### `BAIDU_SECRET_KEY` (선택 사항) + +Baidu Secret 키입니다. + +### `BAIDU_URL` (선택 사항) + +Baidu API URL입니다. + +### `BYTEDANCE_API_KEY` (선택 사항) + +ByteDance API 키입니다. + +### `BYTEDANCE_URL` (선택 사항) + +ByteDance API URL입니다. + +### `ALIBABA_API_KEY` (선택 사항) + +Alibaba Cloud API 키입니다. + +### `ALIBABA_URL` (선택 사항) + +Alibaba Cloud API URL입니다. + +### `IFLYTEK_URL` (선택 사항) + +iflytek API URL입니다. + +### `IFLYTEK_API_KEY` (선택 사항) + +iflytek API 키입니다. + +### `IFLYTEK_API_SECRET` (선택 사항) + +iflytek API 시크릿입니다. + +### `CHATGLM_API_KEY` (선택 사항) + +ChatGLM API 키입니다. + +### `CHATGLM_URL` (선택 사항) + +ChatGLM API URL입니다. + +### `DEEPSEEK_API_KEY` (선택 사항) + +DeepSeek API 키입니다. + +### `DEEPSEEK_URL` (선택 사항) + +DeepSeek API URL입니다. + +### `HIDE_USER_API_KEY` (선택 사항) + +> 기본값: 비어 있음 + +사용자가 자신의 API 키를 입력하지 못하게 하려면 이 값을 1로 설정하세요. + +### `DISABLE_GPT4` (선택 사항) + +> 기본값: 비어 있음 + +사용자가 GPT-4를 사용하지 못하게 하려면 이 값을 1로 설정하세요. + +### `ENABLE_BALANCE_QUERY` (선택 사항) + +> 기본값: 비어 있음 + +사용자가 쿼리 잔액을 조회할 수 있도록 하려면 이 값을 1로 설정하세요. + +### `DISABLE_FAST_LINK` (선택 사항) + +> 기본값: 비어 있음 + +URL에서 설정을 파싱하는 기능을 비활성화하려면 이 값을 1로 설정하세요. + +### `CUSTOM_MODELS` (선택 사항) + +> 기본값: 비어 있음 +> 예시: `+llama,+claude-2,-gpt-3.5-turbo,gpt-4-1106-preview=gpt-4-turbo` +이는 `llama`, `claude-2`를 모델 리스트에 추가하고, `gpt-3.5-turbo`를 제거하며, `gpt-4-1106-preview`를 `gpt-4-turbo`로 표시합니다. + +사용자 지정 모델 제어 시 `+`는 추가, `-`는 제거, `이름=표시이름`은 모델명 커스터마이징을 의미합니다. 쉼표로 구분하세요. + +- `-all`은 기본 모델을 모두 비활성화 +- `+all`은 기본 모델을 모두 활성화 + +Azure 용법 예시: `modelName@Azure=deploymentName` → 배포 이름을 커스터마이징 가능 +> 예시: `+gpt-3.5-turbo@Azure=gpt35` → 리스트에 `gpt35(Azure)` 표시됨 +> Azure 모델만 사용할 경우: `-all,+gpt-3.5-turbo@Azure=gpt35` + +ByteDance 용법 예시: `modelName@bytedance=deploymentName` +> 예시: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx` → `Doubao-lite-4k(ByteDance)`로 표시됨 + +### `DEFAULT_MODEL` (선택 사항) + +기본 모델을 변경합니다. + +### `VISION_MODELS` (선택 사항) + +> 기본값: 비어 있음 +> 예시: `gpt-4-vision,claude-3-opus,my-custom-model` +위의 모델들에 시각 기능을 부여합니다 (기본적으로 `"vision"`, `"claude-3"`, `"gemini-1.5"` 키워드를 포함한 모델은 자동 인식됨). 기본 모델 외에도 모델을 추가할 수 있습니다. 쉼표로 구분하세요. + +### `WHITE_WEBDAV_ENDPOINTS` (선택 사항) + +접속 허용할 WebDAV 서비스 주소를 늘리고자 할 때 사용합니다. + +- 각 주소는 완전한 endpoint 여야 함: `https://xxxx/yyy` +- 여러 주소는 `,`로 구분 + +### `DEFAULT_INPUT_TEMPLATE` (선택 사항) + +설정 메뉴의 사용자 입력 전처리 구성 항목 초기화 시 사용할 기본 템플릿을 설정합니다. + +### `STABILITY_API_KEY` (선택 사항) + +Stability API 키입니다. + +### `STABILITY_URL` (선택 사항) + +Stability API URL을 커스터마이징합니다. + +### `ENABLE_MCP` (선택 사항) + +MCP (Model Context Protocol) 기능을 활성화합니다. + +### `SILICONFLOW_API_KEY` (선택 사항) + +SiliconFlow API 키입니다. + +### `SILICONFLOW_URL` (선택 사항) + +SiliconFlow API URL입니다. + +### `AI302_API_KEY` (선택 사항) + +302.AI API 키입니다. + +### `AI302_URL` (선택 사항) + +302.AI API URL입니다. + +## 요구 사항 (Requirements) + +NodeJS >= 18, Docker >= 20 + +## 개발 (Development) + +[![Gitpod에서 열기](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) + +개발을 시작하기 전에 프로젝트 루트에 `.env.local` 파일을 만들고, 아래와 같이 API 키를 입력하세요: + +``` +OPENAI_API_KEY=<여기에 API 키 입력> + +# OpenAI 서비스를 사용할 수 없는 경우 아래 BASE_URL 사용 +BASE_URL=https://chatgpt1.nextweb.fun/api/proxy +``` + +### 로컬 개발 실행 + +```shell +# 1. Node.js와 Yarn을 먼저 설치 +# 2. `.env.local` 파일에 환경 변수 설정 +# 3. 실행 +yarn install +yarn dev +``` + +## 배포 (Deployment) + +### Docker (권장) + +```shell +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 +``` + +서비스에 프록시를 사용하려면: + +```shell +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 +``` + +프록시에 인증이 필요한 경우: + +```shell +-e PROXY_URL="http://127.0.0.1:7890 user pass" +``` + +MCP를 활성화하려면: + +``` +docker run -d -p 3000:3000 \ + -e OPENAI_API_KEY=sk-xxxx \ + -e CODE=your-password \ + -e ENABLE_MCP=true \ + yidadaa/chatgpt-next-web +``` + +### 로컬 배포 + +콘솔에서 다음 명령을 실행하세요. + +```shell +bash <(curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/scripts/setup.sh) +``` + +⚠️ 참고: 설치 중에 문제가 발생하면 Docker 배포를 사용하세요. + +## 채팅 기록 동기화 (UpStash) + +| [简体中文](./docs/synchronise-chat-logs-cn.md) | [English](./docs/synchronise-chat-logs-en.md) | [Italiano](./docs/synchronise-chat-logs-es.md) | [日本語](./docs/synchronise-chat-logs-ja.md) | [한국어](./docs/synchronise-chat-logs-ko.md) + +## 문서 (Documentation) + +> 더 많은 문서는 [docs](./docs) 디렉토리를 참고하세요. + +- [Cloudflare 배포 가이드 (폐기됨)](./docs/cloudflare-pages-ko.md) +- [자주 묻는 질문](./docs/faq-ko.md) +- [새 번역 추가 방법](./docs/translation.md) +- [Vercel 사용법 (중문)](./docs/vercel-cn.md) +- [사용자 매뉴얼 (중문, 작성 중)](./docs/user-manual-cn.md) + +## 번역 (Translation) + +새로운 번역을 추가하고 싶다면, [이 문서](./docs/translation.md)를 읽어보세요. + +## 후원 (Donation) + +[Buy Me a Coffee](https://www.buymeacoffee.com/yidadaa) + +## 특별 감사 (Special Thanks) + +### 기여자 (Contributors) + + + + + +## 라이선스 (LICENSE) + +[MIT](https://opensource.org/license/mit/) diff --git a/app/api/302ai.ts b/app/api/302ai.ts new file mode 100644 index 00000000000..b4636bcd7be --- /dev/null +++ b/app/api/302ai.ts @@ -0,0 +1,128 @@ +import { getServerSideConfig } from "@/app/config/server"; +import { + AI302_BASE_URL, + ApiPath, + ModelProvider, + ServiceProvider, +} from "@/app/constant"; +import { prettyObject } from "@/app/utils/format"; +import { NextRequest, NextResponse } from "next/server"; +import { auth } from "@/app/api/auth"; +import { isModelNotavailableInServer } from "@/app/utils/model"; + +const serverConfig = getServerSideConfig(); + +export async function handle( + req: NextRequest, + { params }: { params: { path: string[] } }, +) { + console.log("[302.AI Route] params ", params); + + if (req.method === "OPTIONS") { + return NextResponse.json({ body: "OK" }, { status: 200 }); + } + + const authResult = auth(req, ModelProvider["302.AI"]); + if (authResult.error) { + return NextResponse.json(authResult, { + status: 401, + }); + } + + try { + const response = await request(req); + return response; + } catch (e) { + console.error("[302.AI] ", e); + return NextResponse.json(prettyObject(e)); + } +} + +async function request(req: NextRequest) { + const controller = new AbortController(); + + // alibaba use base url or just remove the path + let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath["302.AI"], ""); + + let baseUrl = serverConfig.ai302Url || AI302_BASE_URL; + + if (!baseUrl.startsWith("http")) { + baseUrl = `https://${baseUrl}`; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, -1); + } + + console.log("[Proxy] ", path); + console.log("[Base Url]", baseUrl); + + const timeoutId = setTimeout( + () => { + controller.abort(); + }, + 10 * 60 * 1000, + ); + + const fetchUrl = `${baseUrl}${path}`; + const fetchOptions: RequestInit = { + headers: { + "Content-Type": "application/json", + Authorization: req.headers.get("Authorization") ?? "", + }, + method: req.method, + body: req.body, + redirect: "manual", + // @ts-ignore + duplex: "half", + signal: controller.signal, + }; + + // #1815 try to refuse some request to some models + if (serverConfig.customModels && req.body) { + try { + const clonedBody = await req.text(); + fetchOptions.body = clonedBody; + + const jsonBody = JSON.parse(clonedBody) as { model?: string }; + + // not undefined and is false + if ( + isModelNotavailableInServer( + serverConfig.customModels, + jsonBody?.model as string, + ServiceProvider["302.AI"] as string, + ) + ) { + return NextResponse.json( + { + error: true, + message: `you are not allowed to use ${jsonBody?.model} model`, + }, + { + status: 403, + }, + ); + } + } catch (e) { + console.error(`[302.AI] filter`, e); + } + } + try { + const res = await fetch(fetchUrl, fetchOptions); + + // to prevent browser prompt for credentials + const newHeaders = new Headers(res.headers); + newHeaders.delete("www-authenticate"); + // to disable nginx buffering + newHeaders.set("X-Accel-Buffering", "no"); + + return new Response(res.body, { + status: res.status, + statusText: res.statusText, + headers: newHeaders, + }); + } finally { + clearTimeout(timeoutId); + } +} diff --git a/app/api/[provider]/[...path]/route.ts b/app/api/[provider]/[...path]/route.ts index 24aa5ec040f..e8af34f29f8 100644 --- a/app/api/[provider]/[...path]/route.ts +++ b/app/api/[provider]/[...path]/route.ts @@ -1,5 +1,5 @@ import { ApiPath } from "@/app/constant"; -import { NextRequest, NextResponse } from "next/server"; +import { NextRequest } from "next/server"; import { handle as openaiHandler } from "../../openai"; import { handle as azureHandler } from "../../azure"; import { handle as googleHandler } from "../../google"; @@ -10,7 +10,12 @@ import { handle as alibabaHandler } from "../../alibaba"; import { handle as moonshotHandler } from "../../moonshot"; import { handle as stabilityHandler } from "../../stability"; import { handle as iflytekHandler } from "../../iflytek"; +import { handle as deepseekHandler } from "../../deepseek"; +import { handle as siliconflowHandler } from "../../siliconflow"; +import { handle as xaiHandler } from "../../xai"; +import { handle as chatglmHandler } from "../../glm"; import { handle as proxyHandler } from "../../proxy"; +import { handle as ai302Handler } from "../../302ai"; async function handle( req: NextRequest, @@ -38,8 +43,18 @@ async function handle( return stabilityHandler(req, { params }); case ApiPath.Iflytek: return iflytekHandler(req, { params }); + case ApiPath.DeepSeek: + return deepseekHandler(req, { params }); + case ApiPath.XAI: + return xaiHandler(req, { params }); + case ApiPath.ChatGLM: + return chatglmHandler(req, { params }); + case ApiPath.SiliconFlow: + return siliconflowHandler(req, { params }); case ApiPath.OpenAI: return openaiHandler(req, { params }); + case ApiPath["302.AI"]: + return ai302Handler(req, { params }); default: return proxyHandler(req, { params }); } diff --git a/app/api/alibaba.ts b/app/api/alibaba.ts index 675d9f301aa..20f6caefa8d 100644 --- a/app/api/alibaba.ts +++ b/app/api/alibaba.ts @@ -1,6 +1,5 @@ import { getServerSideConfig } from "@/app/config/server"; import { - Alibaba, ALIBABA_BASE_URL, ApiPath, ModelProvider, @@ -9,8 +8,7 @@ import { import { prettyObject } from "@/app/utils/format"; import { NextRequest, NextResponse } from "next/server"; import { auth } from "@/app/api/auth"; -import { isModelAvailableInServer } from "@/app/utils/model"; -import type { RequestPayload } from "@/app/client/platforms/openai"; +import { isModelNotavailableInServer } from "@/app/utils/model"; const serverConfig = getServerSideConfig(); @@ -91,7 +89,7 @@ async function request(req: NextRequest) { // not undefined and is false if ( - isModelAvailableInServer( + isModelNotavailableInServer( serverConfig.customModels, jsonBody?.model as string, ServiceProvider.Alibaba as string, diff --git a/app/api/anthropic.ts b/app/api/anthropic.ts index d7b070247b7..b96637b2c8c 100644 --- a/app/api/anthropic.ts +++ b/app/api/anthropic.ts @@ -3,14 +3,13 @@ import { ANTHROPIC_BASE_URL, Anthropic, ApiPath, - DEFAULT_MODELS, ServiceProvider, ModelProvider, } from "@/app/constant"; import { prettyObject } from "@/app/utils/format"; import { NextRequest, NextResponse } from "next/server"; import { auth } from "./auth"; -import { isModelAvailableInServer } from "@/app/utils/model"; +import { isModelNotavailableInServer } from "@/app/utils/model"; import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare"; const ALLOWD_PATH = new Set([Anthropic.ChatPath, Anthropic.ChatPath1]); @@ -123,7 +122,7 @@ async function request(req: NextRequest) { // not undefined and is false if ( - isModelAvailableInServer( + isModelNotavailableInServer( serverConfig.customModels, jsonBody?.model as string, ServiceProvider.Anthropic as string, diff --git a/app/api/auth.ts b/app/api/auth.ts index 95965ceec2d..8c78c70c865 100644 --- a/app/api/auth.ts +++ b/app/api/auth.ts @@ -92,6 +92,18 @@ export function auth(req: NextRequest, modelProvider: ModelProvider) { systemApiKey = serverConfig.iflytekApiKey + ":" + serverConfig.iflytekApiSecret; break; + case ModelProvider.DeepSeek: + systemApiKey = serverConfig.deepseekApiKey; + break; + case ModelProvider.XAI: + systemApiKey = serverConfig.xaiApiKey; + break; + case ModelProvider.ChatGLM: + systemApiKey = serverConfig.chatglmApiKey; + break; + case ModelProvider.SiliconFlow: + systemApiKey = serverConfig.siliconFlowApiKey; + break; case ModelProvider.GPT: default: if (req.nextUrl.pathname.includes("azure/deployments")) { diff --git a/app/api/azure.ts b/app/api/azure.ts index e2cb0c7e66b..39d872e8cf8 100644 --- a/app/api/azure.ts +++ b/app/api/azure.ts @@ -1,4 +1,3 @@ -import { getServerSideConfig } from "@/app/config/server"; import { ModelProvider } from "@/app/constant"; import { prettyObject } from "@/app/utils/format"; import { NextRequest, NextResponse } from "next/server"; diff --git a/app/api/baidu.ts b/app/api/baidu.ts index f4315d186da..0f4e05ee86c 100644 --- a/app/api/baidu.ts +++ b/app/api/baidu.ts @@ -3,13 +3,12 @@ import { BAIDU_BASE_URL, ApiPath, ModelProvider, - BAIDU_OATUH_URL, ServiceProvider, } from "@/app/constant"; import { prettyObject } from "@/app/utils/format"; import { NextRequest, NextResponse } from "next/server"; import { auth } from "@/app/api/auth"; -import { isModelAvailableInServer } from "@/app/utils/model"; +import { isModelNotavailableInServer } from "@/app/utils/model"; import { getAccessToken } from "@/app/utils/baidu"; const serverConfig = getServerSideConfig(); @@ -105,7 +104,7 @@ async function request(req: NextRequest) { // not undefined and is false if ( - isModelAvailableInServer( + isModelNotavailableInServer( serverConfig.customModels, jsonBody?.model as string, ServiceProvider.Baidu as string, diff --git a/app/api/bytedance.ts b/app/api/bytedance.ts index cb65b106109..51b39ceb7cb 100644 --- a/app/api/bytedance.ts +++ b/app/api/bytedance.ts @@ -8,7 +8,7 @@ import { import { prettyObject } from "@/app/utils/format"; import { NextRequest, NextResponse } from "next/server"; import { auth } from "@/app/api/auth"; -import { isModelAvailableInServer } from "@/app/utils/model"; +import { isModelNotavailableInServer } from "@/app/utils/model"; const serverConfig = getServerSideConfig(); @@ -88,7 +88,7 @@ async function request(req: NextRequest) { // not undefined and is false if ( - isModelAvailableInServer( + isModelNotavailableInServer( serverConfig.customModels, jsonBody?.model as string, ServiceProvider.ByteDance as string, diff --git a/app/api/common.ts b/app/api/common.ts index 25decbf620e..b7e41fa2647 100644 --- a/app/api/common.ts +++ b/app/api/common.ts @@ -1,13 +1,8 @@ import { NextRequest, NextResponse } from "next/server"; import { getServerSideConfig } from "../config/server"; -import { - DEFAULT_MODELS, - OPENAI_BASE_URL, - GEMINI_BASE_URL, - ServiceProvider, -} from "../constant"; -import { isModelAvailableInServer } from "../utils/model"; +import { OPENAI_BASE_URL, ServiceProvider } from "../constant"; import { cloudflareAIGatewayUrl } from "../utils/cloudflare"; +import { getModelProvider, isModelNotavailableInServer } from "../utils/model"; const serverConfig = getServerSideConfig(); @@ -76,7 +71,7 @@ export async function requestOpenai(req: NextRequest) { .filter((v) => !!v && !v.startsWith("-") && v.includes(modelName)) .forEach((m) => { const [fullName, displayName] = m.split("="); - const [_, providerName] = fullName.split("@"); + const [_, providerName] = getModelProvider(fullName); if (providerName === "azure" && !displayName) { const [_, deployId] = (serverConfig?.azureUrl ?? "").split( "deployments/", @@ -123,15 +118,14 @@ export async function requestOpenai(req: NextRequest) { // not undefined and is false if ( - isModelAvailableInServer( + isModelNotavailableInServer( serverConfig.customModels, jsonBody?.model as string, - ServiceProvider.OpenAI as string, - ) || - isModelAvailableInServer( - serverConfig.customModels, - jsonBody?.model as string, - ServiceProvider.Azure as string, + [ + ServiceProvider.OpenAI, + ServiceProvider.Azure, + jsonBody?.model as string, // support provider-unspecified model + ], ) ) { return NextResponse.json( diff --git a/app/api/config/route.ts b/app/api/config/route.ts