Feature/chatglm

README.md

@@ -32,7 +32,7 @@ One-Click to get a well-designed cross-platform ChatGPT web UI, with Claude, GPT
 [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://vercel.com/button" alt="Deploy on Vercel" height="30">](https://vercel.com/new/clone?repository-url=https://github.com/Dogtiti/ChatGPT-Next-Web-EarlyBird&env=OPENAI_API_KEY&env=CODE&project-name=nextchat-earlyBird&repository-name=NextChat-EarlyBird) [<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)
 
@@ -477,7 +477,7 @@ If you want to add a new translation, read this [document](./docs/translation.md
 
 ## Donation
 
-[Buy Me a Coffee](https://www.buymeacoffee.com/yidadaa)
+[Buy Me a Coffee](https://1kafei.com/dogtiti)
 
 ## Special Thanks
 

README_CN.md

@@ -33,7 +33,7 @@
 
 1. 准备好你的 [OpenAI API Key](https://platform.openai.com/account/api-keys);
 2. 点击右侧按钮开始部署：
-   [![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&env=GOOGLE_API_KEY&project-name=chatgpt-next-web&repository-name=ChatGPT-Next-Web)，直接使用 Github 账号登录即可，记得在环境变量页填入 API Key 和[页面访问密码](#配置页面访问密码) CODE；
+   [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https://github.com/Dogtiti/ChatGPT-Next-Web-EarlyBird&env=OPENAI_API_KEY&env=CODE&project-name=nextchat-earlyBird&repository-name=NextChat-EarlyBird)，直接使用 Github 账号登录即可，记得在环境变量页填入 API Key 和[页面访问密码](#配置页面访问密码) CODE；
 3. 部署完毕后，即可开始使用；
 4. （可选）[绑定自定义域名](https://vercel.com/docs/concepts/projects/domains/add-a-domain)：Vercel 分配的域名 DNS 在某些区域被污染了，绑定自定义域名即可直连。
 

README_JA.md

@@ -30,7 +30,7 @@
 
 1. [OpenAI API Key](https://platform.openai.com/account/api-keys)を準備する;
 2. 右側のボタンをクリックしてデプロイを開始：
-   [![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&env=GOOGLE_API_KEY&project-name=chatgpt-next-web&repository-name=ChatGPT-Next-Web) 、GitHubアカウントで直接ログインし、環境変数ページにAPI Keyと[ページアクセスパスワード](#設定ページアクセスパスワード) CODEを入力してください;
+   [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https://github.com/Dogtiti/ChatGPT-Next-Web-EarlyBird&env=OPENAI_API_KEY&env=CODE&project-name=nextchat-earlyBird&repository-name=NextChat-EarlyBird) 、GitHubアカウントで直接ログインし、環境変数ページにAPI Keyと[ページアクセスパスワード](#設定ページアクセスパスワード) CODEを入力してください;
 3. デプロイが完了したら、すぐに使用を開始できます;
 4. （オプション）[カスタムドメインをバインド](https://vercel.com/docs/concepts/projects/domains/add-a-domain)：Vercelが割り当てたドメインDNSは一部の地域で汚染されているため、カスタムドメインをバインドすると直接接続できます。
 

app/client/platforms/glm.ts

@@ -25,12 +25,103 @@ import { getMessageTextContent } from "@/app/utils";
 import { RequestPayload } from "./openai";
 import { fetch } from "@/app/utils/stream";
 
+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](${imageUrl})` : "";
+      }
+      case "video": {
+        const videoUrl = json.data?.[0]?.url;
+        return videoUrl ? `<video controls src="${videoUrl}"></video>` : "";
+      }
+      default:
+        return this.extractMessage(json);
+    }
+  }
+
   path(path: string): string {
     const accessStore = useAccessStore.getState();
-
     let baseUrl = "";
 
     if (accessStore.useCustomConfig) {
@@ -51,7 +142,6 @@ export class ChatGLMApi implements LLMApi {
     }
 
     console.log("[Proxy Endpoint] ", baseUrl, path);
-
     return [baseUrl, path].join("/");
   }
 
@@ -79,53 +169,55 @@ export class ChatGLMApi implements LLMApi {
       },
     };
 
-    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,
-    };
+    const modelType = this.getModelType(modelConfig.model);
+    const requestPayload = this.createPayload(messages, modelConfig, options);
+    const path = this.path(this.getModelPath(modelType));
 
-    console.log("[Request] glm payload: ", requestPayload);
+    console.log(`[Request] glm ${modelType} payload: `, requestPayload);
 
-    const shouldStream = !!options.config.stream;
     const controller = new AbortController();
     options.onController?.(controller);
 
     try {
-      const chatPath = this.path(ChatGLM.ChatPath);
       const chatPayload = {
         method: "POST",
         body: JSON.stringify(requestPayload),
         signal: controller.signal,
         headers: getHeaders(),
       };
 
-      // make a fetch request
       const requestTimeoutId = setTimeout(
         () => controller.abort(),
         REQUEST_TIMEOUT_MS,
       );
 
