Merge feature/update-bedrock-api into main

README.md

@@ -31,7 +31,7 @@ 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 Zeabur" 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="Open in Gitpod" 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%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://github.com/user-attachments/assets/903482d4-3e87-4134-9af1-f2588fa90659" height="60" width="288" >](https://monica.im/?utm=nxcrp)
 
@@ -301,6 +301,14 @@ iflytek Api Key.
 
 iflytek Api Secret.
 
+### `CHATGLM_API_KEY` (optional)
+
+ChatGLM Api Key.
+
+### `CHATGLM_URL` (optional)
+
+ChatGLM Api Url.
+
 ### `HIDE_USER_API_KEY` (optional)
 
 > Default: Empty
@@ -397,6 +405,9 @@ yarn dev
 
 > [简体中文 > 如何部署到私人服务器](./README_CN.md#部署)
 
+### BT Install
+> [简体中文 > 如何通过宝塔一键部署](./docs/bt-cn.md)
+
 ### Docker (Recommended)
 
 ```shell

README_CN.md

@@ -184,6 +184,13 @@ ByteDance Api Url.
 
 讯飞星火Api Secret.
 
+### `CHATGLM_API_KEY` (可选)
+
+ChatGLM Api Key.
+
+### `CHATGLM_URL` (可选)
+
+ChatGLM Api Url.
 
 
 ### `HIDE_USER_API_KEY` （可选）
@@ -264,6 +271,9 @@ 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。

app/api/[provider]/[...path]/route.ts

@@ -12,6 +12,7 @@ import { handle as moonshotHandler } from "../../moonshot";
 import { handle as stabilityHandler } from "../../stability";
 import { handle as iflytekHandler } from "../../iflytek";
 import { handle as xaiHandler } from "../../xai";
+import { handle as chatglmHandler } from "../../glm";
 import { handle as proxyHandler } from "../../proxy";
 
 async function handle(
@@ -45,6 +46,8 @@ async function handle(
       return iflytekHandler(req, { params });
     case ApiPath.XAI:
       return xaiHandler(req, { params });
+    case ApiPath.ChatGLM:
+      return chatglmHandler(req, { params });
     case ApiPath.OpenAI:
       return openaiHandler(req, { params });
     default:

app/api/auth.ts

@@ -117,6 +117,9 @@ export function auth(req: NextRequest, modelProvider: ModelProvider) {
       case ModelProvider.XAI:
         systemApiKey = serverConfig.xaiApiKey;
         break;
+      case ModelProvider.ChatGLM:
+        systemApiKey = serverConfig.chatglmApiKey;
+        break;
       case ModelProvider.GPT:
       default:
         if (req.nextUrl.pathname.includes("azure/deployments")) {

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 { isModelAvailableInServer } 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 (
+        isModelAvailableInServer(
+          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);
+  }
+}

app/client/api.ts

@@ -22,6 +22,7 @@ import { HunyuanApi } from "./platforms/tencent";
 import { MoonshotApi } from "./platforms/moonshot";
 import { SparkApi } from "./platforms/iflytek";
 import { XAIApi } from "./platforms/xai";
+import { ChatGLMApi } from "./platforms/glm";
 
 export const ROLES = ["system", "user", "assistant"] as const;
 export type MessageRole = (typeof ROLES)[number];
@@ -78,7 +79,7 @@ export interface ChatOptions {
   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;
@@ -168,6 +169,9 @@ export class ClientApi {
       case ModelProvider.XAI:
         this.llm = new XAIApi();
         break;
+      case ModelProvider.ChatGLM:
+        this.llm = new ChatGLMApi();
+        break;
       default:
         this.llm = new ChatGPTApi();
     }
@@ -257,6 +261,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
     const isMoonshot = modelConfig.providerName === ServiceProvider.Moonshot;
     const isIflytek = modelConfig.providerName === ServiceProvider.Iflytek;
     const isXAI = modelConfig.providerName === ServiceProvider.XAI;
+    const isChatGLM = modelConfig.providerName === ServiceProvider.ChatGLM;
     const isEnabledAccessControl = accessStore.enabledAccessControl();