index b0d9da03103..855a5db017e 100644 --- a/app/api/config/route.ts +++ b/app/api/config/route.ts @@ -14,6 +14,7 @@ const DANGER_CONFIG = { disableFastLink: serverConfig.disableFastLink, customModels: serverConfig.customModels, defaultModel: serverConfig.defaultModel, + visionModels: serverConfig.visionModels, }; declare global { diff --git a/app/api/deepseek.ts b/app/api/deepseek.ts new file mode 100644 index 00000000000..a9879ecedeb --- /dev/null +++ b/app/api/deepseek.ts @@ -0,0 +1,128 @@ +import { getServerSideConfig } from "@/app/config/server"; +import { + DEEPSEEK_BASE_URL, + ApiPath, + ModelProvider, + ServiceProvider, +} from "@/app/constant"; +import { prettyObject } from "@/app/utils/format"; +import { NextRequest, NextResponse } from "next/server"; +import { auth } from "@/app/api/auth"; +import { isModelNotavailableInServer } from "@/app/utils/model"; + +const serverConfig = getServerSideConfig(); + +export async function handle( + req: NextRequest, + { params }: { params: { path: string[] } }, +) { + console.log("[DeepSeek Route] params ", params); + + if (req.method === "OPTIONS") { + return NextResponse.json({ body: "OK" }, { status: 200 }); + } + + const authResult = auth(req, ModelProvider.DeepSeek); + if (authResult.error) { + return NextResponse.json(authResult, { + status: 401, + }); + } + + try { + const response = await request(req); + return response; + } catch (e) { + console.error("[DeepSeek] ", e); + return NextResponse.json(prettyObject(e)); + } +} + +async function request(req: NextRequest) { + const controller = new AbortController(); + + // alibaba use base url or just remove the path + let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath.DeepSeek, ""); + + let baseUrl = serverConfig.deepseekUrl || DEEPSEEK_BASE_URL; + + if (!baseUrl.startsWith("http")) { + baseUrl = `https://${baseUrl}`; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, -1); + } + + console.log("[Proxy] ", path); + console.log("[Base Url]", baseUrl); + + const timeoutId = setTimeout( + () => { + controller.abort(); + }, + 10 * 60 * 1000, + ); + + const fetchUrl = `${baseUrl}${path}`; + const fetchOptions: RequestInit = { + headers: { + "Content-Type": "application/json", + Authorization: req.headers.get("Authorization") ?? "", + }, + method: req.method, + body: req.body, + redirect: "manual", + // @ts-ignore + duplex: "half", + signal: controller.signal, + }; + + // #1815 try to refuse some request to some models + if (serverConfig.customModels && req.body) { + try { + const clonedBody = await req.text(); + fetchOptions.body = clonedBody; + + const jsonBody = JSON.parse(clonedBody) as { model?: string }; + + // not undefined and is false + if ( + isModelNotavailableInServer( + serverConfig.customModels, + jsonBody?.model as string, + ServiceProvider.DeepSeek as string, + ) + ) { + return NextResponse.json( + { + error: true, + message: `you are not allowed to use ${jsonBody?.model} model`, + }, + { + status: 403, + }, + ); + } + } catch (e) { + console.error(`[DeepSeek] filter`, e); + } + } + try { + const res = await fetch(fetchUrl, fetchOptions); + + // to prevent browser prompt for credentials + const newHeaders = new Headers(res.headers); + newHeaders.delete("www-authenticate"); + // to disable nginx buffering + newHeaders.set("X-Accel-Buffering", "no"); + + return new Response(res.body, { + status: res.status, + statusText: res.statusText, + headers: newHeaders, + }); + } finally { + clearTimeout(timeoutId); + } +} diff --git a/app/api/glm.ts b/app/api/glm.ts new file mode 100644 index 00000000000..8431c5db5b0 --- /dev/null +++ b/app/api/glm.ts @@ -0,0 +1,129 @@ +import { getServerSideConfig } from "@/app/config/server"; +import { + CHATGLM_BASE_URL, + ApiPath, + ModelProvider, + ServiceProvider, +} from "@/app/constant"; +import { prettyObject } from "@/app/utils/format"; +import { NextRequest, NextResponse } from "next/server"; +import { auth } from "@/app/api/auth"; +import { isModelNotavailableInServer } from "@/app/utils/model"; + +const serverConfig = getServerSideConfig(); + +export async function handle( + req: NextRequest, + { params }: { params: { path: string[] } }, +) { + console.log("[GLM Route] params ", params); + + if (req.method === "OPTIONS") { + return NextResponse.json({ body: "OK" }, { status: 200 }); + } + + const authResult = auth(req, ModelProvider.ChatGLM); + if (authResult.error) { + return NextResponse.json(authResult, { + status: 401, + }); + } + + try { + const response = await request(req); + return response; + } catch (e) { + console.error("[GLM] ", e); + return NextResponse.json(prettyObject(e)); + } +} + +async function request(req: NextRequest) { + const controller = new AbortController(); + + // alibaba use base url or just remove the path + let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath.ChatGLM, ""); + + let baseUrl = serverConfig.chatglmUrl || CHATGLM_BASE_URL; + + if (!baseUrl.startsWith("http")) { + baseUrl = `https://${baseUrl}`; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, -1); + } + + console.log("[Proxy] ", path); + console.log("[Base Url]", baseUrl); + + const timeoutId = setTimeout( + () => { + controller.abort(); + }, + 10 * 60 * 1000, + ); + + const fetchUrl = `${baseUrl}${path}`; + console.log("[Fetch Url] ", fetchUrl); + const fetchOptions: RequestInit = { + headers: { + "Content-Type": "application/json", + Authorization: req.headers.get("Authorization") ?? "", + }, + method: req.method, + body: req.body, + redirect: "manual", + // @ts-ignore + duplex: "half", + signal: controller.signal, + }; + + // #1815 try to refuse some request to some models + if (serverConfig.customModels && req.body) { + try { + const clonedBody = await req.text(); + fetchOptions.body = clonedBody; + + const jsonBody = JSON.parse(clonedBody) as { model?: string }; + + // not undefined and is false + if ( + isModelNotavailableInServer( + serverConfig.customModels, + jsonBody?.model as string, + ServiceProvider.ChatGLM as string, + ) + ) { + return NextResponse.json( + { + error: true, + message: `you are not allowed to use ${jsonBody?.model} model`, + }, + { + status: 403, + }, + ); + } + } catch (e) { + console.error(`[GLM] filter`, e); + } + } + try { + const res = await fetch(fetchUrl, fetchOptions); + + // to prevent browser prompt for credentials + const newHeaders = new Headers(res.headers); + newHeaders.delete("www-authenticate"); + // to disable nginx buffering + newHeaders.set("X-Accel-Buffering", "no"); + + return new Response(res.body, { + status: res.status, + statusText: res.statusText, + headers: newHeaders, + }); + } finally { + clearTimeout(timeoutId); + } +} diff --git a/app/api/google.ts b/app/api/google.ts index 98fe469bfb7..707892c33d0 100644 --- a/app/api/google.ts +++ b/app/api/google.ts @@ -1,12 +1,7 @@ import { NextRequest, NextResponse } from "next/server"; import { auth } from "./auth"; import { getServerSideConfig } from "@/app/config/server"; -import { - ApiPath, - GEMINI_BASE_URL, - Google, - ModelProvider, -} from "@/app/constant"; +import { ApiPath, GEMINI_BASE_URL, ModelProvider } from "@/app/constant"; import { prettyObject } from "@/app/utils/format"; const serverConfig = getServerSideConfig(); @@ -28,7 +23,8 @@ export async function handle( }); } - const bearToken = req.headers.get("Authorization") ?? ""; + const bearToken = + req.headers.get("x-goog-api-key") || req.headers.get("Authorization") || ""; const token = bearToken.trim().replaceAll("Bearer ", "").trim(); const apiKey = token ? token : serverConfig.googleApiKey; @@ -96,8 +92,8 @@ async function request(req: NextRequest, apiKey: string) { }, 10 * 60 * 1000, ); - const fetchUrl = `${baseUrl}${path}?key=${apiKey}${ - req?.nextUrl?.searchParams?.get("alt") === "sse" ? "&alt=sse" : "" + const fetchUrl = `${baseUrl}${path}${ + req?.nextUrl?.searchParams?.get("alt") === "sse" ? "?alt=sse" : "" }`; console.log("[Fetch Url] ", fetchUrl); @@ -105,6 +101,9 @@ async function request(req: NextRequest, apiKey: string) { headers: { "Content-Type": "application/json", "Cache-Control": "no-store", + "x-goog-api-key": + req.headers.get("x-goog-api-key") || + (req.headers.get("Authorization") ?? "").replace("Bearer ", ""), }, method: req.method, body: req.body, diff --git a/app/api/iflytek.ts b/app/api/iflytek.ts index eabdd9f4ce6..6624f74e9ab 100644 --- a/app/api/iflytek.ts +++ b/app/api/iflytek.ts @@ -1,6 +1,5 @@ import { getServerSideConfig } from "@/app/config/server"; import { - Iflytek, IFLYTEK_BASE_URL, ApiPath, ModelProvider, @@ -9,8 +8,7 @@ import { import { prettyObject } from "@/app/utils/format"; import { NextRequest, NextResponse } from "next/server"; import { auth } from "@/app/api/auth"; -import { isModelAvailableInServer } from "@/app/utils/model"; -import type { RequestPayload } from "@/app/client/platforms/openai"; +import { isModelNotavailableInServer } from "@/app/utils/model"; // iflytek const serverConfig = getServerSideConfig(); @@ -91,7 +89,7 @@ async function request(req: NextRequest) { // not undefined and is false if ( - isModelAvailableInServer( + isModelNotavailableInServer( serverConfig.customModels, jsonBody?.model as string, ServiceProvider.Iflytek as string, diff --git a/app/api/moonshot.ts b/app/api/moonshot.ts index 247dd618321..792d14d3334 100644 --- a/app/api/moonshot.ts +++ b/app/api/moonshot.ts @@ -1,6 +1,5 @@ import { getServerSideConfig } from "@/app/config/server"; import { - Moonshot, MOONSHOT_BASE_URL, ApiPath, ModelProvider, @@ -9,8 +8,7 @@ import { import { prettyObject } from "@/app/utils/format"; import { NextRequest, NextResponse } from "next/server"; import { auth } from "@/app/api/auth"; -import { isModelAvailableInServer } from "@/app/utils/model"; -import type { RequestPayload } from "@/app/client/platforms/openai"; +import { isModelNotavailableInServer } from "@/app/utils/model"; const serverConfig = getServerSideConfig(); @@ -90,7 +88,7 @@ async function request(req: NextRequest) { // not undefined and is false if ( - isModelAvailableInServer( + isModelNotavailableInServer( serverConfig.customModels, jsonBody?.model as string, ServiceProvider.Moonshot as string, diff --git a/app/api/openai.ts b/app/api/openai.ts index 7dfd84e1785..5bb3a5dcb64 100644 --- a/app/api/openai.ts +++ b/app/api/openai.ts @@ -6,7 +6,7 @@ import { NextRequest, NextResponse } from "next/server"; import { auth } from "./auth"; import { requestOpenai } from "./common"; -const ALLOWD_PATH = new Set(Object.values(OpenaiPath)); +const ALLOWED_PATH = new Set(Object.values(OpenaiPath)); function getModels(remoteModelRes: OpenAIListModelResponse) { const config = getServerSideConfig(); @@ -14,8 +14,12 @@ function getModels(remoteModelRes: OpenAIListModelResponse) { if (config.disableGPT4) { remoteModelRes.data = remoteModelRes.data.filter( (m) => - !(m.id.startsWith("gpt-4") || m.id.startsWith("chatgpt-4o")) || - m.id.startsWith("gpt-4o-mini"), + !( + m.id.startsWith("gpt-4") || + m.id.startsWith("chatgpt-4o") || + m.id.startsWith("o1") || + m.id.startsWith("o3") + ) || m.id.startsWith("gpt-4o-mini"), ); } @@ -34,7 +38,7 @@ export async function handle( const subpath = params.path.join("/"); - if (!ALLOWD_PATH.has(subpath)) { + if (!ALLOWED_PATH.has(subpath)) { console.log("[OpenAI Route] forbidden path ", subpath); return NextResponse.json( { diff --git a/app/api/proxy.ts b/app/api/proxy.ts index 731003aa1ea..b3e5e7b7b93 100644 --- a/app/api/proxy.ts +++ b/app/api/proxy.ts @@ -1,4 +1,5 @@ import { NextRequest, NextResponse } from "next/server"; +import { getServerSideConfig } from "@/app/config/server"; export async function handle( req: NextRequest, @@ -9,6 +10,7 @@ export async function handle( if (req.method === "OPTIONS") { return NextResponse.json({ body: "OK" }, { status: 200 }); } + const serverConfig = getServerSideConfig(); // remove path params from searchParams req.nextUrl.searchParams.delete("path"); @@ -31,6 +33,18 @@ export async function handle( return true; }), ); + // if dalle3 use openai api key + const baseUrl = req.headers.get("x-base-url"); + if (baseUrl?.includes("api.openai.com")) { + if (!serverConfig.apiKey) { + return NextResponse.json( + { error: "OpenAI API key not configured" }, + { status: 500 }, + ); + } + headers.set("Authorization", `Bearer ${serverConfig.apiKey}`); + } + const controller = new AbortController(); const fetchOptions: RequestInit = { headers, diff --git a/app/api/siliconflow.ts b/app/api/siliconflow.ts new file mode 100644 index 00000000000..e298a21d43c --- /dev/null +++ b/app/api/siliconflow.ts @@ -0,0 +1,128 @@ +import { getServerSideConfig } from "@/app/config/server"; +import { + SILICONFLOW_BASE_URL, + ApiPath, + ModelProvider, + ServiceProvider, +} from "@/app/constant"; +import { prettyObject } from "@/app/utils/format"; +import { NextRequest, NextResponse } from "next/server"; +import { auth } from "@/app/api/auth"; +import { isModelNotavailableInServer } from "@/app/utils/model"; + +const serverConfig = getServerSideConfig(); + +export async function handle( + req: NextRequest, + { params }: { params: { path: string[] } }, +) { + console.log("[SiliconFlow Route] params ", params); + + if (req.method === "OPTIONS") { + return NextResponse.json({ body: "OK" }, { status: 200 }); + } + + const authResult = auth(req, ModelProvider.SiliconFlow); + if (authResult.error) { + return NextResponse.json(authResult, { + status: 401, + }); + } + + try { + const response = await request(req); + return response; + } catch (e) { + console.error("[SiliconFlow] ", e); + return NextResponse.json(prettyObject(e)); + } +} + +async function request(req: NextRequest) { + const controller = new AbortController(); + + // alibaba use base url or just remove the path + let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath.SiliconFlow, ""); + + let baseUrl = serverConfig.siliconFlowUrl || SILICONFLOW_BASE_URL; + + if (!baseUrl.startsWith("http")) { + baseUrl = `https://${baseUrl}`; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, -1); + } + + console.log("[Proxy] ", path); + console.log("[Base Url]", baseUrl); + + const timeoutId = setTimeout( + () => { + controller.abort(); + }, + 10 * 60 * 1000, + ); + + const fetchUrl = `${baseUrl}${path}`; + const fetchOptions: RequestInit = { + headers: { + "Content-Type": "application/json", + Authorization: req.headers.get("Authorization") ?? "", + }, + method: req.method, + body: req.body, + redirect: "manual", + // @ts-ignore + duplex: "half", + signal: controller.signal, + }; + + // #1815 try to refuse some request to some models + if (serverConfig.customModels && req.body) { + try { + const clonedBody = await req.text(); + fetchOptions.body = clonedBody; + + const jsonBody = JSON.parse(clonedBody) as { model?: string }; + + // not undefined and is false + if ( + isModelNotavailableInServer( + serverConfig.customModels, + jsonBody?.model as string, + ServiceProvider.SiliconFlow as string, + ) + ) { + return NextResponse.json( + { + error: true, + message: `you are not allowed to use ${jsonBody?.model} model`, + }, + { + status: 403, + }, + ); + } + } catch (e) { + console.error(`[SiliconFlow] filter`, e); + } + } + try { + const res = await fetch(fetchUrl, fetchOptions); + + // to prevent browser prompt for credentials + const newHeaders = new Headers(res.headers); + newHeaders.delete("www-authenticate"); + // to disable nginx buffering + newHeaders.set("X-Accel-Buffering", "no"); + + return new Response(res.body, { + status: res.status, + statusText: res.statusText, + headers: newHeaders, + }); + } finally { + clearTimeout(timeoutId); + } +} diff --git a/app/api/tencent/route.ts b/app/api/tencent/route.ts index 885909e7a75..fc4f8c79edf 100644 --- a/app/api/tencent/route.ts +++ b/app/api/tencent/route.ts @@ -1,15 +1,8 @@ import { getServerSideConfig } from "@/app/config/server"; -import { - TENCENT_BASE_URL, - ApiPath, - ModelProvider, - ServiceProvider, - Tencent, -} from "@/app/constant"; +import { TENCENT_BASE_URL, ModelProvider } from "@/app/constant"; import { prettyObject } from "@/app/utils/format"; import { NextRequest, NextResponse } from "next/server"; import { auth } from "@/app/api/auth"; -import { isModelAvailableInServer } from "@/app/utils/model"; import { getHeader } from "@/app/utils/tencent"; const serverConfig = getServerSideConfig(); diff --git a/app/api/webdav/[...path]/route.ts b/app/api/webdav/[...path]/route.ts index 9f96cbfcf74..bb7743bda40 100644 --- a/app/api/webdav/[...path]/route.ts +++ b/app/api/webdav/[...path]/route.ts @@ -6,7 +6,7 @@ const config = getServerSideConfig(); const mergedAllowedWebDavEndpoints = [ ...internalAllowedWebDavEndpoints, - ...config.allowedWebDevEndpoints, + ...config.allowedWebDavEndpoints, ].filter((domain) => Boolean(domain.trim())); const normalizeUrl = (url: string) => { diff --git a/app/api/xai.ts b/app/api/xai.ts new file mode 100644 index 00000000000..4aad5e5fb3e --- /dev/null +++ b/app/api/xai.ts @@ -0,0 +1,128 @@ +import { getServerSideConfig } from "@/app/config/server"; +import { + XAI_BASE_URL, + ApiPath, + ModelProvider, + ServiceProvider, +} from "@/app/constant"; +import { prettyObject } from "@/app/utils/format"; +import { NextRequest, NextResponse } from "next/server"; +import { auth } from "@/app/api/auth"; +import { isModelNotavailableInServer } from "@/app/utils/model"; + +const serverConfig = getServerSideConfig(); + +export async function handle( + req: NextRequest, + { params }: { params: { path: string[] } }, +) { + console.log("[XAI Route] params ", params); + + if (req.method === "OPTIONS") { + return NextResponse.json({ body: "OK" }, { status: 200 }); + } + + const authResult = auth(req, ModelProvider.XAI); + if (authResult.error) { + return NextResponse.json(authResult, { + status: 401, + }); + } + + try { + const response = await request(req); + return response; + } catch (e) { + console.error("[XAI] ", e); + return NextResponse.json(prettyObject(e)); + } +} + +async function request(req: NextRequest) { + const controller = new AbortController(); + + // alibaba use base url or just remove the path + let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath.XAI, ""); + + let baseUrl = serverConfig.xaiUrl || XAI_BASE_URL; + + if (!baseUrl.startsWith("http")) { + baseUrl = `https://${baseUrl}`; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, -1); + } + + console.log("[Proxy] ", path); + console.log("[Base Url]", baseUrl); + + const timeoutId = setTimeout( + () => { + controller.abort(); + }, + 10 * 60 * 1000, + ); + + const fetchUrl = `${baseUrl}${path}`; + const fetchOptions: RequestInit = { + headers: { + "Content-Type": "application/json", + Authorization: req.headers.get("Authorization") ?? "", + }, + method: req.method, + body: req.body, + redirect: "manual", + // @ts-ignore + duplex: "half", + signal: controller.signal, + }; + + // #1815 try to refuse some request to some models + if (serverConfig.customModels && req.body) { + try { + const clonedBody = await req.text(); + fetchOptions.body = clonedBody; + + const jsonBody = JSON.parse(clonedBody) as { model?: string }; + + // not undefined and is false + if ( + isModelNotavailableInServer( + serverConfig.customModels, + jsonBody?.model as string, + ServiceProvider.XAI as string, + ) + ) { + return NextResponse.json( + { + error: true, + message: `you are not allowed to use ${jsonBody?.model} model`, + }, + { + status: 403, + }, + ); + } + } catch (e) { + console.error(`[XAI] filter`, e); + } + } + try { + const res = await fetch(fetchUrl, fetchOptions); + + // to prevent browser prompt for credentials + const newHeaders = new Headers(res.headers); + newHeaders.delete("www-authenticate"); + // to disable nginx buffering + newHeaders.set("X-Accel-Buffering", "no"); + + return new Response(res.body, { + status: res.status, + statusText: res.statusText, + headers: newHeaders, + }); + } finally { + clearTimeout(timeoutId); + } +} diff --git a/app/client/api.ts b/app/client/api.ts index cecc453baa2..f60b0e2ad71 100644 --- a/app/client/api.ts +++ b/app/client/api.ts @@ -1,7 +1,6 @@ import { getClientConfig } from "../config/client"; import { ACCESS_CODE_PREFIX, - Azure, ModelProvider, ServiceProvider, } from "../constant"; @@ -21,11 +20,17 @@ import { QwenApi } from "./platforms/alibaba"; import { HunyuanApi } from "./platforms/tencent"; import { MoonshotApi } from "./platforms/moonshot"; import { SparkApi } from "./platforms/iflytek"; +import { DeepSeekApi } from "./platforms/deepseek"; +import { XAIApi } from "./platforms/xai"; +import { ChatGLMApi } from "./platforms/glm"; +import { SiliconflowApi } from "./platforms/siliconflow"; +import { Ai302Api } from "./platforms/ai302"; export const ROLES = ["system", "user", "assistant"] as const; export type MessageRole = (typeof ROLES)[number]; export const Models = ["gpt-3.5-turbo", "gpt-4"] as const; +export const TTSModels = ["tts-1", "tts-1-hd"] as const; export type ChatModel = ModelType; export interface MultimodalContent { @@ -36,6 +41,11 @@ export interface MultimodalContent { }; } +export interface MultimodalContentForAlibaba { + text?: string; + image?: string; +} + export interface RequestMessage { role: MessageRole; content: string | MultimodalContent[]; @@ -54,12 +64,21 @@ export interface LLMConfig { style?: DalleRequestPayload["style"]; } +export interface SpeechOptions { + model: string; + input: string; + voice: string; + response_format?: string; + speed?: number; + onController?: (controller: AbortController) => void; +} + export interface ChatOptions { messages: RequestMessage[]; config: LLMConfig; onUpdate?: (message: string, chunk: string) => void; - onFinish: (message: string) => void; + onFinish: (message: string, responseRes: Response) => void; onError?: (err: Error) => void; onController?: (controller: AbortController) => void; onBeforeTool?: (tool: ChatMessageTool) => void; @@ -88,6 +107,7 @@ export interface LLMModelProvider { export abstract class LLMApi { abstract chat(options: ChatOptions): Promise; + abstract speech(options: SpeechOptions): Promise; abstract usage(): Promise; abstract models(): Promise; } @@ -142,6 +162,21 @@ export class ClientApi { case ModelProvider.Iflytek: this.llm = new SparkApi(); break; + case ModelProvider.DeepSeek: + this.llm = new DeepSeekApi(); + break; + case ModelProvider.XAI: + this.llm = new XAIApi(); + break; + case ModelProvider.ChatGLM: + this.llm = new ChatGLMApi(); + break; + case ModelProvider.SiliconFlow: + this.llm = new SiliconflowApi(); + break; + case ModelProvider["302.AI"]: + this.llm = new Ai302Api(); + break; default: this.llm = new ChatGPTApi(); } @@ -206,19 +241,22 @@ export function validString(x: string): boolean { return x?.length > 0; } -export function getHeaders() { +export function getHeaders(ignoreHeaders: boolean = false) { const accessStore = useAccessStore.getState(); const chatStore = useChatStore.getState(); - const headers: Record = { - "Content-Type": "application/json", - Accept: "application/json", - }; + let headers: Record = {}; + if (!ignoreHeaders) { + headers = { + "Content-Type": "application/json", + Accept: "application/json", + }; + } const clientConfig = getClientConfig(); function getConfig() { const modelConfig = chatStore.currentSession().mask.modelConfig; - const isGoogle = modelConfig.providerName == ServiceProvider.Google; + const isGoogle = modelConfig.providerName === ServiceProvider.Google; const isAzure = modelConfig.providerName === ServiceProvider.Azure; const isAnthropic = modelConfig.providerName === ServiceProvider.Anthropic; const isBaidu = modelConfig.providerName == ServiceProvider.Baidu; @@ -226,6 +264,12 @@ export function getHeaders() { const isAlibaba = modelConfig.providerName === ServiceProvider.Alibaba; const isMoonshot = modelConfig.providerName === ServiceProvider.Moonshot; const isIflytek = modelConfig.providerName === ServiceProvider.Iflytek; + const isDeepSeek = modelConfig.providerName === ServiceProvider.DeepSeek; + const isXAI = modelConfig.providerName === ServiceProvider.XAI; + const isChatGLM = modelConfig.providerName === ServiceProvider.ChatGLM; + const isSiliconFlow = + modelConfig.providerName === ServiceProvider.SiliconFlow; + const isAI302 = modelConfig.providerName === ServiceProvider["302.AI"]; const isEnabledAccessControl = accessStore.enabledAccessControl(); const apiKey = isGoogle ? accessStore.googleApiKey @@ -239,10 +283,20 @@ export function getHeaders() { ? accessStore.alibabaApiKey : isMoonshot ? accessStore.moonshotApiKey + : isXAI + ? accessStore.xaiApiKey + : isDeepSeek + ? accessStore.deepseekApiKey + : isChatGLM + ? accessStore.chatglmApiKey + : isSiliconFlow + ? accessStore.siliconflowApiKey : isIflytek ? accessStore.iflytekApiKey && accessStore.iflytekApiSecret ? accessStore.iflytekApiKey + ":" + accessStore.iflytekApiSecret : "" + : isAI302 + ? accessStore.ai302ApiKey : accessStore.openaiApiKey; return { isGoogle, @@ -253,13 +307,24 @@ export function getHeaders() { isAlibaba, isMoonshot, isIflytek, + isDeepSeek, + isXAI, + isChatGLM, + isSiliconFlow, + isAI302, apiKey, isEnabledAccessControl, }; } function getAuthHeader(): string { - return isAzure ? "api-key" : isAnthropic ? "x-api-key" : "Authorization"; + return isAzure + ? "api-key" + : isAnthropic + ? "x-api-key" + : isGoogle + ? "x-goog-api-key" + : "Authorization"; } const { @@ -267,17 +332,27 @@ export function getHeaders() { isAzure, isAnthropic, isBaidu, + isByteDance, + isAlibaba, + isMoonshot, + isIflytek, + isDeepSeek, + isXAI, + isChatGLM, + isSiliconFlow, + isAI302, apiKey, isEnabledAccessControl, } = getConfig(); - // when using google api in app, not set auth header - if (isGoogle && clientConfig?.isApp) return headers; // when using baidu api in app, not set auth header if (isBaidu && clientConfig?.isApp) return headers; const authHeader = getAuthHeader(); - const bearerToken = getBearerToken(apiKey, isAzure || isAnthropic); + const bearerToken = getBearerToken( + apiKey, + isAzure || isAnthropic || isGoogle, + ); if (bearerToken) { headers[authHeader] = bearerToken; @@ -308,6 +383,16 @@ export function getClientApi(provider: ServiceProvider): ClientApi { return new ClientApi(ModelProvider.Moonshot); case ServiceProvider.Iflytek: return new ClientApi(ModelProvider.Iflytek); + case ServiceProvider.DeepSeek: + return new ClientApi(ModelProvider.DeepSeek); + case ServiceProvider.XAI: + return new ClientApi(ModelProvider.XAI); + case ServiceProvider.ChatGLM: + return new ClientApi(ModelProvider.ChatGLM); + case ServiceProvider.SiliconFlow: + return new ClientApi(ModelProvider.SiliconFlow); + case ServiceProvider["302.AI"]: + return new ClientApi(ModelProvider["302.AI"]); default: return new ClientApi(ModelProvider.GPT); } diff --git a/app/client/platforms/ai302.ts b/app/client/platforms/ai302.ts new file mode 100644 index 00000000000..7bd18f96d4c --- /dev/null +++ b/app/client/platforms/ai302.ts @@ -0,0 +1,287 @@ +"use client"; + +import { + ApiPath, + AI302_BASE_URL, + DEFAULT_MODELS, + AI302, +} from "@/app/constant"; +import { + useAccessStore, + useAppConfig, + useChatStore, + ChatMessageTool, + usePluginStore, +} from "@/app/store"; +import { preProcessImageContent, streamWithThink } from "@/app/utils/chat"; +import { + ChatOptions, + getHeaders, + LLMApi, + LLMModel, + SpeechOptions, +} from "../api"; +import { getClientConfig } from "@/app/config/client"; +import { + getMessageTextContent, + getMessageTextContentWithoutThinking, + isVisionModel, + getTimeoutMSByModel, +} from "@/app/utils"; +import { RequestPayload } from "./openai"; + +import { fetch } from "@/app/utils/stream"; +export interface Ai302ListModelResponse { + object: string; + data: Array<{ + id: string; + object: string; + root: string; + }>; +} + +export class Ai302Api implements LLMApi { + private disableListModels = false; + + path(path: string): string { + const accessStore = useAccessStore.getState(); + + let baseUrl = ""; + + if (accessStore.useCustomConfig) { + baseUrl = accessStore.ai302Url; + } + + if (baseUrl.length === 0) { + const isApp = !!getClientConfig()?.isApp; + const apiPath = ApiPath["302.AI"]; + baseUrl = isApp ? AI302_BASE_URL : apiPath; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, baseUrl.length - 1); + } + if ( + !baseUrl.startsWith("http") && + !baseUrl.startsWith(ApiPath["302.AI"]) + ) { + baseUrl = "https://" + baseUrl; + } + + console.log("[Proxy Endpoint] ", baseUrl, path); + + return [baseUrl, path].join("/"); + } + + extractMessage(res: any) { + return res.choices?.at(0)?.message?.content ?? ""; + } + + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + + async chat(options: ChatOptions) { + const visionModel = isVisionModel(options.config.model); + const messages: ChatOptions["messages"] = []; + for (const v of options.messages) { + if (v.role === "assistant") { + const content = getMessageTextContentWithoutThinking(v); + messages.push({ role: v.role, content }); + } else { + const content = visionModel + ? await preProcessImageContent(v.content) + : getMessageTextContent(v); + messages.push({ role: v.role, content }); + } + } + + const modelConfig = { + ...useAppConfig.getState().modelConfig, + ...useChatStore.getState().currentSession().mask.modelConfig, + ...{ + model: options.config.model, + providerName: options.config.providerName, + }, + }; + + const requestPayload: RequestPayload = { + messages, + stream: options.config.stream, + model: modelConfig.model, + temperature: modelConfig.temperature, + presence_penalty: modelConfig.presence_penalty, + frequency_penalty: modelConfig.frequency_penalty, + top_p: modelConfig.top_p, + // max_tokens: Math.max(modelConfig.max_tokens, 1024), + // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore. + }; + + console.log("[Request] openai payload: ", requestPayload); + + const shouldStream = !!options.config.stream; + const controller = new AbortController(); + options.onController?.(controller); + + try { + const chatPath = this.path(AI302.ChatPath); + const chatPayload = { + method: "POST", + body: JSON.stringify(requestPayload), + signal: controller.signal, + headers: getHeaders(), + }; + + // console.log(chatPayload); + + // Use extended timeout for thinking models as they typically require more processing time + const requestTimeoutId = setTimeout( + () => controller.abort(), + getTimeoutMSByModel(options.config.model), + ); + + if (shouldStream) { + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return streamWithThink( + chatPath, + requestPayload, + getHeaders(), + tools as any, + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + // console.log("parseSSE", text, runTools); + const json = JSON.parse(text); + const choices = json.choices as Array<{ + delta: { + content: string | null; + tool_calls: ChatMessageTool[]; + reasoning_content: string | null; + }; + }>; + const tool_calls = choices[0]?.delta?.tool_calls; + if (tool_calls?.length > 0) { + const index = tool_calls[0]?.index; + const id = tool_calls[0]?.id; + const args = tool_calls[0]?.function?.arguments; + if (id) { + runTools.push({ + id, + type: tool_calls[0]?.type, + function: { + name: tool_calls[0]?.function?.name as string, + arguments: args, + }, + }); + } else { + // @ts-ignore + runTools[index]["function"]["arguments"] += args; + } + } + const reasoning = choices[0]?.delta?.reasoning_content; + const content = choices[0]?.delta?.content; + + // Skip if both content and reasoning_content are empty or null + if ( + (!reasoning || reasoning.length === 0) && + (!content || content.length === 0) + ) { + return { + isThinking: false, + content: "", + }; + } + + if (reasoning && reasoning.length > 0) { + return { + isThinking: true, + content: reasoning, + }; + } else if (content && content.length > 0) { + return { + isThinking: false, + content: content, + }; + } + + return { + isThinking: false, + content: "", + }; + }, + // processToolMessage, include tool_calls message and tool call results + ( + requestPayload: RequestPayload, + toolCallMessage: any, + toolCallResult: any[], + ) => { + // @ts-ignore + requestPayload?.messages?.splice( + // @ts-ignore + requestPayload?.messages?.length, + 0, + toolCallMessage, + ...toolCallResult, + ); + }, + options, + ); + } else { + const res = await fetch(chatPath, chatPayload); + clearTimeout(requestTimeoutId); + + const resJson = await res.json(); + const message = this.extractMessage(resJson); + options.onFinish(message, res); + } + } catch (e) { + console.log("[Request] failed to make a chat request", e); + options.onError?.