+      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(
-          chatPath,
+          path,
           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: {
@@ -154,7 +246,7 @@ export class ChatGLMApi implements LLMApi {
             }
             return choices[0]?.delta?.content;
           },
-          // processToolMessage, include tool_calls message and tool call results
+          // processToolMessage
           (
             requestPayload: RequestPayload,
             toolCallMessage: any,
@@ -172,7 +264,7 @@ export class ChatGLMApi implements LLMApi {
           options,
         );
       } else {
-        const res = await fetch(chatPath, chatPayload);
+        const res = await fetch(path, chatPayload);
         clearTimeout(requestTimeoutId);
 
         const resJson = await res.json();
@@ -184,6 +276,7 @@ export class ChatGLMApi implements LLMApi {
       options.onError?.(e as Error);
     }
   }
+
   async usage() {
     return {
       used: 0,

app/client/platforms/openai.ts

@@ -24,7 +24,7 @@ import {
   stream,
 } 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,
@@ -73,7 +73,7 @@ export interface DalleRequestPayload {
   prompt: string;
   response_format: "url" | "b64_json";
   n: number;
-  size: DalleSize;
+  size: ModelSize;
   quality: DalleQuality;
   style: DalleStyle;
 }

app/components/chat.tsx

@@ -72,14 +72,16 @@ import {
   isDalle3,
   showPlugins,
   safeLocalStorage,
+  getModelSizes,
+  supportsCustomSize,
 } from "../utils";
 
 import { uploadImage as uploadImageRemote } from "@/app/utils/chat";
 
 import dynamic from "next/dynamic";
 
 import { ChatControllerPool } from "../client/controller";
-import { DalleSize, DalleQuality, DalleStyle } from "../typing";
+import { DalleQuality, DalleStyle, ModelSize } from "../typing";
 import { Prompt, usePromptStore } from "../store/prompt";
 import Locale from "../locales";
 
@@ -519,10 +521,11 @@ export function ChatActions(props: {
   const [showSizeSelector, setShowSizeSelector] = useState(false);
   const [showQualitySelector, setShowQualitySelector] = useState(false);
   const [showStyleSelector, setShowStyleSelector] = useState(false);
-  const dalle3Sizes: DalleSize[] = ["1024x1024", "1792x1024", "1024x1792"];
+  const modelSizes = getModelSizes(currentModel);
   const dalle3Qualitys: DalleQuality[] = ["standard", "hd"];
   const dalle3Styles: DalleStyle[] = ["vivid", "natural"];
-  const currentSize = session.mask.modelConfig?.size ?? "1024x1024";
+  const currentSize =
+    session.mask.modelConfig?.size ?? ("1024x1024" as ModelSize);
   const currentQuality = session.mask.modelConfig?.quality ?? "standard";
   const currentStyle = session.mask.modelConfig?.style ?? "vivid";
 
@@ -673,7 +676,7 @@ export function ChatActions(props: {
           />
         )}
 
-        {isDalle3(currentModel) && (
+        {supportsCustomSize(currentModel) && (
           <ChatAction
             onClick={() => setShowSizeSelector(true)}
             text={currentSize}
@@ -684,7 +687,7 @@ export function ChatActions(props: {
         {showSizeSelector && (
           <Selector
             defaultSelectedValue={currentSize}
-            items={dalle3Sizes.map((m) => ({
+            items={modelSizes.map((m) => ({
               title: m,
               value: m,
             }))}

app/constant.ts

@@ -233,6 +233,8 @@ export const XAI = {
 export const ChatGLM = {
   ExampleEndpoint: CHATGLM_BASE_URL,
   ChatPath: "api/paas/v4/chat/completions",
+  ImagePath: "api/paas/v4/images/generations",
+  VideoPath: "api/paas/v4/videos/generations",
 };
 
 export const DEFAULT_INPUT_TEMPLATE = `{{input}}`; // input / time / model / lang
@@ -431,6 +433,15 @@ const chatglmModels = [
   "glm-4-long",
   "glm-4-flashx",
   "glm-4-flash",
+  "glm-4v-plus",
+  "glm-4v",
+  "glm-4v-flash", // free
+  "cogview-3-plus",
+  "cogview-3",
+  "cogview-3-flash", // free
+  // 目前无法适配轮询任务
+  //   "cogvideox",
+  //   "cogvideox-flash", // free
 ];
 
 let seq = 1000; // 内置的模型序号生成器从1000开始

app/store/config.ts

@@ -1,5 +1,5 @@
 import { LLMModel } from "../client/api";
-import { DalleSize, DalleQuality, DalleStyle } from "../typing";
+import { DalleQuality, DalleStyle, ModelSize } from "../typing";
 import { getClientConfig } from "../config/client";
 import {
   DEFAULT_INPUT_TEMPLATE,
@@ -78,7 +78,7 @@ export const DEFAULT_CONFIG = {
     compressProviderName: "",
     enableInjectSystemPrompts: true,
     template: config?.template ?? DEFAULT_INPUT_TEMPLATE,
-    size: "1024x1024" as DalleSize,
+    size: "1024x1024" as ModelSize,
     quality: "standard" as DalleQuality,
     style: "vivid" as DalleStyle,
   },

app/typing.ts

@@ -11,3 +11,14 @@ export interface RequestMessage {
 export type DalleSize = "1024x1024" | "1792x1024" | "1024x1792";
 export type DalleQuality = "standard" | "hd";
 export type DalleStyle = "vivid" | "natural";
+
+export type ModelSize =
+  | "1024x1024"
+  | "1792x1024"
+  | "1024x1792"
+  | "768x1344"
+  | "864x1152"
+  | "1344x768"
+  | "1152x864"
+  | "1440x720"
+  | "720x1440";