Merge pull request #18 from Dogtiti/merge

Merge

README.md

@@ -1,16 +1,17 @@
 <div align="center">
 
-<a href='#企业版'>
+<a href='https://nextchat.dev/chat'>
-  <img src="./docs/images/ent.svg" alt="icon"/>
+  <img src="https://github.com/user-attachments/assets/287c510f-f508-478e-ade3-54d30453dc18" width="1000" alt="icon"/>
 </a>
 
+
 <h1 align="center">NextChat (ChatGPT Next Web)</h1>
 
 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.
+One-Click to get a well-designed cross-platform ChatGPT web UI, with Claude, GPT4 & Gemini Pro support.
 
-一键免费部署你的跨平台私人 ChatGPT 应用, 支持 GPT3, GPT4 & Gemini Pro 模型。
+一键免费部署你的跨平台私人 ChatGPT 应用, 支持 Claude, GPT4 & Gemini Pro 模型。
 
 [![Saas][Saas-image]][saas-url]
 [![Web][Web-image]][web-url]
@@ -31,7 +32,7 @@ One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4
 [MacOS-image]: https://img.shields.io/badge/-MacOS-black?logo=apple
 [Linux-image]: https://img.shields.io/badge/-Linux-333?logo=ubuntu
 
-[<img src="https://vercel.com/button" alt="Deploy on Vercel" height="30">](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) [<img src="https://zeabur.com/button.svg" alt="Deploy on Zeabur" height="30">](https://zeabur.com/templates/ZBUEFA)  [<img src="https://gitpod.io/button/open-in-gitpod.svg" alt="Open in Gitpod" height="30">](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) [<img src="https://img.shields.io/badge/BT_Deploy-Install-20a53a" alt="BT Deply Install" height="30">](https://www.bt.cn/new/download.html) [<img src="https://svgshare.com/i/1AVg.svg" alt="Deploy to Alibaba Cloud" height="30">](https://computenest.aliyun.com/market/service-f1c9b75e59814dc49d52)
+[<img src="https://vercel.com/button" alt="Deploy on Vercel" height="30">](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) [<img src="https://zeabur.com/button.svg" alt="Deploy on Zeabur" height="30">](https://zeabur.com/templates/ZBUEFA)  [<img src="https://gitpod.io/button/open-in-gitpod.svg" alt="Open in Gitpod" height="30">](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) [<img src="https://img.shields.io/badge/BT_Deploy-Install-20a53a" alt="BT Deply Install" height="30">](https://www.bt.cn/new/download.html)
 
 [<img src="https://github.com/user-attachments/assets/903482d4-3e87-4134-9af1-f2588fa90659" height="60" width="288" >](https://monica.im/?utm=nxcrp)
 
@@ -355,6 +356,13 @@ For ByteDance: use `modelName@bytedance=deploymentName` to customize model name
 
 Change default model
 
+### `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：

README_CN.md

@@ -235,6 +235,13 @@ ChatGLM Api Url.
 
 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

README_JA.md

@@ -217,6 +217,13 @@ ByteDance モードでは、`modelName@bytedance=deploymentName` 形式でモデ
 
 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。

app/config/build.ts

@@ -40,6 +40,7 @@ export const getBuildConfig = () => {
     buildMode,
     isApp,
     template: process.env.DEFAULT_INPUT_TEMPLATE ?? DEFAULT_INPUT_TEMPLATE,
+    visionModels: process.env.VISION_MODELS || "",
   };
 };
 

app/constant.ts

@@ -291,6 +291,22 @@ export const DEFAULT_TTS_VOICES = [
   "shimmer",
 ];
 
+export const VISION_MODEL_REGEXES = [
+  /vision/,
+  /gpt-4o/,
+  /claude-3/,
+  /gemini-1\.5/,
+  /gemini-exp/,
+  /gemini-2\.0/,
+  /learnlm/,
+  /qwen-vl/,
+  /qwen2-vl/,
+  /gpt-4-turbo(?!.*preview)/, // Matches "gpt-4-turbo" but not "gpt-4-turbo-preview"
+  /^dall-e-3$/, // Matches exactly "dall-e-3"
+];
+
+export const EXCLUDE_VISION_MODEL_REGEXES = [/claude-3-5-haiku-20241022/];
+
 const openaiModels = [
   "gpt-3.5-turbo",
   "gpt-3.5-turbo-1106",
@@ -317,13 +333,23 @@ const openaiModels = [
 ];
 