(e as Error); + } + } + async usage() { + return { + used: 0, + total: 0, + }; + } + + async models(): Promise { + if (this.disableListModels) { + return DEFAULT_MODELS.slice(); + } + + const res = await fetch(this.path(AI302.ListModelPath), { + method: "GET", + headers: { + ...getHeaders(), + }, + }); + + const resJson = (await res.json()) as Ai302ListModelResponse; + const chatModels = resJson.data; + console.log("[Models]", chatModels); + + if (!chatModels) { + return []; + } + + let seq = 1000; //同 Constant.ts 中的排序保持一致 + return chatModels.map((m) => ({ + name: m.id, + available: true, + sorted: seq++, + provider: { + id: "ai302", + providerName: "302.AI", + providerType: "ai302", + sorted: 15, + }, + })); + } +} diff --git a/app/client/platforms/alibaba.ts b/app/client/platforms/alibaba.ts index d5fa3042fc1..4875e5c02d9 100644 --- a/app/client/platforms/alibaba.ts +++ b/app/client/platforms/alibaba.ts @@ -1,27 +1,33 @@ "use client"; +import { ApiPath, Alibaba, ALIBABA_BASE_URL } from "@/app/constant"; import { - ApiPath, - Alibaba, - ALIBABA_BASE_URL, - REQUEST_TIMEOUT_MS, -} from "@/app/constant"; -import { useAccessStore, useAppConfig, useChatStore } from "@/app/store"; - + useAccessStore, + useAppConfig, + useChatStore, + ChatMessageTool, + usePluginStore, +} from "@/app/store"; +import { + preProcessImageContentForAlibabaDashScope, + streamWithThink, +} from "@/app/utils/chat"; import { ChatOptions, getHeaders, LLMApi, LLMModel, + SpeechOptions, MultimodalContent, + MultimodalContentForAlibaba, } from "../api"; -import Locale from "../../locales"; -import { - EventStreamContentType, - fetchEventSource, -} from "@fortaine/fetch-event-source"; -import { prettyObject } from "@/app/utils/format"; import { getClientConfig } from "@/app/config/client"; -import { getMessageTextContent } from "@/app/utils"; +import { + getMessageTextContent, + getMessageTextContentWithoutThinking, + getTimeoutMSByModel, + isVisionModel, +} from "@/app/utils"; +import { fetch } from "@/app/utils/stream"; export interface OpenAIListModelResponse { object: string; @@ -83,12 +89,11 @@ export class QwenApi implements LLMApi { return res?.output?.choices?.at(0)?.message?.content ?? ""; } - async chat(options: ChatOptions) { - const messages = options.messages.map((v) => ({ - role: v.role, - content: getMessageTextContent(v), - })); + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + async chat(options: ChatOptions) { const modelConfig = { ...useAppConfig.getState().modelConfig, ...useChatStore.getState().currentSession().mask.modelConfig, @@ -97,6 +102,21 @@ export class QwenApi implements LLMApi { }, }; + const visionModel = isVisionModel(options.config.model); + + const messages: ChatOptions["messages"] = []; + for (const v of options.messages) { + const content = ( + visionModel + ? await preProcessImageContentForAlibabaDashScope(v.content) + : v.role === "assistant" + ? getMessageTextContentWithoutThinking(v) + : getMessageTextContent(v) + ) as any; + + messages.push({ role: v.role, content }); + } + const shouldStream = !!options.config.stream; const requestPayload: RequestPayload = { model: modelConfig.model, @@ -116,138 +136,127 @@ export class QwenApi implements LLMApi { options.onController?.(controller); try { - const chatPath = this.path(Alibaba.ChatPath); + const headers = { + ...getHeaders(), + "X-DashScope-SSE": shouldStream ? "enable" : "disable", + }; + + const chatPath = this.path(Alibaba.ChatPath(modelConfig.model)); const chatPayload = { method: "POST", body: JSON.stringify(requestPayload), signal: controller.signal, - headers: { - ...getHeaders(), - "X-DashScope-SSE": shouldStream ? "enable" : "disable", - }, + headers: headers, }; // make a fetch request const requestTimeoutId = setTimeout( () => controller.abort(), - REQUEST_TIMEOUT_MS, + getTimeoutMSByModel(options.config.model), ); if (shouldStream) { - let responseText = ""; - let remainText = ""; - let finished = false; - - // animate response to make it looks smooth - function animateResponseText() { - if (finished || controller.signal.aborted) { - responseText += remainText; - console.log("[Response Animation] finished"); - if (responseText?.length === 0) { - options.onError?.(new Error("empty response from server")); + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return streamWithThink( + chatPath, + requestPayload, + headers, + tools as any, + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + // console.log("parseSSE", text, runTools); + const json = JSON.parse(text); + const choices = json.output.choices as Array<{ + message: { + content: string | null | MultimodalContentForAlibaba[]; + tool_calls: ChatMessageTool[]; + reasoning_content: string | null; + }; + }>; + + if (!choices?.length) return { isThinking: false, content: "" }; + + const tool_calls = choices[0]?.message?.tool_calls; + if (tool_calls?.length > 0) { + const index = tool_calls[0]?.index; + const id = tool_calls[0]?.id; + const args = tool_calls[0]?.function?.arguments; + if (id) { + runTools.push({ + id, + type: tool_calls[0]?.type, + function: { + name: tool_calls[0]?.function?.name as string, + arguments: args, + }, + }); + } else { + // @ts-ignore + runTools[index]["function"]["arguments"] += args; + } } - return; - } - - if (remainText.length > 0) { - const fetchCount = Math.max(1, Math.round(remainText.length / 60)); - const fetchText = remainText.slice(0, fetchCount); - responseText += fetchText; - remainText = remainText.slice(fetchCount); - options.onUpdate?.(responseText, fetchText); - } - - requestAnimationFrame(animateResponseText); - } - - // start animaion - animateResponseText(); - const finish = () => { - if (!finished) { - finished = true; - options.onFinish(responseText + remainText); - } - }; - - controller.signal.onabort = finish; - - fetchEventSource(chatPath, { - ...chatPayload, - async onopen(res) { - clearTimeout(requestTimeoutId); - const contentType = res.headers.get("content-type"); - console.log( - "[Alibaba] request response content type: ", - contentType, - ); - - if (contentType?.startsWith("text/plain")) { - responseText = await res.clone().text(); - return finish(); - } + const reasoning = choices[0]?.message?.reasoning_content; + const content = choices[0]?.message?.content; + // Skip if both content and reasoning_content are empty or null if ( - !res.ok || - !res.headers - .get("content-type") - ?.startsWith(EventStreamContentType) || - res.status !== 200 + (!reasoning || reasoning.length === 0) && + (!content || content.length === 0) ) { - const responseTexts = [responseText]; - let extraInfo = await res.clone().text(); - try { - const resJson = await res.clone().json(); - extraInfo = prettyObject(resJson); - } catch {} - - if (res.status === 401) { - responseTexts.push(Locale.Error.Unauthorized); - } - - if (extraInfo) { - responseTexts.push(extraInfo); - } - - responseText = responseTexts.join("\n\n"); - - return finish(); + return { + isThinking: false, + content: "", + }; } - }, - onmessage(msg) { - if (msg.data === "[DONE]" || finished) { - return finish(); - } - const text = msg.data; - try { - const json = JSON.parse(text); - const choices = json.output.choices as Array<{ - message: { content: string }; - }>; - const delta = choices[0]?.message?.content; - if (delta) { - remainText += delta; - } - } catch (e) { - console.error("[Request] parse error", text, msg); + + if (reasoning && reasoning.length > 0) { + return { + isThinking: true, + content: reasoning, + }; + } else if (content && content.length > 0) { + return { + isThinking: false, + content: Array.isArray(content) + ? content.map((item) => item.text).join(",") + : content, + }; } + + return { + isThinking: false, + content: "", + }; }, - onclose() { - finish(); - }, - onerror(e) { - options.onError?.(e); - throw e; + // processToolMessage, include tool_calls message and tool call results + ( + requestPayload: RequestPayload, + toolCallMessage: any, + toolCallResult: any[], + ) => { + requestPayload?.input?.messages?.splice( + requestPayload?.input?.messages?.length, + 0, + toolCallMessage, + ...toolCallResult, + ); }, - openWhenHidden: true, - }); + options, + ); } else { const res = await fetch(chatPath, chatPayload); clearTimeout(requestTimeoutId); const resJson = await res.json(); const message = this.extractMessage(resJson); - options.onFinish(message); + options.onFinish(message, res); } } catch (e) { console.log("[Request] failed to make a chat request", e); diff --git a/app/client/platforms/anthropic.ts b/app/client/platforms/anthropic.ts index 7dd39c9cddc..2377470904f 100644 --- a/app/client/platforms/anthropic.ts +++ b/app/client/platforms/anthropic.ts @@ -1,5 +1,5 @@ -import { ACCESS_CODE_PREFIX, Anthropic, ApiPath } from "@/app/constant"; -import { ChatOptions, getHeaders, LLMApi, MultimodalContent } from "../api"; +import { Anthropic, ApiPath } from "@/app/constant"; +import { ChatOptions, getHeaders, LLMApi, SpeechOptions } from "../api"; import { useAccessStore, useAppConfig, @@ -8,18 +8,12 @@ import { ChatMessageTool, } from "@/app/store"; import { getClientConfig } from "@/app/config/client"; -import { DEFAULT_API_HOST } from "@/app/constant"; -import { - EventStreamContentType, - fetchEventSource, -} from "@fortaine/fetch-event-source"; - -import Locale from "../../locales"; -import { prettyObject } from "@/app/utils/format"; +import { ANTHROPIC_BASE_URL } from "@/app/constant"; import { getMessageTextContent, isVisionModel } from "@/app/utils"; import { preProcessImageContent, stream } from "@/app/utils/chat"; import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare"; import { RequestPayload } from "./openai"; +import { fetch } from "@/app/utils/stream"; export type MultiBlockContent = { type: "image" | "text"; @@ -80,6 +74,10 @@ const ClaudeMapper = { const keys = ["claude-2, claude-instant-1"]; export class ClaudeApi implements LLMApi { + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + extractMessage(res: any) { console.log("[Response] claude response: ", res); @@ -226,7 +224,7 @@ export class ClaudeApi implements LLMApi { let chunkJson: | undefined | { - type: "content_block_delta" | "content_block_stop"; + type: "content_block_delta" | "content_block_stop" | "message_delta" | "message_stop"; content_block?: { type: "tool_use"; id: string; @@ -236,11 +234,20 @@ export class ClaudeApi implements LLMApi { type: "text_delta" | "input_json_delta"; text?: string; partial_json?: string; + stop_reason?: string; }; index: number; }; chunkJson = JSON.parse(text); + // Handle refusal stop reason in message_delta + if (chunkJson?.delta?.stop_reason === "refusal") { + // Return a message to display to the user + const refusalMessage = "\n\n[Assistant refused to respond. Please modify your request and try again.]"; + options.onError?.(new Error("Content policy violation: " + refusalMessage)); + return refusalMessage; + } + if (chunkJson?.content_block?.type == "tool_use") { index += 1; const id = chunkJson?.content_block.id; @@ -319,13 +326,14 @@ export class ClaudeApi implements LLMApi { }; try { - controller.signal.onabort = () => options.onFinish(""); + controller.signal.onabort = () => + options.onFinish("", new Response(null, { status: 400 })); const res = await fetch(path, payload); const resJson = await res.json(); const message = this.extractMessage(resJson); - options.onFinish(message); + options.onFinish(message, res); } catch (e) { console.error("failed to chat", e); options.onError?.(e as Error); @@ -391,9 +399,7 @@ export class ClaudeApi implements LLMApi { if (baseUrl.trim().length === 0) { const isApp = !!getClientConfig()?.isApp; - baseUrl = isApp - ? DEFAULT_API_HOST + "/api/proxy/anthropic" - : ApiPath.Anthropic; + baseUrl = isApp ? ANTHROPIC_BASE_URL : ApiPath.Anthropic; } if (!baseUrl.startsWith("http") && !baseUrl.startsWith("/api")) { diff --git a/app/client/platforms/baidu.ts b/app/client/platforms/baidu.ts index 3be147f4985..dc990db4103 100644 --- a/app/client/platforms/baidu.ts +++ b/app/client/platforms/baidu.ts @@ -1,10 +1,5 @@ "use client"; -import { - ApiPath, - Baidu, - BAIDU_BASE_URL, - REQUEST_TIMEOUT_MS, -} from "@/app/constant"; +import { ApiPath, Baidu, BAIDU_BASE_URL } from "@/app/constant"; import { useAccessStore, useAppConfig, useChatStore } from "@/app/store"; import { getAccessToken } from "@/app/utils/baidu"; @@ -14,6 +9,7 @@ import { LLMApi, LLMModel, MultimodalContent, + SpeechOptions, } from "../api"; import Locale from "../../locales"; import { @@ -22,7 +18,8 @@ import { } from "@fortaine/fetch-event-source"; import { prettyObject } from "@/app/utils/format"; import { getClientConfig } from "@/app/config/client"; -import { getMessageTextContent } from "@/app/utils"; +import { getMessageTextContent, getTimeoutMSByModel } from "@/app/utils"; +import { fetch } from "@/app/utils/stream"; export interface OpenAIListModelResponse { object: string; @@ -75,6 +72,10 @@ export class ErnieApi implements LLMApi { return [baseUrl, path].join("/"); } + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + async chat(options: ChatOptions) { const messages = options.messages.map((v) => ({ // "error_code": 336006, "error_msg": "the role of message with even index in the messages must be user or function", @@ -149,13 +150,14 @@ export class ErnieApi implements LLMApi { // make a fetch request const requestTimeoutId = setTimeout( () => controller.abort(), - REQUEST_TIMEOUT_MS, + getTimeoutMSByModel(options.config.model), ); if (shouldStream) { let responseText = ""; let remainText = ""; let finished = false; + let responseRes: Response; // animate response to make it looks smooth function animateResponseText() { @@ -185,19 +187,20 @@ export class ErnieApi implements LLMApi { const finish = () => { if (!finished) { finished = true; - options.onFinish(responseText + remainText); + options.onFinish(responseText + remainText, responseRes); } }; controller.signal.onabort = finish; fetchEventSource(chatPath, { + fetch: fetch as any, ...chatPayload, async onopen(res) { clearTimeout(requestTimeoutId); const contentType = res.headers.get("content-type"); console.log("[Baidu] request response content type: ", contentType); - + responseRes = res; if (contentType?.startsWith("text/plain")) { responseText = await res.clone().text(); return finish(); @@ -260,7 +263,7 @@ export class ErnieApi implements LLMApi { const resJson = await res.json(); const message = resJson?.result; - options.onFinish(message); + options.onFinish(message, res); } } catch (e) { console.log("[Request] failed to make a chat request", e); diff --git a/app/client/platforms/bytedance.ts b/app/client/platforms/bytedance.ts index 7677cafe12b..f9524cba28d 100644 --- a/app/client/platforms/bytedance.ts +++ b/app/client/platforms/bytedance.ts @@ -1,11 +1,12 @@ "use client"; +import { ApiPath, ByteDance, BYTEDANCE_BASE_URL } from "@/app/constant"; import { - ApiPath, - ByteDance, - BYTEDANCE_BASE_URL, - REQUEST_TIMEOUT_MS, -} from "@/app/constant"; -import { useAccessStore, useAppConfig, useChatStore } from "@/app/store"; + useAccessStore, + useAppConfig, + useChatStore, + ChatMessageTool, + usePluginStore, +} from "@/app/store"; import { ChatOptions, @@ -13,15 +14,17 @@ import { LLMApi, LLMModel, MultimodalContent, + SpeechOptions, } from "../api"; -import Locale from "../../locales"; -import { - EventStreamContentType, - fetchEventSource, -} from "@fortaine/fetch-event-source"; -import { prettyObject } from "@/app/utils/format"; + +import { streamWithThink } from "@/app/utils/chat"; import { getClientConfig } from "@/app/config/client"; -import { getMessageTextContent } from "@/app/utils"; +import { preProcessImageContent } from "@/app/utils/chat"; +import { + getMessageTextContentWithoutThinking, + getTimeoutMSByModel, +} from "@/app/utils"; +import { fetch } from "@/app/utils/stream"; export interface OpenAIListModelResponse { object: string; @@ -32,7 +35,7 @@ export interface OpenAIListModelResponse { }>; } -interface RequestPayload { +interface RequestPayloadForByteDance { messages: { role: "system" | "user" | "assistant"; content: string | MultimodalContent[]; @@ -77,11 +80,19 @@ export class DoubaoApi implements LLMApi { return res.choices?.at(0)?.message?.content ?? ""; } + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + async chat(options: ChatOptions) { - const messages = options.messages.map((v) => ({ - role: v.role, - content: getMessageTextContent(v), - })); + const messages: ChatOptions["messages"] = []; + for (const v of options.messages) { + const content = + v.role === "assistant" + ? getMessageTextContentWithoutThinking(v) + : await preProcessImageContent(v.content); + messages.push({ role: v.role, content }); + } const modelConfig = { ...useAppConfig.getState().modelConfig, @@ -92,7 +103,7 @@ export class DoubaoApi implements LLMApi { }; const shouldStream = !!options.config.stream; - const requestPayload: RequestPayload = { + const requestPayload: RequestPayloadForByteDance = { messages, stream: shouldStream, model: modelConfig.model, @@ -117,124 +128,108 @@ export class DoubaoApi implements LLMApi { // make a fetch request const requestTimeoutId = setTimeout( () => controller.abort(), - REQUEST_TIMEOUT_MS, + getTimeoutMSByModel(options.config.model), ); if (shouldStream) { - let responseText = ""; - let remainText = ""; - let finished = false; - - // animate response to make it looks smooth - function animateResponseText() { - if (finished || controller.signal.aborted) { - responseText += remainText; - console.log("[Response Animation] finished"); - if (responseText?.length === 0) { - options.onError?.