     const apiKey = isGoogle
       ? accessStore.googleApiKey
@@ -274,6 +279,8 @@ export function getHeaders(ignoreHeaders: boolean = false) {
       ? accessStore.moonshotApiKey
       : isXAI
       ? accessStore.xaiApiKey
+      : isChatGLM
+      ? accessStore.chatglmApiKey
       : isIflytek
       ? accessStore.iflytekApiKey && accessStore.iflytekApiSecret
         ? accessStore.iflytekApiKey + ":" + accessStore.iflytekApiSecret
@@ -290,6 +297,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
       isMoonshot,
       isIflytek,
       isXAI,
+      isChatGLM,
       apiKey,
       isEnabledAccessControl,
     };
@@ -372,6 +380,8 @@ export function getClientApi(provider: ServiceProvider): ClientApi {
       return new ClientApi(ModelProvider.Iflytek);
     case ServiceProvider.XAI:
       return new ClientApi(ModelProvider.XAI);
+    case ServiceProvider.ChatGLM:
+      return new ClientApi(ModelProvider.ChatGLM);
     default:
       return new ClientApi(ModelProvider.GPT);
   }

app/client/platforms/alibaba.ts

@@ -143,6 +143,7 @@ export class QwenApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // animate response to make it looks smooth
         function animateResponseText() {
@@ -172,7 +173,7 @@ export class QwenApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -188,6 +189,7 @@ export class QwenApi implements LLMApi {
               "[Alibaba] request response content type: ",
               contentType,
             );
+            responseRes = res;
 
             if (contentType?.startsWith("text/plain")) {
               responseText = await res.clone().text();
@@ -254,7 +256,7 @@ export class QwenApi 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);

app/client/platforms/anthropic.ts

@@ -317,13 +317,14 @@ 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);

app/client/platforms/baidu.ts

@@ -162,6 +162,7 @@ export class ErnieApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // animate response to make it looks smooth
         function animateResponseText() {
@@ -191,7 +192,7 @@ export class ErnieApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -204,7 +205,7 @@ export class ErnieApi implements LLMApi {
             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();
@@ -267,7 +268,7 @@ 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);

app/client/platforms/bytedance.ts

@@ -130,6 +130,7 @@ export class DoubaoApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // animate response to make it looks smooth
         function animateResponseText() {
@@ -159,7 +160,7 @@ export class DoubaoApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -175,7 +176,7 @@ export class DoubaoApi implements LLMApi {
               "[ByteDance] request response content type: ",
               contentType,
             );
-
+            responseRes = res;
             if (contentType?.startsWith("text/plain")) {
               responseText = await res.clone().text();
               return finish();
@@ -241,7 +242,7 @@ export class DoubaoApi 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);

app/client/platforms/glm.ts

@@ -0,0 +1,197 @@
+"use client";
+import {
+  ApiPath,
+  CHATGLM_BASE_URL,
+  ChatGLM,
+  REQUEST_TIMEOUT_MS,
+} 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 } from "@/app/utils";
+import { RequestPayload } from "./openai";
+import { fetch } from "@/app/utils/stream";
+
+export class ChatGLMApi implements LLMApi {
+  private disableListModels = true;
+
+  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<ArrayBuffer> {
+    throw new Error("Method not implemented.");
+  }
+
+  async chat(options: ChatOptions) {
+    const messages: ChatOptions["messages"] = [];
+    for (const v of options.messages) {
+      const 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,
