+
+ 
](https://zeabur.com/templates/ZBUEFA) [
](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web)
+[](https://zeabur.com/templates/ZBUEFA) [](https://gitpod.io/#https://github.com/ChatGPTNextWeb/NextChat)
-[](https://zeabur.com/templates/ZBUEFA) [](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web)
@@ -27,7 +27,8 @@
企业版咨询: **business@nextchat.dev**
-](https://zeabur.com/templates/ZBUEFA) [](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web)
@@ -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。
diff --git a/app/api/[provider]/[...path]/route.ts b/app/api/[provider]/[...path]/route.ts
index dffb3e9da..8975bf971 100644
--- a/app/api/[provider]/[...path]/route.ts
+++ b/app/api/[provider]/[...path]/route.ts
@@ -10,6 +10,10 @@ 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";
async function handle(
@@ -38,6 +42,14 @@ 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 });
default:
diff --git a/app/api/alibaba.ts b/app/api/alibaba.ts
index 894b1ae4c..20f6caefa 100644
--- a/app/api/alibaba.ts
+++ b/app/api/alibaba.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();
@@ -89,7 +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 7a4444371..b96637b2c 100644
--- a/app/api/anthropic.ts
+++ b/app/api/anthropic.ts
@@ -9,7 +9,7 @@ import {
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]);
@@ -122,7 +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 95965ceec..8c78c70c8 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/baidu.ts b/app/api/baidu.ts
index 0408b43c5..0f4e05ee8 100644
--- a/app/api/baidu.ts
+++ b/app/api/baidu.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";
import { getAccessToken } from "@/app/utils/baidu";
const serverConfig = getServerSideConfig();
@@ -104,7 +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 cb65b1061..51b39ceb7 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 b4c792d6f..b7e41fa26 100644
--- a/app/api/common.ts
+++ b/app/api/common.ts
@@ -1,8 +1,8 @@
import { NextRequest, NextResponse } from "next/server";
import { getServerSideConfig } from "../config/server";
import { OPENAI_BASE_URL, ServiceProvider } from "../constant";
-import { isModelAvailableInServer } from "../utils/model";
import { cloudflareAIGatewayUrl } from "../utils/cloudflare";
+import { getModelProvider, isModelNotavailableInServer } from "../utils/model";
const serverConfig = getServerSideConfig();
@@ -71,7 +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/",
@@ -118,15 +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 b0d9da031..855a5db01 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 000000000..a9879eced
--- /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 ${jsonBody?.model} model`,
+ },
+ {
+ status: 403,
+ },
+ );
+ }
+ } catch (e) {
+ console.error(`[DeepSeek] filter`, e);
+ }
+ }
+ try {
+ const res = await fetch(fetchUrl, fetchOptions);
+
+ // to prevent browser prompt for credentials
+ const newHeaders = new Headers(res.headers);
+ newHeaders.delete("www-authenticate");
+ // to disable nginx buffering
+ newHeaders.set("X-Accel-Buffering", "no");
+
+ return new Response(res.body, {
+ status: res.status,
+ statusText: res.statusText,
+ headers: newHeaders,
+ });
+ } finally {
+ clearTimeout(timeoutId);
+ }
+}
diff --git a/app/api/glm.ts b/app/api/glm.ts
new file mode 100644
index 000000000..8431c5db5
--- /dev/null
+++ b/app/api/glm.ts
@@ -0,0 +1,129 @@
+import { getServerSideConfig } from "@/app/config/server";
+import {
+ CHATGLM_BASE_URL,
+ ApiPath,
+ ModelProvider,
+ ServiceProvider,
+} from "@/app/constant";
+import { prettyObject } from "@/app/utils/format";
+import { NextRequest, NextResponse } from "next/server";
+import { auth } from "@/app/api/auth";
+import { isModelNotavailableInServer } from "@/app/utils/model";
+
+const serverConfig = getServerSideConfig();
+
+export async function handle(
+ req: NextRequest,
+ { params }: { params: { path: string[] } },
+) {
+ console.log("[GLM Route] params ", params);
+
+ if (req.method === "OPTIONS") {
+ return NextResponse.json({ body: "OK" }, { status: 200 });
+ }
+
+ const authResult = auth(req, ModelProvider.ChatGLM);
+ if (authResult.error) {
+ return NextResponse.json(authResult, {
+ status: 401,
+ });
+ }
+
+ try {
+ const response = await request(req);
+ return response;
+ } catch (e) {
+ console.error("[GLM] ", e);
+ return NextResponse.json(prettyObject(e));
+ }
+}
+
+async function request(req: NextRequest) {
+ const controller = new AbortController();
+
+ // alibaba use base url or just remove the path
+ let path = `${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/iflytek.ts b/app/api/iflytek.ts
index 8b8227dce..6624f74e9 100644
--- a/app/api/iflytek.ts
+++ b/app/api/iflytek.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";
// iflytek
const serverConfig = getServerSideConfig();
@@ -89,7 +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 5bf4807e3..792d14d33 100644
--- a/app/api/moonshot.ts