(new Error("empty response from server")); - } - return; - } - - if (remainText.length > 0) { - const fetchCount = Math.max(1, Math.round(remainText.length / 60)); - const fetchText = remainText.slice(0, fetchCount); - responseText += fetchText; - remainText = remainText.slice(fetchCount); - options.onUpdate?.(responseText, fetchText); - } - - requestAnimationFrame(animateResponseText); - } - - // start animaion - animateResponseText(); - - const finish = () => { - if (!finished) { - finished = true; - options.onFinish(responseText + remainText); - } - }; - - controller.signal.onabort = finish; - - fetchEventSource(chatPath, { - ...chatPayload, - async onopen(res) { - clearTimeout(requestTimeoutId); - const contentType = res.headers.get("content-type"); - console.log( - "[ByteDance] request response content type: ", - contentType, - ); - - if (contentType?.startsWith("text/plain")) { - responseText = await res.clone().text(); - return finish(); + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return streamWithThink( + chatPath, + requestPayload, + getHeaders(), + tools as any, + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + // console.log("parseSSE", text, runTools); + const json = JSON.parse(text); + const choices = json.choices as Array<{ + delta: { + content: string | null; + tool_calls: ChatMessageTool[]; + reasoning_content: string | null; + }; + }>; + + if (!choices?.length) return { isThinking: false, content: "" }; + + const tool_calls = choices[0]?.delta?.tool_calls; + if (tool_calls?.length > 0) { + const index = tool_calls[0]?.index; + const id = tool_calls[0]?.id; + const args = tool_calls[0]?.function?.arguments; + if (id) { + runTools.push({ + id, + type: tool_calls[0]?.type, + function: { + name: tool_calls[0]?.function?.name as string, + arguments: args, + }, + }); + } else { + // @ts-ignore + runTools[index]["function"]["arguments"] += args; + } } + const reasoning = choices[0]?.delta?.reasoning_content; + const content = choices[0]?.delta?.content; + // Skip if both content and reasoning_content are empty or null if ( - !res.ok || - !res.headers - .get("content-type") - ?.startsWith(EventStreamContentType) || - res.status !== 200 + (!reasoning || reasoning.length === 0) && + (!content || content.length === 0) ) { - const responseTexts = [responseText]; - let extraInfo = await res.clone().text(); - try { - const resJson = await res.clone().json(); - extraInfo = prettyObject(resJson); - } catch {} - - if (res.status === 401) { - responseTexts.push(Locale.Error.Unauthorized); - } - - if (extraInfo) { - responseTexts.push(extraInfo); - } - - responseText = responseTexts.join("\n\n"); - - return finish(); - } - }, - onmessage(msg) { - if (msg.data === "[DONE]" || finished) { - return finish(); + return { + isThinking: false, + content: "", + }; } - const text = msg.data; - try { - const json = JSON.parse(text); - const choices = json.choices as Array<{ - delta: { content: string }; - }>; - const delta = choices[0]?.delta?.content; - if (delta) { - remainText += delta; - } - } catch (e) { - console.error("[Request] parse error", text, msg); + + if (reasoning && reasoning.length > 0) { + return { + isThinking: true, + content: reasoning, + }; + } else if (content && content.length > 0) { + return { + isThinking: false, + content: content, + }; } + + return { + isThinking: false, + content: "", + }; }, - onclose() { - finish(); - }, - onerror(e) { - options.onError?.(e); - throw e; + // processToolMessage, include tool_calls message and tool call results + ( + requestPayload: RequestPayloadForByteDance, + toolCallMessage: any, + toolCallResult: any[], + ) => { + requestPayload?.messages?.splice( + requestPayload?.messages?.length, + 0, + toolCallMessage, + ...toolCallResult, + ); }, - openWhenHidden: true, - }); + options, + ); } else { const res = await fetch(chatPath, chatPayload); clearTimeout(requestTimeoutId); const resJson = await res.json(); const message = this.extractMessage(resJson); - options.onFinish(message); + options.onFinish(message, res); } } catch (e) { console.log("[Request] failed to make a chat request", e); diff --git a/app/client/platforms/deepseek.ts b/app/client/platforms/deepseek.ts new file mode 100644 index 00000000000..1b38b40cc64 --- /dev/null +++ b/app/client/platforms/deepseek.ts @@ -0,0 +1,253 @@ +"use client"; +// azure and openai, using same models. so using same LLMApi. +import { ApiPath, DEEPSEEK_BASE_URL, DeepSeek } from "@/app/constant"; +import { + useAccessStore, + useAppConfig, + useChatStore, + ChatMessageTool, + usePluginStore, +} from "@/app/store"; +import { streamWithThink } from "@/app/utils/chat"; +import { + ChatOptions, + getHeaders, + LLMApi, + LLMModel, + SpeechOptions, +} from "../api"; +import { getClientConfig } from "@/app/config/client"; +import { + getMessageTextContent, + getMessageTextContentWithoutThinking, + getTimeoutMSByModel, +} from "@/app/utils"; +import { RequestPayload } from "./openai"; +import { fetch } from "@/app/utils/stream"; + +export class DeepSeekApi implements LLMApi { + private disableListModels = true; + + path(path: string): string { + const accessStore = useAccessStore.getState(); + + let baseUrl = ""; + + if (accessStore.useCustomConfig) { + baseUrl = accessStore.deepseekUrl; + } + + if (baseUrl.length === 0) { + const isApp = !!getClientConfig()?.isApp; + const apiPath = ApiPath.DeepSeek; + baseUrl = isApp ? DEEPSEEK_BASE_URL : apiPath; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, baseUrl.length - 1); + } + if (!baseUrl.startsWith("http") && !baseUrl.startsWith(ApiPath.DeepSeek)) { + baseUrl = "https://" + baseUrl; + } + + console.log("[Proxy Endpoint] ", baseUrl, path); + + return [baseUrl, path].join("/"); + } + + extractMessage(res: any) { + return res.choices?.at(0)?.message?.content ?? ""; + } + + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + + async chat(options: ChatOptions) { + const messages: ChatOptions["messages"] = []; + for (const v of options.messages) { + if (v.role === "assistant") { + const content = getMessageTextContentWithoutThinking(v); + messages.push({ role: v.role, content }); + } else { + const content = getMessageTextContent(v); + messages.push({ role: v.role, content }); + } + } + + // 检测并修复消息顺序,确保除system外的第一个消息是user + const filteredMessages: ChatOptions["messages"] = []; + let hasFoundFirstUser = false; + + for (const msg of messages) { + if (msg.role === "system") { + // Keep all system messages + filteredMessages.push(msg); + } else if (msg.role === "user") { + // User message directly added + filteredMessages.push(msg); + hasFoundFirstUser = true; + } else if (hasFoundFirstUser) { + // After finding the first user message, all subsequent non-system messages are retained. + filteredMessages.push(msg); + } + // If hasFoundFirstUser is false and it is not a system message, it will be skipped. + } + + const modelConfig = { + ...useAppConfig.getState().modelConfig, + ...useChatStore.getState().currentSession().mask.modelConfig, + ...{ + model: options.config.model, + providerName: options.config.providerName, + }, + }; + + const requestPayload: RequestPayload = { + messages: filteredMessages, + stream: options.config.stream, + model: modelConfig.model, + temperature: modelConfig.temperature, + presence_penalty: modelConfig.presence_penalty, + frequency_penalty: modelConfig.frequency_penalty, + top_p: modelConfig.top_p, + // max_tokens: Math.max(modelConfig.max_tokens, 1024), + // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore. + }; + + console.log("[Request] openai payload: ", requestPayload); + + const shouldStream = !!options.config.stream; + const controller = new AbortController(); + options.onController?.(controller); + + try { + const chatPath = this.path(DeepSeek.ChatPath); + const chatPayload = { + method: "POST", + body: JSON.stringify(requestPayload), + signal: controller.signal, + headers: getHeaders(), + }; + + // make a fetch request + const requestTimeoutId = setTimeout( + () => controller.abort(), + getTimeoutMSByModel(options.config.model), + ); + + if (shouldStream) { + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return streamWithThink( + chatPath, + requestPayload, + getHeaders(), + tools as any, + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + // console.log("parseSSE", text, runTools); + const json = JSON.parse(text); + const choices = json.choices as Array<{ + delta: { + content: string | null; + tool_calls: ChatMessageTool[]; + reasoning_content: string | null; + }; + }>; + const tool_calls = choices[0]?.delta?.tool_calls; + if (tool_calls?.length > 0) { + const index = tool_calls[0]?.index; + const id = tool_calls[0]?.id; + const args = tool_calls[0]?.function?.arguments; + if (id) { + runTools.push({ + id, + type: tool_calls[0]?.type, + function: { + name: tool_calls[0]?.function?.name as string, + arguments: args, + }, + }); + } else { + // @ts-ignore + runTools[index]["function"]["arguments"] += args; + } + } + const reasoning = choices[0]?.delta?.reasoning_content; + const content = choices[0]?.delta?.content; + + // Skip if both content and reasoning_content are empty or null + if ( + (!reasoning || reasoning.length === 0) && + (!content || content.length === 0) + ) { + return { + isThinking: false, + content: "", + }; + } + + if (reasoning && reasoning.length > 0) { + return { + isThinking: true, + content: reasoning, + }; + } else if (content && content.length > 0) { + return { + isThinking: false, + content: content, + }; + } + + return { + isThinking: false, + content: "", + }; + }, + // processToolMessage, include tool_calls message and tool call results + ( + requestPayload: RequestPayload, + toolCallMessage: any, + toolCallResult: any[], + ) => { + // @ts-ignore + requestPayload?.messages?.splice( + // @ts-ignore + requestPayload?.messages?.length, + 0, + toolCallMessage, + ...toolCallResult, + ); + }, + options, + ); + } else { + const res = await fetch(chatPath, chatPayload); + clearTimeout(requestTimeoutId); + + const resJson = await res.json(); + const message = this.extractMessage(resJson); + options.onFinish(message, res); + } + } catch (e) { + console.log("[Request] failed to make a chat request", e); + options.onError?.(e as Error); + } + } + async usage() { + return { + used: 0, + total: 0, + }; + } + + async models(): Promise { + return []; + } +} diff --git a/app/client/platforms/glm.ts b/app/client/platforms/glm.ts new file mode 100644 index 00000000000..98b10277de9 --- /dev/null +++ b/app/client/platforms/glm.ts @@ -0,0 +1,292 @@ +"use client"; +import { ApiPath, CHATGLM_BASE_URL, ChatGLM } from "@/app/constant"; +import { + useAccessStore, + useAppConfig, + useChatStore, + ChatMessageTool, + usePluginStore, +} from "@/app/store"; +import { stream } from "@/app/utils/chat"; +import { + ChatOptions, + getHeaders, + LLMApi, + LLMModel, + SpeechOptions, +} from "../api"; +import { getClientConfig } from "@/app/config/client"; +import { + getMessageTextContent, + isVisionModel, + getTimeoutMSByModel, +} from "@/app/utils"; +import { RequestPayload } from "./openai"; +import { fetch } from "@/app/utils/stream"; +import { preProcessImageContent } from "@/app/utils/chat"; + +interface BasePayload { + model: string; +} + +interface ChatPayload extends BasePayload { + messages: ChatOptions["messages"]; + stream?: boolean; + temperature?: number; + presence_penalty?: number; + frequency_penalty?: number; + top_p?: number; +} + +interface ImageGenerationPayload extends BasePayload { + prompt: string; + size?: string; + user_id?: string; +} + +interface VideoGenerationPayload extends BasePayload { + prompt: string; + duration?: number; + resolution?: string; + user_id?: string; +} + +type ModelType = "chat" | "image" | "video"; + +export class ChatGLMApi implements LLMApi { + private disableListModels = true; + + private getModelType(model: string): ModelType { + if (model.startsWith("cogview-")) return "image"; + if (model.startsWith("cogvideo-")) return "video"; + return "chat"; + } + + private getModelPath(type: ModelType): string { + switch (type) { + case "image": + return ChatGLM.ImagePath; + case "video": + return ChatGLM.VideoPath; + default: + return ChatGLM.ChatPath; + } + } + + private createPayload( + messages: ChatOptions["messages"], + modelConfig: any, + options: ChatOptions, + ): BasePayload { + const modelType = this.getModelType(modelConfig.model); + const lastMessage = messages[messages.length - 1]; + const prompt = + typeof lastMessage.content === "string" + ? lastMessage.content + : lastMessage.content.map((c) => c.text).join("\n"); + + switch (modelType) { + case "image": + return { + model: modelConfig.model, + prompt, + size: options.config.size, + } as ImageGenerationPayload; + default: + return { + messages, + stream: options.config.stream, + model: modelConfig.model, + temperature: modelConfig.temperature, + presence_penalty: modelConfig.presence_penalty, + frequency_penalty: modelConfig.frequency_penalty, + top_p: modelConfig.top_p, + } as ChatPayload; + } + } + + private parseResponse(modelType: ModelType, json: any): string { + switch (modelType) { + case "image": { + const imageUrl = json.data?.[0]?.url; + return imageUrl ? `![Generated Image](${imageUrl})` : ""; + } + case "video": { + const videoUrl = json.data?.