+    };
+
+    console.log("[Request] glm 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 (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<LLMModel[]> {
+    return [];
+  }
+}

app/client/platforms/google.ts

@@ -274,7 +274,7 @@ 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);

app/client/platforms/iflytek.ts

@@ -117,6 +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() {
@@ -143,7 +144,7 @@ export class SparkApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -156,7 +157,7 @@ export class SparkApi implements LLMApi {
             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();
@@ -231,7 +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);

app/client/platforms/moonshot.ts

@@ -180,7 +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);

app/client/platforms/openai.ts

@@ -361,7 +361,7 @@ 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);

app/client/platforms/tencent.ts

@@ -142,6 +142,7 @@ export class HunyuanApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // animate response to make it looks smooth
         function animateResponseText() {
@@ -171,7 +172,7 @@ export class HunyuanApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -187,7 +188,7 @@ 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();
@@ -253,7 +254,7 @@ 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);

app/client/platforms/xai.ts

@@ -173,7 +173,7 @@ export class XAIApi 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);

app/components/chat.tsx

@@ -1607,7 +1607,7 @@ function _Chat() {
               title={Locale.Chat.Actions.RefreshTitle}
               onClick={() => {
                 showToast(Locale.Chat.Actions.RefreshToast);
-                chatStore.summarizeSession(true);
+                chatStore.summarizeSession(true, session);
               }}
             />
           </div>

app/components/settings.tsx

@@ -72,6 +72,7 @@ import {
   Stability,
   Iflytek,
   SAAS_CHAT_URL,
+  ChatGLM,
 } from "../constant";
 import { Prompt, SearchService, usePromptStore } from "../store/prompt";
 import { ErrorBoundary } from "./error";
@@ -1302,6 +1303,47 @@ export function Settings() {
     </>
   );
 
+  const chatglmConfigComponent = accessStore.provider ===
+    ServiceProvider.ChatGLM && (
+    <>
+      <ListItem
+        title={Locale.Settings.Access.ChatGLM.Endpoint.Title}
+        subTitle={
+          Locale.Settings.Access.ChatGLM.Endpoint.SubTitle +
+          ChatGLM.ExampleEndpoint
+        }
+      >
+        <input
+          aria-label={Locale.Settings.Access.ChatGLM.Endpoint.Title}
+          type="text"
+          value={accessStore.chatglmUrl}
+          placeholder={ChatGLM.ExampleEndpoint}
+          onChange={(e) =>
+            accessStore.update(
+              (access) => (access.chatglmUrl = e.currentTarget.value),
+            )
+          }
+        ></input>
+      </ListItem>
+      <ListItem
+        title={Locale.Settings.Access.ChatGLM.ApiKey.Title}
+        subTitle={Locale.Settings.Access.ChatGLM.ApiKey.SubTitle}
+      >
+        <PasswordInput
+          aria-label={Locale.Settings.Access.ChatGLM.ApiKey.Title}
+          value={accessStore.chatglmApiKey}
+          type="text"
+          placeholder={Locale.Settings.Access.ChatGLM.ApiKey.Placeholder}
+          onChange={(e) => {
+            accessStore.update(
+              (access) => (access.chatglmApiKey = e.currentTarget.value),
+            );
+          }}
+        />
+      </ListItem>
+    </>
+  );
+
   const stabilityConfigComponent = accessStore.provider ===
     ServiceProvider.Stability && (
     <>
@@ -1762,6 +1804,7 @@ export function Settings() {
                   {stabilityConfigComponent}
                   {lflytekConfigComponent}