+++ b/app/api/moonshot.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.Moonshot as string,
diff --git a/app/api/openai.ts b/app/api/openai.ts
index bbba69e56..5bb3a5dcb 100644
--- a/app/api/openai.ts
+++ b/app/api/openai.ts
@@ -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"),
);
}
diff --git a/app/api/proxy.ts b/app/api/proxy.ts
index 731003aa1..b3e5e7b7b 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 ${serverConfig.apiKey}`);
+ }
+
const controller = new AbortController();
const fetchOptions: RequestInit = {
headers,
diff --git a/app/api/siliconflow.ts b/app/api/siliconflow.ts
new file mode 100644
index 000000000..e298a21d4
--- /dev/null
+++ b/app/api/siliconflow.ts
@@ -0,0 +1,128 @@
+import { getServerSideConfig } from "@/app/config/server";
+import {
+ SILICONFLOW_BASE_URL,
+ ApiPath,
+ ModelProvider,
+ ServiceProvider,
+} from "@/app/constant";
+import { prettyObject } from "@/app/utils/format";
+import { NextRequest, NextResponse } from "next/server";
+import { auth } from "@/app/api/auth";
+import { isModelNotavailableInServer } from "@/app/utils/model";
+
+const serverConfig = getServerSideConfig();
+
+export async function handle(
+ req: NextRequest,
+ { params }: { params: { path: string[] } },
+) {
+ console.log("[SiliconFlow Route] params ", params);
+
+ if (req.method === "OPTIONS") {
+ return NextResponse.json({ body: "OK" }, { status: 200 });
+ }
+
+ const authResult = auth(req, ModelProvider.SiliconFlow);
+ if (authResult.error) {
+ return NextResponse.json(authResult, {
+ status: 401,
+ });
+ }
+
+ try {
+ const response = await request(req);
+ return response;
+ } catch (e) {
+ console.error("[SiliconFlow] ", e);
+ return NextResponse.json(prettyObject(e));
+ }
+}
+
+async function request(req: NextRequest) {
+ const controller = new AbortController();
+
+ // alibaba use base url or just remove the path
+ let path = `${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 ${jsonBody?.model} model`,
+ },
+ {
+ status: 403,
+ },
+ );
+ }
+ } catch (e) {
+ console.error(`[SiliconFlow] filter`, e);
+ }
+ }
+ try {
+ const res = await fetch(fetchUrl, fetchOptions);
+
+ // to prevent browser prompt for credentials
+ const newHeaders = new Headers(res.headers);
+ newHeaders.delete("www-authenticate");
+ // to disable nginx buffering
+ newHeaders.set("X-Accel-Buffering", "no");
+
+ return new Response(res.body, {
+ status: res.status,
+ statusText: res.statusText,
+ headers: newHeaders,
+ });
+ } finally {
+ clearTimeout(timeoutId);
+ }
+}
diff --git a/app/api/xai.ts b/app/api/xai.ts
new file mode 100644
index 000000000..4aad5e5fb
--- /dev/null
+++ b/app/api/xai.ts
@@ -0,0 +1,128 @@
+import { getServerSideConfig } from "@/app/config/server";
+import {
+ XAI_BASE_URL,
+ ApiPath,
+ ModelProvider,
+ ServiceProvider,
+} from "@/app/constant";
+import { prettyObject } from "@/app/utils/format";
+import { NextRequest, NextResponse } from "next/server";
+import { auth } from "@/app/api/auth";
+import { isModelNotavailableInServer } from "@/app/utils/model";
+
+const serverConfig = getServerSideConfig();
+
+export async function handle(
+ req: NextRequest,
+ { params }: { params: { path: string[] } },
+) {
+ console.log("[XAI Route] params ", params);
+
+ if (req.method === "OPTIONS") {
+ return NextResponse.json({ body: "OK" }, { status: 200 });
+ }
+
+ const authResult = auth(req, ModelProvider.XAI);
+ if (authResult.error) {
+ return NextResponse.json(authResult, {
+ status: 401,
+ });
+ }
+
+ try {
+ const response = await request(req);
+ return response;
+ } catch (e) {
+ console.error("[XAI] ", e);
+ return NextResponse.json(prettyObject(e));
+ }
+}
+
+async function request(req: NextRequest) {
+ const controller = new AbortController();
+
+ // alibaba use base url or just remove the path
+ let path = `${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 7a242ea99..64ac82b2a 100644
--- a/app/client/api.ts
+++ b/app/client/api.ts
@@ -20,6 +20,10 @@ 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";
export const ROLES = ["system", "user", "assistant"] as const;
export type MessageRole = (typeof ROLES)[number];
@@ -68,7 +72,7 @@ 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;
@@ -152,6 +156,18 @@ 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;
default:
this.llm = new ChatGPTApi();
}
@@ -239,6 +255,11 @@ export function getHeaders(ignoreHeaders: boolean = false) {
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 isEnabledAccessControl = accessStore.enabledAccessControl();
const apiKey = isGoogle
? accessStore.googleApiKey
@@ -252,6 +273,14 @@ export function getHeaders(ignoreHeaders: boolean = false) {
? 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
@@ -266,6 +295,10 @@ export function getHeaders(ignoreHeaders: boolean = false) {
isAlibaba,
isMoonshot,
isIflytek,
+ isDeepSeek,
+ isXAI,
+ isChatGLM,
+ isSiliconFlow,
apiKey,
isEnabledAccessControl,
};
@@ -286,6 +319,14 @@ export function getHeaders(ignoreHeaders: boolean = false) {
isAzure,
isAnthropic,
isBaidu,
+ isByteDance,