[0]?.url; + return videoUrl ? `` : ""; + } + default: + return this.extractMessage(json); + } + } + + path(path: string): string { + const accessStore = useAccessStore.getState(); + let baseUrl = ""; + + if (accessStore.useCustomConfig) { + baseUrl = accessStore.chatglmUrl; + } + + if (baseUrl.length === 0) { + const isApp = !!getClientConfig()?.isApp; + const apiPath = ApiPath.ChatGLM; + baseUrl = isApp ? CHATGLM_BASE_URL : apiPath; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, baseUrl.length - 1); + } + if (!baseUrl.startsWith("http") && !baseUrl.startsWith(ApiPath.ChatGLM)) { + baseUrl = "https://" + baseUrl; + } + + console.log("[Proxy Endpoint] ", baseUrl, path); + return [baseUrl, path].join("/"); + } + + extractMessage(res: any) { + return res.choices?.at(0)?.message?.content ?? ""; + } + + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + + async chat(options: ChatOptions) { + const visionModel = isVisionModel(options.config.model); + const messages: ChatOptions["messages"] = []; + for (const v of options.messages) { + const content = visionModel + ? await preProcessImageContent(v.content) + : getMessageTextContent(v); + messages.push({ role: v.role, content }); + } + + const modelConfig = { + ...useAppConfig.getState().modelConfig, + ...useChatStore.getState().currentSession().mask.modelConfig, + ...{ + model: options.config.model, + providerName: options.config.providerName, + }, + }; + const modelType = this.getModelType(modelConfig.model); + const requestPayload = this.createPayload(messages, modelConfig, options); + const path = this.path(this.getModelPath(modelType)); + + console.log(`[Request] glm ${modelType} payload: `, requestPayload); + + const controller = new AbortController(); + options.onController?.(controller); + + try { + const chatPayload = { + method: "POST", + body: JSON.stringify(requestPayload), + signal: controller.signal, + headers: getHeaders(), + }; + + const requestTimeoutId = setTimeout( + () => controller.abort(), + getTimeoutMSByModel(options.config.model), + ); + + if (modelType === "image" || modelType === "video") { + const res = await fetch(path, chatPayload); + clearTimeout(requestTimeoutId); + + const resJson = await res.json(); + console.log(`[Response] glm ${modelType}:`, resJson); + const message = this.parseResponse(modelType, resJson); + options.onFinish(message, res); + return; + } + + const shouldStream = !!options.config.stream; + if (shouldStream) { + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return stream( + path, + requestPayload, + getHeaders(), + tools as any, + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + const json = JSON.parse(text); + const choices = json.choices as Array<{ + delta: { + content: string; + tool_calls: ChatMessageTool[]; + }; + }>; + const tool_calls = choices[0]?.delta?.tool_calls; + if (tool_calls?.length > 0) { + const index = tool_calls[0]?.index; + const id = tool_calls[0]?.id; + const args = tool_calls[0]?.function?.arguments; + if (id) { + runTools.push({ + id, + type: tool_calls[0]?.type, + function: { + name: tool_calls[0]?.function?.name as string, + arguments: args, + }, + }); + } else { + // @ts-ignore + runTools[index]["function"]["arguments"] += args; + } + } + return choices[0]?.delta?.content; + }, + // processToolMessage + ( + requestPayload: RequestPayload, + toolCallMessage: any, + toolCallResult: any[], + ) => { + // @ts-ignore + requestPayload?.messages?.splice( + // @ts-ignore + requestPayload?.messages?.length, + 0, + toolCallMessage, + ...toolCallResult, + ); + }, + options, + ); + } else { + const res = await fetch(path, chatPayload); + clearTimeout(requestTimeoutId); + + const resJson = await res.json(); + const message = this.extractMessage(resJson); + options.onFinish(message, res); + } + } catch (e) { + console.log("[Request] failed to make a chat request", e); + options.onError?.(e as Error); + } + } + + async usage() { + return { + used: 0, + total: 0, + }; + } + + async models(): Promise { + return []; + } +} diff --git a/app/client/platforms/google.ts b/app/client/platforms/google.ts index 12d8846357a..654f0e3e4c7 100644 --- a/app/client/platforms/google.ts +++ b/app/client/platforms/google.ts @@ -1,23 +1,36 @@ -import { ApiPath, Google, REQUEST_TIMEOUT_MS } from "@/app/constant"; -import { ChatOptions, getHeaders, LLMApi, LLMModel, LLMUsage } from "../api"; -import { useAccessStore, useAppConfig, useChatStore } from "@/app/store"; -import { getClientConfig } from "@/app/config/client"; -import { DEFAULT_API_HOST } from "@/app/constant"; -import Locale from "../../locales"; +import { ApiPath, Google } from "@/app/constant"; import { - EventStreamContentType, - fetchEventSource, -} from "@fortaine/fetch-event-source"; -import { prettyObject } from "@/app/utils/format"; + ChatOptions, + getHeaders, + LLMApi, + LLMModel, + LLMUsage, + SpeechOptions, +} from "../api"; +import { + useAccessStore, + useAppConfig, + useChatStore, + usePluginStore, + ChatMessageTool, +} from "@/app/store"; +import { stream } from "@/app/utils/chat"; +import { getClientConfig } from "@/app/config/client"; +import { GEMINI_BASE_URL } from "@/app/constant"; + import { getMessageTextContent, getMessageImages, isVisionModel, + getTimeoutMSByModel, } from "@/app/utils"; import { preProcessImageContent } from "@/app/utils/chat"; +import { nanoid } from "nanoid"; +import { RequestPayload } from "./openai"; +import { fetch } from "@/app/utils/stream"; export class GeminiProApi implements LLMApi { - path(path: string): string { + path(path: string, shouldStream = false): string { const accessStore = useAccessStore.getState(); let baseUrl = ""; @@ -27,7 +40,7 @@ export class GeminiProApi implements LLMApi { const isApp = !!getClientConfig()?.isApp; if (baseUrl.length === 0) { - baseUrl = isApp ? DEFAULT_API_HOST + `/api/proxy/google` : ApiPath.Google; + baseUrl = isApp ? GEMINI_BASE_URL : ApiPath.Google; } if (baseUrl.endsWith("/")) { baseUrl = baseUrl.slice(0, baseUrl.length - 1); @@ -39,23 +52,42 @@ export class GeminiProApi implements LLMApi { console.log("[Proxy Endpoint] ", baseUrl, path); let chatPath = [baseUrl, path].join("/"); - - chatPath += chatPath.includes("?") ? "&alt=sse" : "?alt=sse"; - // if chatPath.startsWith('http') then add key in query string - if (chatPath.startsWith("http") && accessStore.googleApiKey) { - chatPath += `&key=${accessStore.googleApiKey}`; + if (shouldStream) { + chatPath += chatPath.includes("?") ? "&alt=sse" : "?alt=sse"; } + return chatPath; } extractMessage(res: any) { console.log("[Response] gemini-pro response: ", res); + const getTextFromParts = (parts: any[]) => { + if (!Array.isArray(parts)) return ""; + + return parts + .map((part) => part?.text || "") + .filter((text) => text.trim() !== "") + .join("\n\n"); + }; + + let content = ""; + if (Array.isArray(res)) { + res.map((item) => { + content += getTextFromParts(item?.candidates?.at(0)?.content?.parts); + }); + } + return ( - res?.candidates?.at(0)?.content?.parts.at(0)?.text || + getTextFromParts(res?.candidates?.at(0)?.content?.parts) || + content || //getTextFromParts(res?.at(0)?.candidates?.at(0)?.content?.parts) || res?.error?.message || "" ); } + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + async chat(options: ChatOptions): Promise { const apiClient = this; let multimodal = false; @@ -154,7 +186,10 @@ export class GeminiProApi implements LLMApi { options.onController?.(controller); try { // https://github.com/google-gemini/cookbook/blob/main/quickstarts/rest/Streaming_REST.ipynb - const chatPath = this.path(Google.ChatPath(modelConfig.model)); + const chatPath = this.path( + Google.ChatPath(modelConfig.model), + shouldStream, + ); const chatPayload = { method: "POST", @@ -163,121 +198,95 @@ export class GeminiProApi implements LLMApi { headers: getHeaders(), }; + const isThinking = options.config.model.includes("-thinking"); // make a fetch request const requestTimeoutId = setTimeout( () => controller.abort(), - REQUEST_TIMEOUT_MS, + getTimeoutMSByModel(options.config.model), ); if (shouldStream) { - let responseText = ""; - let remainText = ""; - let finished = false; - - const finish = () => { - if (!finished) { - finished = true; - options.onFinish(responseText + remainText); - } - }; - - // animate response to make it looks smooth - function animateResponseText() { - if (finished || controller.signal.aborted) { - responseText += remainText; - finish(); - return; - } - - if (remainText.length > 0) { - const fetchCount = Math.max(1, Math.round(remainText.length / 60)); - const fetchText = remainText.slice(0, fetchCount); - responseText += fetchText; - remainText = remainText.slice(fetchCount); - options.onUpdate?.(responseText, fetchText); - } - - requestAnimationFrame(animateResponseText); - } - - // start animaion - animateResponseText(); - - controller.signal.onabort = finish; - - fetchEventSource(chatPath, { - ...chatPayload, - async onopen(res) { - clearTimeout(requestTimeoutId); - const contentType = res.headers.get("content-type"); - console.log( - "[Gemini] request response content type: ", - contentType, - ); - - if (contentType?.startsWith("text/plain")) { - responseText = await res.clone().text(); - return finish(); - } - - if ( - !res.ok || - !res.headers - .get("content-type") - ?.startsWith(EventStreamContentType) || - res.status !== 200 - ) { - const responseTexts = [responseText]; - let extraInfo = await res.clone().text(); - try { - const resJson = await res.clone().json(); - extraInfo = prettyObject(resJson); - } catch {} - - if (res.status === 401) { - responseTexts.push(Locale.Error.Unauthorized); - } - - if (extraInfo) { - responseTexts.push(extraInfo); - } - - responseText = responseTexts.join("\n\n"); - - return finish(); - } - }, - onmessage(msg) { - if (msg.data === "[DONE]" || finished) { - return finish(); - } - const text = msg.data; - try { - const json = JSON.parse(text); - const delta = apiClient.extractMessage(json); - - if (delta) { - remainText += delta; - } + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return stream( + chatPath, + requestPayload, + getHeaders(), + // @ts-ignore + tools.length > 0 + ? // @ts-ignore + [{ functionDeclarations: tools.map((tool) => tool.function) }] + : [], + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + // console.log("parseSSE", text, runTools); + const chunkJson = JSON.parse(text); - const blockReason = json?.promptFeedback?.blockReason; - if (blockReason) { - // being blocked - console.log(`[Google] [Safety Ratings] result:`, blockReason); - } - } catch (e) { - console.error("[Request] parse error", text, msg); + const functionCall = chunkJson?.candidates + ?.at(0) + ?.content.parts.at(0)?.functionCall; + if (functionCall) { + const { name, args } = functionCall; + runTools.push({ + id: nanoid(), + type: "function", + function: { + name, + arguments: JSON.stringify(args), // utils.chat call function, using JSON.parse + }, + }); } + return chunkJson?.candidates + ?.at(0) + ?.content.parts?.map((part: { text: string }) => part.text) + .join("\n\n"); }, - onclose() { - finish(); - }, - onerror(e) { - options.onError?.(e); - throw e; + // processToolMessage, include tool_calls message and tool call results + ( + requestPayload: RequestPayload, + toolCallMessage: any, + toolCallResult: any[], + ) => { + // @ts-ignore + requestPayload?.contents?.splice( + // @ts-ignore + requestPayload?.contents?.length, + 0, + { + role: "model", + parts: toolCallMessage.tool_calls.map( + (tool: ChatMessageTool) => ({ + functionCall: { + name: tool?.function?.name, + args: JSON.parse(tool?.function?.arguments as string), + }, + }), + ), + }, + // @ts-ignore + ...toolCallResult.map((result) => ({ + role: "function", + parts: [ + { + functionResponse: { + name: result.name, + response: { + name: result.name, + content: result.content, // TODO just text content... + }, + }, + }, + ], + })), + ); }, - openWhenHidden: true, - }); + options, + ); } else { const res = await fetch(chatPath, chatPayload); clearTimeout(requestTimeoutId); @@ -292,7 +301,7 @@ export class GeminiProApi implements LLMApi { ); } const message = apiClient.extractMessage(resJson); - options.onFinish(message); + options.onFinish(message, res); } } catch (e) { console.log("[Request] failed to make a chat request", e); diff --git a/app/client/platforms/iflytek.ts b/app/client/platforms/iflytek.ts index 73cea5ba0e7..cfc37b3b256 100644 --- a/app/client/platforms/iflytek.ts +++ b/app/client/platforms/iflytek.ts @@ -1,13 +1,19 @@ "use client"; import { ApiPath, - DEFAULT_API_HOST, + IFLYTEK_BASE_URL, Iflytek, REQUEST_TIMEOUT_MS, } from "@/app/constant"; import { useAccessStore, useAppConfig, useChatStore } from "@/app/store"; -import { ChatOptions, getHeaders, LLMApi, LLMModel } from "../api"; +import { + ChatOptions, + getHeaders, + LLMApi, + LLMModel, + SpeechOptions, +} from "../api"; import Locale from "../../locales"; import { EventStreamContentType, @@ -16,8 +22,9 @@ import { import { prettyObject } from "@/app/utils/format"; import { getClientConfig } from "@/app/config/client"; import { getMessageTextContent } from "@/app/utils"; +import { fetch } from "@/app/utils/stream"; -import { OpenAIListModelResponse, RequestPayload } from "./openai"; +import { RequestPayload } from "./openai"; export class SparkApi implements LLMApi { private disableListModels = true; @@ -34,7 +41,7 @@ export class SparkApi implements LLMApi { if (baseUrl.length === 0) { const isApp = !!getClientConfig()?.isApp; const apiPath = ApiPath.Iflytek; - baseUrl = isApp ? DEFAULT_API_HOST + "/proxy" + apiPath : apiPath; + baseUrl = isApp ? IFLYTEK_BASE_URL : apiPath; } if (baseUrl.endsWith("/")) { @@ -53,6 +60,10 @@ export class SparkApi implements LLMApi { return res.choices?.at(0)?.message?.content ?? ""; } + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + async chat(options: ChatOptions) { const messages: ChatOptions["messages"] = []; for (const v of options.messages) { @@ -106,6 +117,7 @@ export class SparkApi implements LLMApi { let responseText = ""; let remainText = ""; let finished = false; + let responseRes: Response; // Animate response text to make it look smooth function animateResponseText() { @@ -132,19 +144,20 @@ export class SparkApi implements LLMApi { const finish = () => { if (!finished) { finished = true; - options.onFinish(responseText + remainText); + options.onFinish(responseText + remainText, responseRes); } }; controller.signal.onabort = finish; fetchEventSource(chatPath, { + fetch: fetch as any, ...chatPayload, async onopen(res) { clearTimeout(requestTimeoutId); const contentType = res.headers.get("content-type"); console.log("[Spark] request response content type: ", contentType); - + responseRes = res; if (contentType?.startsWith("text/plain")) { responseText = await res.clone().text(); return finish(); @@ -219,7 +232,7 @@ export class SparkApi implements LLMApi { const resJson = await res.json(); const message = this.extractMessage(resJson); - options.onFinish(message); + options.onFinish(message, res); } } catch (e) { console.log("[Request] failed to make a chat request", e); diff --git a/app/client/platforms/moonshot.ts b/app/client/platforms/moonshot.ts index cd10d2f6c15..b6812c0d766 100644 --- a/app/client/platforms/moonshot.ts +++ b/app/client/platforms/moonshot.ts @@ -2,11 +2,9 @@ // azure and openai, using same models. so using same LLMApi. import { ApiPath, - DEFAULT_API_HOST, - DEFAULT_MODELS, + MOONSHOT_BASE_URL, Moonshot, REQUEST_TIMEOUT_MS, - ServiceProvider, } from "@/app/constant"; import { useAccessStore, @@ -15,28 +13,18 @@ import { ChatMessageTool, usePluginStore, } from "@/app/store"; -import { collectModelsWithDefaultModel } from "@/app/utils/model"; -import { preProcessImageContent, stream } from "@/app/utils/chat"; -import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare"; - +import { stream } from "@/app/utils/chat"; import { ChatOptions, getHeaders, LLMApi, LLMModel, - LLMUsage, - MultimodalContent, + SpeechOptions, } from "../api"; -import Locale from "../../locales"; -import { - EventStreamContentType, - fetchEventSource, -} from "@fortaine/fetch-event-source"; -import { prettyObject } from "@/app/utils/format"; import { getClientConfig } from "@/app/config/client"; import { getMessageTextContent } from "@/app/utils"; - -import { OpenAIListModelResponse, RequestPayload } from "./openai"; +import { RequestPayload } from "./openai"; +import { fetch } from "@/app/utils/stream"; export class MoonshotApi implements LLMApi { private disableListModels = true; @@ -53,7 +41,7 @@ export class MoonshotApi implements LLMApi { if (baseUrl.length === 0) { const isApp = !!getClientConfig()?.isApp; const apiPath = ApiPath.Moonshot; - baseUrl = isApp ? DEFAULT_API_HOST + "/proxy" + apiPath : apiPath; + baseUrl = isApp ? MOONSHOT_BASE_URL : apiPath; } if (baseUrl.endsWith("/")) { @@ -72,6 +60,10 @@ export class MoonshotApi implements LLMApi { return res.choices?.at(0)?.message?.content ?? ""; } + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + async chat(options: ChatOptions) { const messages: ChatOptions["messages"] = []; for (const v of options.messages) { @@ -188,7 +180,7 @@ export class MoonshotApi implements LLMApi { const resJson = await res.json(); const message = this.extractMessage(resJson); - options.onFinish(message); + options.onFinish(message, res); } } catch (e) { console.log("[Request] failed to make a chat request", e); diff --git a/app/client/platforms/openai.ts b/app/client/platforms/openai.ts index 664ff872ba3..cfbff99e978 100644 --- a/app/client/platforms/openai.ts +++ b/app/client/platforms/openai.ts @@ -2,7 +2,7 @@ // azure and openai, using same models. so using same LLMApi. import { ApiPath, - DEFAULT_API_HOST, + OPENAI_BASE_URL, DEFAULT_MODELS, OpenaiPath, Azure, @@ -21,10 +21,10 @@ import { preProcessImageContent, uploadImage, base64Image2Blob, - stream, + streamWithThink, } from "@/app/utils/chat"; import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare"; -import { DalleSize, DalleQuality, DalleStyle } from "@/app/typing"; +import { ModelSize, DalleQuality, DalleStyle } from "@/app/typing"; import { ChatOptions, @@ -33,20 +33,17 @@ import { LLMModel, LLMUsage, MultimodalContent, + SpeechOptions, } from "../api"; import Locale from "../../locales"; -import { - EventStreamContentType, - fetchEventSource, -} from "@fortaine/fetch-event-source"; -import { prettyObject } from "@/app/utils/format"; import { getClientConfig } from "@/app/config/client"; import { getMessageTextContent, - getMessageImages, isVisionModel, isDalle3 as _isDalle3, + getTimeoutMSByModel, } from "@/app/utils"; +import { fetch } from "@/app/utils/stream"; export interface OpenAIListModelResponse { object: string; @@ -59,7 +56,7 @@ export interface OpenAIListModelResponse { export interface RequestPayload { messages: { - role: "system" | "user" | "assistant"; + role: "developer" | "system" | "user" | "assistant"; content: string | MultimodalContent[]; }[]; stream?: boolean; @@ -69,6 +66,7 @@ export interface RequestPayload { frequency_penalty: number; top_p: number; max_tokens?: number; + max_completion_tokens?: number; } export interface DalleRequestPayload { @@ -76,7 +74,7 @@ export interface DalleRequestPayload { prompt: string; response_format: "url" | "b64_json"; n: number; - size: DalleSize; + size: ModelSize; quality: DalleQuality; style: DalleStyle; } @@ -103,7 +101,7 @@ export class ChatGPTApi implements LLMApi { if (baseUrl.length === 0) { const isApp = !!getClientConfig()?.isApp; const apiPath = isAzure ? ApiPath.Azure : ApiPath.OpenAI; - baseUrl = isApp ? DEFAULT_API_HOST + "/proxy" + apiPath : apiPath; + baseUrl = isApp ? OPENAI_BASE_URL : apiPath; } if (baseUrl.endsWith("/")) { @@ -147,6 +145,44 @@ export class ChatGPTApi implements LLMApi { return res.choices?.at(0)?.message?.content ?? res; } + async speech(options: SpeechOptions): Promise { + const requestPayload = { + model: options.model, + input: options.input, + voice: options.voice, + response_format: options.response_format, + speed: options.speed, + }; + + console.log("[Request] openai speech payload: ", requestPayload); + + const controller = new AbortController(); + options.onController?.(controller); + + try { + const speechPath = this.path(OpenaiPath.SpeechPath); + const speechPayload = { + method: "POST", + body: JSON.stringify(requestPayload), + signal: controller.signal, + headers: getHeaders(), + }; + + // make a fetch request + const requestTimeoutId = setTimeout( + () => controller.abort(), + REQUEST_TIMEOUT_MS, + ); + + const res = await fetch(speechPath, speechPayload); + clearTimeout(requestTimeoutId); + return await res.arrayBuffer(); + } catch (e) { + console.log("[Request] failed to make a speech request", e); + throw e; + } + } + async chat(options: ChatOptions) { const modelConfig = { ...useAppConfig.getState().modelConfig, @@ -160,7 +196,11 @@ export class ChatGPTApi implements LLMApi { let requestPayload: RequestPayload | DalleRequestPayload; const isDalle3 = _isDalle3(options.config.model); - const isO1 = options.config.model.startsWith("o1"); + const isO1OrO3 = + options.config.model.startsWith("o1") || + options.config.model.startsWith("o3") || + options.config.model.startsWith("o4-mini"); + const isGpt5 = options.config.model.startsWith("gpt-5"); if (isDalle3) { const prompt = getMessageTextContent( options.messages.slice(-1)?.pop() as any, @@ -182,32 +222,52 @@ export class ChatGPTApi implements LLMApi { const content = visionModel ? await preProcessImageContent(v.content) : getMessageTextContent(v); - if (!(isO1 && v.role === "system")) + if (!(isO1OrO3 && v.role === "system")) messages.push({ role: v.role, content }); } // O1 not support image, tools (plugin in ChatGPTNextWeb) and system, stream, logprobs, temperature, top_p, n, presence_penalty, frequency_penalty yet. requestPayload = { messages, - stream: !isO1 ? options.config.stream : false, + stream: options.config.stream, model: modelConfig.model, - temperature: !isO1 ? modelConfig.temperature : 1, - presence_penalty: !isO1 ? modelConfig.presence_penalty : 0, - frequency_penalty: !isO1 ? modelConfig.frequency_penalty : 0, - top_p: !isO1 ? modelConfig.top_p : 1, + temperature: (!isO1OrO3 && !isGpt5) ? modelConfig.temperature : 1, + presence_penalty: !isO1OrO3 ? modelConfig.presence_penalty : 0, + frequency_penalty: !isO1OrO3 ? modelConfig.frequency_penalty : 0, + top_p: !isO1OrO3 ? modelConfig.top_p : 1, // max_tokens: Math.max(modelConfig.max_tokens, 1024), // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore. }; + if (isGpt5) { + // Remove max_tokens if present + delete requestPayload.max_tokens; + // Add max_completion_tokens (or max_completion_tokens if that's what you meant) + requestPayload["max_completion_tokens"] = modelConfig.max_tokens; + + } else if (isO1OrO3) { + // by default the o1/o3 models will not attempt to produce output that includes markdown formatting + // manually add "Formatting re-enabled" developer message to encourage markdown inclusion in model responses + // (https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/reasoning?tabs=python-secure#markdown-output) + requestPayload["messages"].unshift({ + role: "developer", + content: "Formatting re-enabled", + }); + + // o1/o3 uses max_completion_tokens to control the number of tokens (https://platform.openai.com/docs/guides/reasoning#controlling-costs) + requestPayload["max_completion_tokens"] = modelConfig.max_tokens; + } + + // add max_tokens to vision model - if (visionModel) { + if (visionModel && !isO1OrO3 && ! isGpt5) { requestPayload["max_tokens"] = Math.max(modelConfig.max_tokens, 4000); } } console.log("[Request] openai payload: ", requestPayload); - const shouldStream = !isDalle3 && !!options.config.stream && !isO1; + const shouldStream = !isDalle3 && !!options.config.stream; const controller = new AbortController(); options.onController?.(controller); @@ -244,13 +304,14 @@ export class ChatGPTApi implements LLMApi { ); } if (shouldStream) { + let index = -1; const [tools, funcs] = usePluginStore .getState() .getAsTools( useChatStore.getState().currentSession().mask?.plugin || [], ); // console.log("getAsTools", tools, funcs); - stream( + streamWithThink( chatPath, requestPayload, getHeaders(), @@ -265,14 +326,18 @@ export class ChatGPTApi implements LLMApi { delta: { content: string; tool_calls: ChatMessageTool[]; + reasoning_content: string | null; }; }>; + + if (!choices?.length) return { isThinking: false, content: "" }; + const tool_calls = choices[0]?.delta?.tool_calls; if (tool_calls?.length > 0) { - const index = tool_calls[0]?.index; const id = tool_calls[0]?.id; const args = tool_calls[0]?.function?.arguments; if (id) { + index += 1; runTools.push({ id, type: tool_calls[0]?.type, @@ -286,7 +351,37 @@ export class ChatGPTApi implements LLMApi { runTools[index]["function"]["arguments"] += args; } } - return choices[0]?.delta?.content; + + const reasoning = choices[0]?.delta?.reasoning_content; + const content = choices[0]?.delta?.content; + + // Skip if both content and reasoning_content are empty or null + if ( + (!reasoning || reasoning.length === 0) && + (!content || content.length === 0) + ) { + return { + isThinking: false, + content: "", + }; + } + + if (reasoning && reasoning.length > 0) { + return { + isThinking: true, + content: reasoning, + }; + } else if (content && content.length > 0) { + return { + isThinking: false, + content: content, + }; + } + + return { + isThinking: false, + content: "", + }; }, // processToolMessage, include tool_calls message and tool call results ( @@ -294,6 +389,8 @@ export class ChatGPTApi implements LLMApi { toolCallMessage: any, toolCallResult: any[], ) => { + // reset index value + index = -1; // @ts-ignore requestPayload?.messages?.splice( // @ts-ignore @@ -316,7 +413,7 @@ export class ChatGPTApi implements LLMApi { // make a fetch request const requestTimeoutId = setTimeout( () => controller.abort(), - isDalle3 || isO1 ? REQUEST_TIMEOUT_MS * 2 : REQUEST_TIMEOUT_MS, // dalle3 using b64_json is slow. + getTimeoutMSByModel(options.config.model), ); const res = await fetch(chatPath, chatPayload); @@ -324,7 +421,7 @@ export class ChatGPTApi implements LLMApi { const resJson = await res.json(); const message = await this.extractMessage(resJson); - options.onFinish(message); + options.onFinish(message, res); } } catch (e) { console.log("[Request] failed to make a chat request", e); diff --git a/app/client/platforms/siliconflow.ts b/app/client/platforms/siliconflow.ts new file mode 100644 index 00000000000..34f0844c328 --- /dev/null +++ b/app/client/platforms/siliconflow.ts @@ -0,0 +1,287 @@ +"use client"; +// azure and openai, using same models. so using same LLMApi. +import { + ApiPath, + SILICONFLOW_BASE_URL, + SiliconFlow, + DEFAULT_MODELS, +} from "@/app/constant"; +import { + useAccessStore, + useAppConfig, + useChatStore, + ChatMessageTool, + usePluginStore, +} from "@/app/store"; +import { preProcessImageContent, streamWithThink } from "@/app/utils/chat"; +import { + ChatOptions, + getHeaders, + LLMApi, + LLMModel, + SpeechOptions, +} from "../api"; +import { getClientConfig } from "@/app/config/client"; +import { + getMessageTextContent, + getMessageTextContentWithoutThinking, + isVisionModel, + getTimeoutMSByModel, +} from "@/app/utils"; +import { RequestPayload } from "./openai"; + +import { fetch } from "@/app/utils/stream"; +export interface SiliconFlowListModelResponse { + object: string; + data: Array<{ + id: string; + object: string; + root: string; + }>; +} + +export class SiliconflowApi implements LLMApi { + private disableListModels = false; + + path(path: string): string { + const accessStore = useAccessStore.getState(); + + let baseUrl = ""; + + if (accessStore.useCustomConfig) { + baseUrl = accessStore.siliconflowUrl; + } + + if (baseUrl.length === 0) { + const isApp = !!getClientConfig()?.isApp; + const apiPath = ApiPath.SiliconFlow; + baseUrl = isApp ? SILICONFLOW_BASE_URL : apiPath; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, baseUrl.length - 1); + } + if ( + !baseUrl.startsWith("http") && + !baseUrl.startsWith(ApiPath.SiliconFlow) + ) { + baseUrl = "https://" + baseUrl; + } + + console.log("[Proxy Endpoint] ", baseUrl, path); + + return [baseUrl, path].join("/"); + } + + extractMessage(res: any) { + return res.choices?.at(0)?.message?.content ?? ""; + } + + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + + async chat(options: ChatOptions) { + const visionModel = isVisionModel(options.config.model); + const messages: ChatOptions["messages"] = []; + for (const v of options.messages) { + if (v.role === "assistant") { + const content = getMessageTextContentWithoutThinking(v); + messages.push({ role: v.role, content }); + } else { + const content = visionModel + ? await preProcessImageContent(v.content) + : getMessageTextContent(v); + messages.push({ role: v.role, content }); + } + } + + const modelConfig = { + ...useAppConfig.getState().modelConfig, + ...useChatStore.getState().currentSession().mask.modelConfig, + ...{ + model: options.config.model, + providerName: options.config.providerName, + }, + }; + + const requestPayload: RequestPayload = { + messages, + stream: options.config.stream, + model: modelConfig.model, + temperature: modelConfig.temperature, + presence_penalty: modelConfig.presence_penalty, + frequency_penalty: modelConfig.frequency_penalty, + top_p: modelConfig.top_p, + // max_tokens: Math.max(modelConfig.max_tokens, 1024), + // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore. + }; + + console.log("[Request] openai payload: ", requestPayload); + + const shouldStream = !!options.config.stream; + const controller = new AbortController(); + options.onController?.(controller); + + try { + const chatPath = this.path(SiliconFlow.ChatPath); + const chatPayload = { + method: "POST", + body: JSON.stringify(requestPayload), + signal: controller.signal, + headers: getHeaders(), + }; + + // console.log(chatPayload); + + // Use extended timeout for thinking models as they typically require more processing time + const requestTimeoutId = setTimeout( + () => controller.abort(), + getTimeoutMSByModel(options.config.model), + ); + + if (shouldStream) { + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return streamWithThink( + chatPath, + requestPayload, + getHeaders(), + tools as any, + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + // console.log("parseSSE", text, runTools); + const json = JSON.parse(text); + const choices = json.choices as Array<{ + delta: { + content: string | null; + tool_calls: ChatMessageTool[]; + reasoning_content: string | null; + }; + }>; + const tool_calls = choices[0]?.delta?.tool_calls; + if (tool_calls?.length > 0) { + const index = tool_calls[0]?.index; + const id = tool_calls[0]?.id; + const args = tool_calls[0]?.function?.arguments; + if (id) { + runTools.push({ + id, + type: tool_calls[0]?.type, + function: { + name: tool_calls[0]?.function?.name as string, + arguments: args, + }, + }); + } else { + // @ts-ignore + runTools[index]["function"]["arguments"] += args; + } + } + const reasoning = choices[0]?.delta?.reasoning_content; + const content = choices[0]?.delta?.content; + + // Skip if both content and reasoning_content are empty or null + if ( + (!reasoning || reasoning.length === 0) && + (!content || content.length === 0) + ) { + return { + isThinking: false, + content: "", + }; + } + + if (reasoning && reasoning.length > 0) { + return { + isThinking: true, + content: reasoning, + }; + } else if (content && content.length > 0) { + return { + isThinking: false, + content: content, + }; + } + + return { + isThinking: false, + content: "", + }; + }, + // processToolMessage, include tool_calls message and tool call results + ( + requestPayload: RequestPayload, + toolCallMessage: any, + toolCallResult: any[], + ) => { + // @ts-ignore + requestPayload?.messages?.splice( + // @ts-ignore + requestPayload?.messages?.length, + 0, + toolCallMessage, + ...toolCallResult, + ); + }, + options, + ); + } else { + const res = await fetch(chatPath, chatPayload); + clearTimeout(requestTimeoutId); + + const resJson = await res.json(); + const message = this.extractMessage(resJson); + options.onFinish(message, res); + } + } catch (e) { + console.log("[Request] failed to make a chat request", e); + options.onError?.