                   {XAIConfigComponent}
+                  {chatglmConfigComponent}
                 </>
               )}
             </>

app/config/server.ts

@@ -80,6 +80,10 @@ declare global {
       XAI_URL?: string;
       XAI_API_KEY?: string;
 
+      // chatglm only
+      CHATGLM_URL?: string;
+      CHATGLM_API_KEY?: string;
+
       // custom template for preprocessing user input
       DEFAULT_INPUT_TEMPLATE?: string;
     }
@@ -156,6 +160,7 @@ export const getServerSideConfig = () => {
   const isMoonshot = !!process.env.MOONSHOT_API_KEY;
   const isIflytek = !!process.env.IFLYTEK_API_KEY;
   const isXAI = !!process.env.XAI_API_KEY;
+  const isChatGLM = !!process.env.CHATGLM_API_KEY;
   // const apiKeyEnvVar = process.env.OPENAI_API_KEY ?? "";
   // const apiKeys = apiKeyEnvVar.split(",").map((v) => v.trim());
   // const randomIndex = Math.floor(Math.random() * apiKeys.length);
@@ -227,6 +232,10 @@ export const getServerSideConfig = () => {
     xaiUrl: process.env.XAI_URL,
     xaiApiKey: getApiKey(process.env.XAI_API_KEY),
 
+    isChatGLM,
+    chatglmUrl: process.env.CHATGLM_URL,
+    chatglmApiKey: getApiKey(process.env.CHATGLM_API_KEY),
+
     cloudflareAccountId: process.env.CLOUDFLARE_ACCOUNT_ID,
     cloudflareKVNamespaceId: process.env.CLOUDFLARE_KV_NAMESPACE_ID,
     cloudflareKVApiKey: getApiKey(process.env.CLOUDFLARE_KV_API_KEY),

app/constant.ts

@@ -32,6 +32,8 @@ export const IFLYTEK_BASE_URL = "https://spark-api-open.xf-yun.com";
 
 export const XAI_BASE_URL = "https://api.x.ai";
 
+export const CHATGLM_BASE_URL = "https://open.bigmodel.cn";
+
 export const CACHE_URL_PREFIX = "/api/cache";
 export const UPLOAD_URL = `${CACHE_URL_PREFIX}/upload`;
 
@@ -65,6 +67,7 @@ export enum ApiPath {
   Stability = "/api/stability",
   Artifacts = "/api/artifacts",
   XAI = "/api/xai",
+  ChatGLM = "/api/chatglm",
 }
 
 export enum SlotID {
@@ -119,6 +122,7 @@ export enum ServiceProvider {
   Iflytek = "Iflytek",
   XAI = "XAI",
   Bedrock = "Bedrock",
+  ChatGLM = "ChatGLM",
 }
 
 // Google API safety settings, see https://ai.google.dev/gemini-api/docs/safety-settings
@@ -143,6 +147,7 @@ export enum ModelProvider {
   Moonshot = "Moonshot",
   Iflytek = "Iflytek",
   XAI = "XAI",
+  ChatGLM = "ChatGLM",
 }
 
 export const Stability = {
@@ -230,6 +235,11 @@ export const XAI = {
   ChatPath: "v1/chat/completions",
 };
 
+export const ChatGLM = {
+  ExampleEndpoint: CHATGLM_BASE_URL,
+  ChatPath: "/api/paas/v4/chat/completions",
+};
+
 export const Bedrock = {
   ChatPath: "converse",
 };
@@ -342,11 +352,12 @@ const anthropicModels = [
   "claude-2.1",
   "claude-3-sonnet-20240229",
   "claude-3-opus-20240229",
+  "claude-3-opus-latest",
   "claude-3-haiku-20240307",
   "claude-3-5-sonnet-20240620",
   "claude-3-5-sonnet-20241022",
   "claude-3-5-sonnet-latest",
-  "claude-3-opus-latest",
+  "claude-3-5-haiku-latest",
 ];
 
 const baiduModels = [
@@ -404,6 +415,17 @@ const iflytekModels = [
 
 const xAIModes = ["grok-beta"];
 
+const chatglmModels = [
+  "glm-4-plus",
+  "glm-4-0520",
+  "glm-4",
+  "glm-4-air",
+  "glm-4-airx",
+  "glm-4-long",
+  "glm-4-flashx",
+  "glm-4-flash",
+];
+
 let seq = 1000; // 内置的模型序号生成器从1000开始
 export const DEFAULT_MODELS = [
   ...openaiModels.map((name) => ({
@@ -527,6 +549,19 @@ export const DEFAULT_MODELS = [
       sorted: 11,
     },
   })),
+
+  ...chatglmModels.map((name) => ({
+    name,
+    available: true,
+    sorted: seq++,
+    provider: {
+      id: "chatglm",
+      providerName: "ChatGLM",
+      providerType: "chatglm",
+      sorted: 12,
+    },
+  })),
+
   ...bedrockModels.map((name) => ({
     name,
     available: true,

app/locales/cn.ts

@@ -500,6 +500,17 @@ const cn = {
           SubTitle: "样例：",
         },