+ isAlibaba,
+ isMoonshot,
+ isIflytek,
+ isDeepSeek,
+ isXAI,
+ isChatGLM,
+ isSiliconFlow,
apiKey,
isEnabledAccessControl,
} = getConfig();
@@ -328,6 +369,14 @@ 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);
default:
return new ClientApi(ModelProvider.GPT);
}
diff --git a/app/client/platforms/alibaba.ts b/app/client/platforms/alibaba.ts
index 86229a147..88511768c 100644
--- a/app/client/platforms/alibaba.ts
+++ b/app/client/platforms/alibaba.ts
@@ -1,12 +1,13 @@
"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 { streamWithThink } from "@/app/utils/chat";
import {
ChatOptions,
getHeaders,
@@ -15,14 +16,12 @@ import {
SpeechOptions,
MultimodalContent,
} 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,
+} from "@/app/utils";
import { fetch } from "@/app/utils/stream";
export interface OpenAIListModelResponse {
@@ -92,7 +91,10 @@ export class QwenApi implements LLMApi {
async chat(options: ChatOptions) {
const messages = options.messages.map((v) => ({
role: v.role,
- content: getMessageTextContent(v),
+ content:
+ v.role === "assistant"
+ ? getMessageTextContentWithoutThinking(v)
+ : getMessageTextContent(v),
}));
const modelConfig = {
@@ -122,139 +124,125 @@ export class QwenApi implements LLMApi {
options.onController?.(controller);
try {
+ const headers = {
+ ...getHeaders(),
+ "X-DashScope-SSE": shouldStream ? "enable" : "disable",
+ };
+
const chatPath = this.path(Alibaba.ChatPath);
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;
+ 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;
+ tool_calls: ChatMessageTool[];
+ reasoning_content: string | null;
+ };
+ }>;
- // 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 (!choices?.length) return { isThinking: false, content: "" };
- 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, {
- fetch: fetch as any,
- ...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 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;
+ }
}
+ 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: content,
+ };
}
+
+ return {
+ isThinking: false,
+ content: "",
+ };
},
- onclose() {
- finish();
+ // 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,
+ );
},
- onerror(e) {
- options.onError?.(e);
- throw e;
- },
- 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 1a83bd53a..6747221a8 100644
--- a/app/client/platforms/anthropic.ts
+++ b/app/client/platforms/anthropic.ts
@@ -13,6 +13,7 @@ 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";
@@ -316,13 +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);
diff --git a/app/client/platforms/baidu.ts b/app/client/platforms/baidu.ts
index 2511a696b..dc990db41 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";
@@ -23,7 +18,7 @@ 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 {
@@ -155,13 +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() {
@@ -191,7 +187,7 @@ export class ErnieApi implements LLMApi {
const finish = () => {
if (!finished) {
finished = true;
- options.onFinish(responseText + remainText);
+ options.onFinish(responseText + remainText, responseRes);
}
};
@@ -204,7 +200,7 @@ 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 +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 000a9e278..f9524cba2 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,
@@ -15,14 +16,14 @@ import {
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 {
@@ -34,7 +35,7 @@ export interface OpenAIListModelResponse {
}>;
}
-interface RequestPayload {
+interface RequestPayloadForByteDance {
messages: {
role: "system" | "user" | "assistant";
content: string | MultimodalContent[];
@@ -84,10 +85,14 @@ export class DoubaoApi implements LLMApi {
}
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,
@@ -98,7 +103,7 @@ export class DoubaoApi implements LLMApi {
};
const shouldStream = !!options.config.stream;
- const requestPayload: RequestPayload = {
+ const requestPayload: RequestPayloadForByteDance = {
messages,
stream: shouldStream,
model: modelConfig.model,
@@ -123,125 +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;
+ 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;
+ };
+ }>;
- // 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, {
- fetch: fetch as any,
- ...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();
+ 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();
+ 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.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();
+ // processToolMessage, include tool_calls message and tool call results
+ (
+ requestPayload: RequestPayloadForByteDance,
+ toolCallMessage: any,
+ toolCallResult: any[],
+ ) => {
+ requestPayload?.messages?.splice(
+ requestPayload?.messages?.length,
+ 0,
+ toolCallMessage,
+ ...toolCallResult,
+ );
},
- onerror(e) {
- options.onError?.(e);
- throw e;
- },
- 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 000000000..b21d24cef
--- /dev/null
+++ b/app/client/platforms/deepseek.ts
@@ -0,0 +1,234 @@
+"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