(e as Error); + } + } + async usage() { + return { + used: 0, + total: 0, + }; + } + + async models(): Promise { + if (this.disableListModels) { + return DEFAULT_MODELS.slice(); + } + + const res = await fetch(this.path(SiliconFlow.ListModelPath), { + method: "GET", + headers: { + ...getHeaders(), + }, + }); + + const resJson = (await res.json()) as SiliconFlowListModelResponse; + const chatModels = resJson.data; + console.log("[Models]", chatModels); + + if (!chatModels) { + return []; + } + + let seq = 1000; //同 Constant.ts 中的排序保持一致 + return chatModels.map((m) => ({ + name: m.id, + available: true, + sorted: seq++, + provider: { + id: "siliconflow", + providerName: "SiliconFlow", + providerType: "siliconflow", + sorted: 14, + }, + })); + } +} diff --git a/app/client/platforms/tencent.ts b/app/client/platforms/tencent.ts index 579008a9b9d..8adeb1b3ea7 100644 --- a/app/client/platforms/tencent.ts +++ b/app/client/platforms/tencent.ts @@ -1,5 +1,5 @@ "use client"; -import { ApiPath, DEFAULT_API_HOST, REQUEST_TIMEOUT_MS } from "@/app/constant"; +import { ApiPath, TENCENT_BASE_URL } from "@/app/constant"; import { useAccessStore, useAppConfig, useChatStore } from "@/app/store"; import { @@ -8,6 +8,7 @@ import { LLMApi, LLMModel, MultimodalContent, + SpeechOptions, } from "../api"; import Locale from "../../locales"; import { @@ -16,11 +17,16 @@ import { } from "@fortaine/fetch-event-source"; import { prettyObject } from "@/app/utils/format"; import { getClientConfig } from "@/app/config/client"; -import { getMessageTextContent, isVisionModel } from "@/app/utils"; +import { + getMessageTextContent, + isVisionModel, + getTimeoutMSByModel, +} from "@/app/utils"; import mapKeys from "lodash-es/mapKeys"; import mapValues from "lodash-es/mapValues"; import isArray from "lodash-es/isArray"; import isObject from "lodash-es/isObject"; +import { fetch } from "@/app/utils/stream"; export interface OpenAIListModelResponse { object: string; @@ -69,9 +75,7 @@ export class HunyuanApi implements LLMApi { if (baseUrl.length === 0) { const isApp = !!getClientConfig()?.isApp; - baseUrl = isApp - ? DEFAULT_API_HOST + "/api/proxy/tencent" - : ApiPath.Tencent; + baseUrl = isApp ? TENCENT_BASE_URL : ApiPath.Tencent; } if (baseUrl.endsWith("/")) { @@ -89,6 +93,10 @@ export class HunyuanApi implements LLMApi { return res.Choices?.at(0)?.Message?.Content ?? ""; } + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + async chat(options: ChatOptions) { const visionModel = isVisionModel(options.config.model); const messages = options.messages.map((v, index) => ({ @@ -131,13 +139,14 @@ export class HunyuanApi implements LLMApi { // make a fetch request const requestTimeoutId = setTimeout( () => controller.abort(), - REQUEST_TIMEOUT_MS, + getTimeoutMSByModel(options.config.model), ); if (shouldStream) { let responseText = ""; let remainText = ""; let finished = false; + let responseRes: Response; // animate response to make it looks smooth function animateResponseText() { @@ -167,13 +176,14 @@ export class HunyuanApi implements LLMApi { const finish = () => { if (!finished) { finished = true; - options.onFinish(responseText + remainText); + options.onFinish(responseText + remainText, responseRes); } }; controller.signal.onabort = finish; fetchEventSource(chatPath, { + fetch: fetch as any, ...chatPayload, async onopen(res) { clearTimeout(requestTimeoutId); @@ -182,7 +192,7 @@ export class HunyuanApi implements LLMApi { "[Tencent] request response content type: ", contentType, ); - + responseRes = res; if (contentType?.startsWith("text/plain")) { responseText = await res.clone().text(); return finish(); @@ -248,7 +258,7 @@ export class HunyuanApi implements LLMApi { const resJson = await res.json(); const message = this.extractMessage(resJson); - options.onFinish(message); + options.onFinish(message, res); } } catch (e) { console.log("[Request] failed to make a chat request", e); diff --git a/app/client/platforms/xai.ts b/app/client/platforms/xai.ts new file mode 100644 index 00000000000..830ad4778ac --- /dev/null +++ b/app/client/platforms/xai.ts @@ -0,0 +1,194 @@ +"use client"; +// azure and openai, using same models. so using same LLMApi. +import { ApiPath, XAI_BASE_URL, XAI } from "@/app/constant"; +import { + useAccessStore, + useAppConfig, + useChatStore, + ChatMessageTool, + usePluginStore, +} from "@/app/store"; +import { stream } from "@/app/utils/chat"; +import { + ChatOptions, + getHeaders, + LLMApi, + LLMModel, + SpeechOptions, +} from "../api"; +import { getClientConfig } from "@/app/config/client"; +import { getTimeoutMSByModel } from "@/app/utils"; +import { preProcessImageContent } from "@/app/utils/chat"; +import { RequestPayload } from "./openai"; +import { fetch } from "@/app/utils/stream"; + +export class XAIApi implements LLMApi { + private disableListModels = true; + + path(path: string): string { + const accessStore = useAccessStore.getState(); + + let baseUrl = ""; + + if (accessStore.useCustomConfig) { + baseUrl = accessStore.xaiUrl; + } + + if (baseUrl.length === 0) { + const isApp = !!getClientConfig()?.isApp; + const apiPath = ApiPath.XAI; + baseUrl = isApp ? XAI_BASE_URL : apiPath; + } + + if (baseUrl.endsWith("/")) { + baseUrl = baseUrl.slice(0, baseUrl.length - 1); + } + if (!baseUrl.startsWith("http") && !baseUrl.startsWith(ApiPath.XAI)) { + baseUrl = "https://" + baseUrl; + } + + console.log("[Proxy Endpoint] ", baseUrl, path); + + return [baseUrl, path].join("/"); + } + + extractMessage(res: any) { + return res.choices?.at(0)?.message?.content ?? ""; + } + + speech(options: SpeechOptions): Promise { + throw new Error("Method not implemented."); + } + + async chat(options: ChatOptions) { + const messages: ChatOptions["messages"] = []; + for (const v of options.messages) { + const content = await preProcessImageContent(v.content); + messages.push({ role: v.role, content }); + } + + const modelConfig = { + ...useAppConfig.getState().modelConfig, + ...useChatStore.getState().currentSession().mask.modelConfig, + ...{ + model: options.config.model, + providerName: options.config.providerName, + }, + }; + + const requestPayload: RequestPayload = { + messages, + stream: options.config.stream, + model: modelConfig.model, + temperature: modelConfig.temperature, + presence_penalty: modelConfig.presence_penalty, + frequency_penalty: modelConfig.frequency_penalty, + top_p: modelConfig.top_p, + }; + + console.log("[Request] xai payload: ", requestPayload); + + const shouldStream = !!options.config.stream; + const controller = new AbortController(); + options.onController?.(controller); + + try { + const chatPath = this.path(XAI.ChatPath); + const chatPayload = { + method: "POST", + body: JSON.stringify(requestPayload), + signal: controller.signal, + headers: getHeaders(), + }; + + // make a fetch request + const requestTimeoutId = setTimeout( + () => controller.abort(), + getTimeoutMSByModel(options.config.model), + ); + + if (shouldStream) { + const [tools, funcs] = usePluginStore + .getState() + .getAsTools( + useChatStore.getState().currentSession().mask?.plugin || [], + ); + return stream( + chatPath, + requestPayload, + getHeaders(), + tools as any, + funcs, + controller, + // parseSSE + (text: string, runTools: ChatMessageTool[]) => { + // console.log("parseSSE", text, runTools); + const json = JSON.parse(text); + const choices = json.choices as Array<{ + delta: { + content: string; + tool_calls: ChatMessageTool[]; + }; + }>; + const tool_calls = choices[0]?.delta?.tool_calls; + if (tool_calls?.length > 0) { + const index = tool_calls[0]?.index; + const id = tool_calls[0]?.id; + const args = tool_calls[0]?.function?.arguments; + if (id) { + runTools.push({ + id, + type: tool_calls[0]?.type, + function: { + name: tool_calls[0]?.function?.name as string, + arguments: args, + }, + }); + } else { + // @ts-ignore + runTools[index]["function"]["arguments"] += args; + } + } + return choices[0]?.delta?.content; + }, + // processToolMessage, include tool_calls message and tool call results + ( + requestPayload: RequestPayload, + toolCallMessage: any, + toolCallResult: any[], + ) => { + // @ts-ignore + requestPayload?.messages?.splice( + // @ts-ignore + requestPayload?.messages?.length, + 0, + toolCallMessage, + ...toolCallResult, + ); + }, + options, + ); + } else { + const res = await fetch(chatPath, chatPayload); + clearTimeout(requestTimeoutId); + + const resJson = await res.json(); + const message = this.extractMessage(resJson); + options.onFinish(message, res); + } + } catch (e) { + console.log("[Request] failed to make a chat request", e); + options.onError?.(e as Error); + } + } + async usage() { + return { + used: 0, + total: 0, + }; + } + + async models(): Promise { + return []; + } +} diff --git a/app/command.ts b/app/command.ts index bea4e06f381..aec73ef53d6 100644 --- a/app/command.ts +++ b/app/command.ts @@ -38,6 +38,7 @@ interface ChatCommands { next?: Command; prev?: Command; clear?: Command; + fork?: Command; del?: Command; } diff --git a/app/components/artifacts.tsx b/app/components/artifacts.tsx index d725ee6596e..7546260d92b 100644 --- a/app/components/artifacts.tsx +++ b/app/components/artifacts.tsx @@ -7,7 +7,6 @@ import { useImperativeHandle, } from "react"; import { useParams } from "react-router"; -import { useWindowSize } from "@/app/utils"; import { IconButton } from "./button"; import { nanoid } from "nanoid"; import ExportIcon from "../icons/share.svg"; @@ -30,11 +29,11 @@ type HTMLPreviewProps = { onLoad?: (title?: string) => void; }; -export type HTMLPreviewHander = { +export type HTMLPreviewHandler = { reload: () => void; }; -export const HTMLPreview = forwardRef( +export const HTMLPreview = forwardRef( function HTMLPreview(props, ref) { const iframeRef = useRef(null); const [frameId, setFrameId] = useState(nanoid()); @@ -208,7 +207,7 @@ export function Artifacts() { const [code, setCode] = useState(""); const [loading, setLoading] = useState(true); const [fileName, setFileName] = useState(""); - const previewRef = useRef(null); + const previewRef = useRef(null); useEffect(() => { if (id) { diff --git a/app/components/auth.module.scss b/app/components/auth.module.scss index 6630c0613c7..fe143b4289b 100644 --- a/app/components/auth.module.scss +++ b/app/components/auth.module.scss @@ -1,12 +1,70 @@ .auth-page { display: flex; - justify-content: center; + justify-content: flex-start; align-items: center; height: 100%; width: 100%; flex-direction: column; + .top-banner { + position: relative; + width: 100%; + display: flex; + justify-content: center; + align-items: center; + padding: 12px 64px; + box-sizing: border-box; + background: var(--second); + .top-banner-inner { + display: flex; + justify-content: center; + align-items: center; + font-size: 14px; + line-height: 150%; + span { + gap: 8px; + a { + display: inline-flex; + align-items: center; + text-decoration: none; + margin-left: 8px; + color: var(--primary); + } + } + } + .top-banner-close { + cursor: pointer; + position: absolute; + top: 50%; + right: 48px; + transform: translateY(-50%); + } + } + + @media (max-width: 600px) { + .top-banner { + padding: 12px 24px 12px 12px; + .top-banner-close { + right: 10px; + } + .top-banner-inner { + .top-banner-logo { + margin-right: 8px; + } + } + } + } + + .auth-header { + display: flex; + justify-content: space-between; + width: 100%; + padding: 10px; + box-sizing: border-box; + animation: slide-in-from-top ease 0.3s; + } .auth-logo { + margin-top: 10vh; transform: scale(1.4); } @@ -14,6 +72,7 @@ font-size: 24px; font-weight: bold; line-height: 2; + margin-bottom: 1vh; } .auth-tips { @@ -24,6 +83,10 @@ margin: 3vh 0; } + .auth-input-second { + margin: 0 0 3vh 0; + } + .auth-actions { display: flex; justify-content: center; diff --git a/app/components/auth.tsx b/app/components/auth.tsx index 57118349bac..5375bda3f70 100644 --- a/app/components/auth.tsx +++ b/app/components/auth.tsx @@ -1,21 +1,37 @@ import styles from "./auth.module.scss"; import { IconButton } from "./button"; - +import { useState, useEffect } from "react"; import { useNavigate } from "react-router-dom"; -import { Path } from "../constant"; +import { Path, SAAS_CHAT_URL } from "../constant"; import { useAccessStore } from "../store"; import Locale from "../locales"; - +import Delete from "../icons/close.svg"; +import Arrow from "../icons/arrow.svg"; +import Logo from "../icons/logo.svg"; +import { useMobileScreen } from "@/app/utils"; import BotIcon from "../icons/bot.svg"; -import { useEffect } from "react"; import { getClientConfig } from "../config/client"; +import { PasswordInput } from "./ui-lib"; +import LeftIcon from "@/app/icons/left.svg"; +import { safeLocalStorage } from "@/app/utils"; +import { + trackSettingsPageGuideToCPaymentClick, + trackAuthorizationPageButtonToCPaymentClick, +} from "../utils/auth-settings-events"; +import clsx from "clsx"; + +const storage = safeLocalStorage(); export function AuthPage() { const navigate = useNavigate(); const accessStore = useAccessStore(); - const goHome = () => navigate(Path.Home); const goChat = () => navigate(Path.Chat); + const goSaas = () => { + trackAuthorizationPageButtonToCPaymentClick(); + window.location.href = SAAS_CHAT_URL; + }; + const resetAccessCode = () => { accessStore.update((access) => { access.openaiApiKey = ""; @@ -32,43 +48,58 @@ export function AuthPage() { return (
-
+ +
+ } + text={Locale.Auth.Return} + onClick={() => navigate(Path.Home)} + > +
+
{Locale.Auth.Title}
{Locale.Auth.Tips}
- { accessStore.update( (access) => (access.accessCode = e.currentTarget.value), ); }} /> + {!accessStore.hideUserApiKey ? ( <>
{Locale.Auth.SubTips}
- { accessStore.update( (access) => (access.openaiApiKey = e.currentTarget.value), ); }} /> - { accessStore.update( (access) => (access.googleApiKey = e.currentTarget.value), @@ -85,13 +116,74 @@ export function AuthPage() { onClick={goChat} /> { - resetAccessCode(); - goHome(); + goSaas(); }} />
); } + +function TopBanner() { + const [isHovered, setIsHovered] = useState(false); + const [isVisible, setIsVisible] = useState(true); + const isMobile = useMobileScreen(); + useEffect(() => { + // 检查 localStorage 中是否有标记 + const bannerDismissed = storage.getItem("bannerDismissed"); + // 如果标记不存在,存储默认值并显示横幅 + if (!bannerDismissed) { + storage.setItem("bannerDismissed", "false"); + setIsVisible(true); // 显示横幅 + } else if (bannerDismissed === "true") { + // 如果标记为 "true",则隐藏横幅 + setIsVisible(false); + } + }, []); + + const handleMouseEnter = () => { + setIsHovered(true); + }; + + const handleMouseLeave = () => { + setIsHovered(false); + }; + + const handleClose = () => { + setIsVisible(false); + storage.setItem("bannerDismissed", "true"); + }; + + if (!isVisible) { + return null; + } + return ( +
+ + {(isHovered || isMobile) && ( + + )} +
+ ); +} diff --git a/app/components/button.module.scss b/app/components/button.module.scss index e332df2d2c8..05248bee812 100644 --- a/app/components/button.module.scss +++ b/app/components/button.module.scss @@ -5,7 +5,6 @@ align-items: center; justify-content: center; padding: 10px; - cursor: pointer; transition: all 0.3s ease; overflow: hidden; diff --git a/app/components/button.tsx b/app/components/button.tsx index 87b4abd30f9..157d5d73da5 100644 --- a/app/components/button.tsx +++ b/app/components/button.tsx @@ -2,6 +2,7 @@ import * as React from "react"; import styles from "./button.module.scss"; import { CSSProperties } from "react"; +import clsx from "clsx"; export type ButtonType = "primary" | "danger" | null; @@ -22,12 +23,16 @@ export function IconButton(props: { }) { return (