       },
+      ChatGLM: {
+        ApiKey: {
+          Title: "接口密钥",
+          SubTitle: "使用自定义 ChatGLM API Key",
+          Placeholder: "ChatGLM API Key",
+        },
+        Endpoint: {
+          Title: "接口地址",
+          SubTitle: "样例：",
+        },
+      },
       Stability: {
         ApiKey: {
           Title: "接口密钥",

app/locales/en.ts

@@ -484,6 +484,17 @@ const en: LocaleType = {
           SubTitle: "Example: ",
         },
       },
+      ChatGLM: {
+        ApiKey: {
+          Title: "ChatGLM API Key",
+          SubTitle: "Use a custom ChatGLM API Key",
+          Placeholder: "ChatGLM API Key",
+        },
+        Endpoint: {
+          Title: "Endpoint Address",
+          SubTitle: "Example: ",
+        },
+      },
       Stability: {
         ApiKey: {
           Title: "Stability API Key",

app/store/access.ts

@@ -15,6 +15,7 @@ import {
   STABILITY_BASE_URL,
   IFLYTEK_BASE_URL,
   XAI_BASE_URL,
+  CHATGLM_BASE_URL,
 } from "../constant";
 import { getHeaders } from "../client/api";
 import { getClientConfig } from "../config/client";
@@ -49,6 +50,8 @@ const DEFAULT_IFLYTEK_URL = isApp ? IFLYTEK_BASE_URL : ApiPath.Iflytek;
 
 const DEFAULT_XAI_URL = isApp ? XAI_BASE_URL : ApiPath.XAI;
 
+const DEFAULT_CHATGLM_URL = isApp ? CHATGLM_BASE_URL : ApiPath.ChatGLM;
+
 const DEFAULT_ACCESS_STATE = {
   accessCode: "",
   useCustomConfig: false,
@@ -117,6 +120,10 @@ const DEFAULT_ACCESS_STATE = {
   xaiUrl: DEFAULT_XAI_URL,
   xaiApiKey: "",
 
+  // chatglm
+  chatglmUrl: DEFAULT_CHATGLM_URL,
+  chatglmApiKey: "",
+
   // server config
   needCode: true,
   hideUserApiKey: false,
@@ -193,6 +200,10 @@ export const useAccessStore = createPersistStore(
       return ensure(get(), ["xaiApiKey"]);
     },
 
+    isValidChatGLM() {
+      return ensure(get(), ["chatglmApiKey"]);
+    },
+
     isAuthorized() {
       this.fetch();
 
@@ -210,6 +221,7 @@ export const useAccessStore = createPersistStore(
         this.isValidMoonshot() ||
         this.isValidIflytek() ||
         this.isValidXAI() ||
+        this.isValidChatGLM() ||
         !this.enabledAccessControl() ||
         (this.enabledAccessControl() && ensure(get(), ["accessCode"]))
       );

app/store/chat.ts

@@ -352,13 +352,13 @@ export const useChatStore = createPersistStore(
         return session;
       },
 
-      onNewMessage(message: ChatMessage) {
+      onNewMessage(message: ChatMessage, targetSession: ChatSession) {
-        get().updateCurrentSession((session) => {
+        get().updateTargetSession(targetSession, (session) => {
           session.messages = session.messages.concat();
           session.lastUpdate = Date.now();
         });
         get().updateStat(message);
-        get().summarizeSession();
+        get().summarizeSession(false, targetSession);
       },
 
       async onUserInput(content: string, attachImages?: string[]) {
@@ -428,7 +428,7 @@ export const useChatStore = createPersistStore(
             botMessage.streaming = false;
             if (message) {
               botMessage.content = message;
-              get().onNewMessage(botMessage);
+              get().onNewMessage(botMessage, session);
             }
             ChatControllerPool.remove(session.id, botMessage.id);
           },
@@ -598,9 +598,12 @@ export const useChatStore = createPersistStore(
         });
       },
 
-      summarizeSession(refreshTitle: boolean = false) {
+      summarizeSession(
+        refreshTitle: boolean = false,
+        targetSession: ChatSession,
+      ) {
         const config = useAppConfig.getState();
-        const session = get().currentSession();
+        const session = targetSession;
         const modelConfig = session.mask.modelConfig;
         // skip summarize when using dalle3?