 const googleModels = [
-  "gemini-1.0-pro",
+  "gemini-1.0-pro", // Deprecated on 2/15/2025
   "gemini-1.5-pro-latest",
+  "gemini-1.5-pro",
+  "gemini-1.5-pro-002",
+  "gemini-1.5-pro-exp-0827",
   "gemini-1.5-flash-latest",
+  "gemini-1.5-flash-8b-latest",
+  "gemini-1.5-flash",
+  "gemini-1.5-flash-8b",
+  "gemini-1.5-flash-002",
+  "gemini-1.5-flash-exp-0827",
+  "learnlm-1.5-pro-experimental",
   "gemini-exp-1114",
   "gemini-exp-1121",
-  "learnlm-1.5-pro-experimental",
+  "gemini-exp-1206",
-  "gemini-pro-vision",
+  "gemini-2.0-flash-exp",
+  "gemini-2.0-flash-thinking-exp-1219",
 ];
 
 const anthropicModels = [

app/masks/cn.ts

@@ -3,7 +3,7 @@ import { BuiltinMask } from "./typing";
 export const CN_MASKS: BuiltinMask[] = [
   {
     avatar: "1f5bc-fe0f",
-    name: "以文搜图",
+    name: "AI文生图",
     context: [
       {
         id: "text-to-pic-0",
@@ -28,7 +28,7 @@ export const CN_MASKS: BuiltinMask[] = [
         id: "text-to-pic-3",
         role: "system",
         content:
-          "助手善于判断用户意图，当确定需要提供图片时，助手会变得沉默寡言，只使用以下格式输出markdown图片：![描述](https://image.pollinations.ai/prompt/描述)，因为这个语法可以自动按照提示生成并渲染图片。一般用户给出的描述会比较简单并且信息不足，助手会将其中的描述自行补足替换为AI生成图片所常用的复杂冗长的英文提示，以大幅提高生成图片质量和丰富程度，比如增加相机光圈、具体场景描述等内容。助手会避免用代码块或原始块包围markdown标记，因为那样只会渲染出代码块或原始块而不是图片。",
+          "助手善于判断用户意图，当确定需要提供图片时，助手会变得沉默寡言，只使用以下格式输出markdown图片：![description](https://image.pollinations.ai/prompt/description?nologo=true)，因为这个语法可以自动按照提示生成并渲染图片。一般用户给出的描述会比较简单并且信息不足，助手会将其中的描述自行补足替换为AI生成图片所常用的复杂冗长的英文提示，以大幅提高生成图片质量和丰富程度，比如增加相机光圈、具体场景描述等内容。助手会避免用代码块或原始块包围markdown标记，因为那样只会渲染出代码块或原始块而不是图片。url中的空格等符号需要转义。",
         date: "",
       },
     ],

app/utils.ts

@@ -5,6 +5,8 @@ import { RequestMessage } from "./client/api";
 import { ServiceProvider } from "./constant";
 // import { fetch as tauriFetch, ResponseType } from "@tauri-apps/api/http";
 import { fetch as tauriStreamFetch } from "./utils/stream";
+import { VISION_MODEL_REGEXES, EXCLUDE_VISION_MODEL_REGEXES } from "./constant";
+import { getClientConfig } from "./config/client";
 
 export function trimTopic(topic: string) {
   // Fix an issue where double quotes still show in the Indonesian language
@@ -252,27 +254,16 @@ export function getMessageImages(message: RequestMessage): string[] {
 }
 
 export function isVisionModel(model: string) {
-  // Note: This is a better way using the TypeScript feature instead of `&&` or `||` (ts v5.5.0-dev.20240314 I've been using)
+  const clientConfig = getClientConfig();
-
+  const envVisionModels = clientConfig?.visionModels
-  const excludeKeywords = ["claude-3-5-haiku-20241022"];
+    ?.split(",")
-  const visionKeywords = [
+    .map((m) => m.trim());
-    "vision",
+  if (envVisionModels?.includes(model)) {
-    "gpt-4o",
+    return true;
-    "claude-3",
+  }
-    "gemini-1.5",
-    "gemini-exp",
-    "learnlm",
-    "qwen-vl",
-    "qwen2-vl",
-  ];
-  const isGpt4Turbo =
-    model.includes("gpt-4-turbo") && !model.includes("preview");
-
   return (
-    !excludeKeywords.some((keyword) => model.includes(keyword)) &&
+    !EXCLUDE_VISION_MODEL_REGEXES.some((regex) => regex.test(model)) &&
-    (visionKeywords.some((keyword) => model.includes(keyword)) ||
+    VISION_MODEL_REGEXES.some((regex) => regex.test(model))
-      isGpt4Turbo ||
-      isDalle3(model))
   );
 }
 