         if (isDalle3(modelConfig.model)) {
@@ -649,13 +652,15 @@ export const useChatStore = createPersistStore(
               stream: false,
               providerName,
             },
-            onFinish(message) {
+            onFinish(message, responseRes) {
-              if (!isValidMessage(message)) return;
+              if (responseRes?.status === 200) {
-              get().updateCurrentSession(
+                get().updateTargetSession(
-                (session) =>
+                  session,
-                  (session.topic =
+                  (session) =>
-                    message.length > 0 ? trimTopic(message) : DEFAULT_TOPIC),
+                    (session.topic =
-              );
+                      message.length > 0 ? trimTopic(message) : DEFAULT_TOPIC),
+                );
+              }
             },
           });
         }
@@ -669,7 +674,7 @@ export const useChatStore = createPersistStore(
 
         const historyMsgLength = countMessages(toBeSummarizedMsgs);
 
-        if (historyMsgLength > modelConfig?.max_tokens ?? 4000) {
+        if (historyMsgLength > (modelConfig?.max_tokens || 4000)) {
           const n = toBeSummarizedMsgs.length;
           toBeSummarizedMsgs = toBeSummarizedMsgs.slice(
             Math.max(0, n - modelConfig.historyMessageCount),
@@ -715,22 +720,20 @@ export const useChatStore = createPersistStore(
             onUpdate(message) {
               session.memoryPrompt = message;
             },
-            onFinish(message) {
+            onFinish(message, responseRes) {
-              console.log("[Memory] ", message);
+              if (responseRes?.status === 200) {
-              get().updateCurrentSession((session) => {
+                console.log("[Memory] ", message);
-                session.lastSummarizeIndex = lastSummarizeIndex;
+                get().updateTargetSession(session, (session) => {
-                session.memoryPrompt = message; // Update the memory prompt for stored it in local storage
+                  session.lastSummarizeIndex = lastSummarizeIndex;
-              });
+                  session.memoryPrompt = message; // Update the memory prompt for stored it in local storage
+                });
+              }
             },
             onError(err) {
               console.error("[Summarize] ", err);
             },
           });
         }
-
-        function isValidMessage(message: any): boolean {
-          return typeof message === "string" && !message.startsWith("```json");
-        }
       },
 
       updateStat(message: ChatMessage) {
@@ -746,7 +749,16 @@ export const useChatStore = createPersistStore(
         updater(sessions[index]);
         set(() => ({ sessions }));
       },
-
+      updateTargetSession(
+        targetSession: ChatSession,
+        updater: (session: ChatSession) => void,
+      ) {
+        const sessions = get().sessions;
+        const index = sessions.findIndex((s) => s.id === targetSession.id);
+        if (index < 0) return;
+        updater(sessions[index]);
+        set(() => ({ sessions }));
+      },
       async clearAllData() {
         await indexedDBStorage.clear();
         localStorage.clear();

app/utils.ts

@@ -266,7 +266,9 @@ export function isVisionModel(model: string) {
     model.includes("gpt-4-turbo") && !model.includes("preview");
 
   return (
-    visionKeywords.some((keyword) => model.includes(keyword)) || isGpt4Turbo
+    visionKeywords.some((keyword) => model.includes(keyword)) ||
+    isGpt4Turbo ||
+    isDalle3(model)
   );
 }
 
@@ -278,7 +280,8 @@ export function showPlugins(provider: ServiceProvider, model: string) {
   if (
     provider == ServiceProvider.OpenAI ||
     provider == ServiceProvider.Azure ||
-    provider == ServiceProvider.Moonshot
+    provider == ServiceProvider.Moonshot ||
+    provider == ServiceProvider.ChatGLM
   ) {
     return true;
   }

app/utils/chat.ts

@@ -174,6 +174,7 @@ export function stream(
   let finished = false;
   let running = false;
   let runTools: any[] = [];
+  let responseRes: Response;
 
   // animate response to make it looks smooth
   function animateResponseText() {
@@ -272,7 +273,7 @@ export function stream(
       }
       console.debug("[ChatAPI] end");
       finished = true;
-      options.onFinish(responseText + remainText);
+      options.onFinish(responseText + remainText, responseRes); // 将res传递给onFinish
     }
   };
 
@@ -304,6 +305,7 @@ export function stream(
         clearTimeout(requestTimeoutId);
         const contentType = res.headers.get("content-type");
         console.log("[Request] response content type: ", contentType);
+        responseRes = res;
 
         if (contentType?.startsWith("text/plain")) {
           responseText = await res.clone().text();

app/utils/stream.ts

@@ -19,7 +19,7 @@ type StreamResponse = {
   headers: Record<string, string>;
 };
 
-export function fetch(url: string, options?: RequestInit): Promise<any> {
+export function fetch(url: string, options?: RequestInit): Promise<Response> {
   if (window.__TAURI__) {
     const {
       signal,

docs/bt-cn.md

@@ -0,0 +1,29 @@
+# 宝塔面板 的部署说明
+
+## 拥有自己的宝塔
+当你需要通过 宝塔面板 部署本项目之前，需要在服务器上先安装好 宝塔面板工具。 接下来的 部署流程 都建立在已有宝塔面板的前提下。宝塔安装请参考 ([宝塔官网](https://www.bt.cn/new/download.html))
+
+> 注意：本项目需要宝塔面板版本 9.2.0 及以上
+
+## 一键安装
+![bt-install-1](./images/bt/bt-install-1.jpeg)
+1. 在 宝塔面板 -> Docker -> 应用商店 页面，搜索 ChatGPT-Next-Web 找到本项目的docker应用；
+2. 点击 安装 开始部署本项目
+
+![bt-install-2](./images/bt/bt-install-2.jpeg)
+1. 在项目配置页，根据要求开始配置环境变量；
+2. 如勾选 允许外部访问 配置，请注意为配置的 web端口 开放安全组端口访问权限；
+3. 请确保你添加了正确的 Open Api Key，否则无法使用；当配置 OpenAI官方 提供的key(国内无法访问)，请配置代理地址；