package.json

@@ -60,7 +60,7 @@
     "@tauri-apps/cli": "1.5.11",
     "@testing-library/dom": "^10.4.0",
     "@testing-library/jest-dom": "^6.6.3",
-    "@testing-library/react": "^16.0.1",
+    "@testing-library/react": "^16.1.0",
     "@types/jest": "^29.5.14",
     "@types/js-yaml": "4.0.9",
     "@types/lodash-es": "^4.17.12",

test/vision-model-checker.test.ts

@@ -0,0 +1,67 @@
+import { isVisionModel } from "../app/utils";
+
+describe("isVisionModel", () => {
+  const originalEnv = process.env;
+
+  beforeEach(() => {
+    jest.resetModules();
+    process.env = { ...originalEnv };
+  });
+
+  afterEach(() => {
+    process.env = originalEnv;
+  });
+
+  test("should identify vision models using regex patterns", () => {
+    const visionModels = [
+      "gpt-4-vision",
+      "claude-3-opus",
+      "gemini-1.5-pro",
+      "gemini-2.0",
+      "gemini-exp-vision",
+      "learnlm-vision",
+      "qwen-vl-max",
+      "qwen2-vl-max",
+      "gpt-4-turbo",
+      "dall-e-3",
+    ];
+
+    visionModels.forEach((model) => {
+      expect(isVisionModel(model)).toBe(true);
+    });
+  });
+
+  test("should exclude specific models", () => {
+    expect(isVisionModel("claude-3-5-haiku-20241022")).toBe(false);
+  });
+
+  test("should not identify non-vision models", () => {
+    const nonVisionModels = [
+      "gpt-3.5-turbo",
+      "gpt-4-turbo-preview",
+      "claude-2",
+      "regular-model",
+    ];
+
+    nonVisionModels.forEach((model) => {
+      expect(isVisionModel(model)).toBe(false);
+    });
+  });
+
+  test("should identify models from VISION_MODELS env var", () => {
+    process.env.VISION_MODELS = "custom-vision-model,another-vision-model";
+    
+    expect(isVisionModel("custom-vision-model")).toBe(true);
+    expect(isVisionModel("another-vision-model")).toBe(true);
+    expect(isVisionModel("unrelated-model")).toBe(false);
+  });
+
+  test("should handle empty or missing VISION_MODELS", () => {
+    process.env.VISION_MODELS = "";
+    expect(isVisionModel("unrelated-model")).toBe(false);
+
+    delete process.env.VISION_MODELS;
+    expect(isVisionModel("unrelated-model")).toBe(false);
+    expect(isVisionModel("gpt-4-vision")).toBe(true);
+  });
+});

yarn.lock

@@ -2127,10 +2127,10 @@
     lodash "^4.17.21"
     redent "^3.0.0"
 
-"@testing-library/react@^16.0.1":
+"@testing-library/react@^16.1.0":
-  version "16.0.1"
+  version "16.1.0"
-  resolved "https://registry.yarnpkg.com/@testing-library/react/-/react-16.0.1.tgz#29c0ee878d672703f5e7579f239005e4e0faa875"
+  resolved "https://registry.yarnpkg.com/@testing-library/react/-/react-16.1.0.tgz#aa0c61398bac82eaf89776967e97de41ac742d71"
-  integrity sha512-dSmwJVtJXmku+iocRhWOUFbrERC76TX2Mnf0ATODz8brzAZrMBbzLwQixlBSanZxR6LddK3eiwpSFZgDET1URg==
+  integrity sha512-Q2ToPvg0KsVL0ohND9A3zLJWcOXXcO8IDu3fj11KhNt0UlCWyFyvnCIBkd12tidB2lkiVRG8VFqdhcqhqnAQtg==
   dependencies:
     "@babel/runtime" "^7.12.5"