+4. 建议配置 访问权限密码，否则部署后所有人均可使用已配置的 Open Api Key(当允许外部访问时)；
+5. 点击 确认 开始自动部署。
+
+## 如何访问
+![bt-install-3](./images/bt/bt-install-3.jpeg)
+通过根据 服务器IP地址 和配置的 web端口 http://$(host):$(port)，在浏览器中打开 ChatGPT-Next-Web。
+
+![bt-install-4](./images/bt/bt-install-4.jpeg)
+若配置了 访问权限密码，访问大模型前需要登录，请点击 登录，获取访问权限。
+
+![bt-install-5](./images/bt/bt-install-5.jpeg)
+
+![bt-install-6](./images/bt/bt-install-6.jpeg)

package.json

@@ -59,7 +59,7 @@
     "@tauri-apps/cli": "1.5.11",
     "@testing-library/dom": "^10.4.0",
     "@testing-library/jest-dom": "^6.6.2",
-    "@testing-library/react": "^16.0.0",
+    "@testing-library/react": "^16.0.1",
     "@types/jest": "^29.5.14",
     "@types/js-yaml": "4.0.9",
     "@types/lodash-es": "^4.17.12",

src-tauri/tauri.conf.json

@@ -9,7 +9,7 @@
   },
   "package": {
     "productName": "NextChat",
-    "version": "2.15.6"
+    "version": "2.15.7"
   },
   "tauri": {
     "allowlist": {

yarn.lock

@@ -1201,14 +1201,7 @@
   resolved "https://registry.yarnpkg.com/@babel/regjsgen/-/regjsgen-0.8.0.tgz#f0ba69b075e1f05fb2825b7fad991e7adbb18310"
   integrity sha512-x/rqGMdzj+fWZvCOYForTghzbtqPDZ5gPwaoNGHdgDfF2QA/XZbCBp4Moo5scrkAMPhB7z26XM/AaHuIJdgauA==
 
-"@babel/runtime@^7.12.1", "@babel/runtime@^7.20.7", "@babel/runtime@^7.23.2", "@babel/runtime@^7.8.4", "@babel/runtime@^7.9.2":
+"@babel/runtime@^7.12.1", "@babel/runtime@^7.12.5", "@babel/runtime@^7.20.7", "@babel/runtime@^7.21.0", "@babel/runtime@^7.23.2", "@babel/runtime@^7.8.4", "@babel/runtime@^7.9.2":
-  version "7.23.6"
-  resolved "https://registry.yarnpkg.com/@babel/runtime/-/runtime-7.23.6.tgz#c05e610dc228855dc92ef1b53d07389ed8ab521d"
-  integrity sha512-zHd0eUrf5GZoOWVCXp6koAKQTfZV07eit6bGPmJgnZdnSAvvZee6zniW2XMF7Cmc4ISOOnPy3QaSiIJGJkVEDQ==
-  dependencies:
-    regenerator-runtime "^0.14.0"
-
-"@babel/runtime@^7.12.5", "@babel/runtime@^7.21.0":
   version "7.25.0"
   resolved "https://registry.yarnpkg.com/@babel/runtime/-/runtime-7.25.0.tgz#3af9a91c1b739c569d5d80cc917280919c544ecb"
   integrity sha512-7dRy4DwXwtzBrPbZflqxnvfxLF8kdZXPkhymtDeFoFqE6ldzjQFgYTtYIFARcLEYDrqfBfYcZt1WqFxRoyC9Rw==
@@ -2134,10 +2127,10 @@
     lodash "^4.17.21"
     redent "^3.0.0"
 
-"@testing-library/react@^16.0.0":
+"@testing-library/react@^16.0.1":
-  version "16.0.0"
+  version "16.0.1"
-  resolved "https://registry.npmmirror.com/@testing-library/react/-/react-16.0.0.tgz#0a1e0c7a3de25841c3591b8cb7fb0cf0c0a27321"
+  resolved "https://registry.yarnpkg.com/@testing-library/react/-/react-16.0.1.tgz#29c0ee878d672703f5e7579f239005e4e0faa875"
-  integrity sha512-guuxUKRWQ+FgNX0h0NS0FIq3Q3uLtWVpBzcLOggmfMoUpgBnzBzvLLd4fbm6yS8ydJd94cIfY4yP9qUQjM2KwQ==
+  integrity sha512-dSmwJVtJXmku+iocRhWOUFbrERC76TX2Mnf0ATODz8brzAZrMBbzLwQixlBSanZxR6LddK3eiwpSFZgDET1URg==
   dependencies:
     "@babel/runtime" "^7.12.5"