@lobehub/chat 1.99.1 → 1.99.3

package/docs/usage/providers/siliconcloud.zh-CN.mdx

@@ -28,7 +28,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置 SiliconCloud
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到 `SiliconFlow` 的设置项
+  - 在`AI 服务商`下找到 `SiliconFlow` 的设置项
 
   <Image alt={'填入 API 密钥'} inStep src={'https://github.com/user-attachments/assets/4c792f62-5203-4f13-8f23-df228f70d67f'} />
 

package/docs/usage/providers/spark.mdx

@@ -33,7 +33,7 @@ This guide will instruct you on how to use iFLYTEK Spark in LobeChat.
   ### Step 2: Configure iFLYTEK Spark in LobeChat
 
   - Access the `Settings` menu in LobeChat
-  - Find the iFLYTEK Spark settings under `Language Model`
+  - Find the iFLYTEK Spark settings under `AI Service Provider`
 
   <Image alt={'Enter API Key'} inStep src={'https://github.com/user-attachments/assets/d693be02-e08c-43ae-8bde-1294f180aaf6'} />
 

package/docs/usage/providers/spark.zh-CN.mdx

@@ -32,7 +32,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置讯飞星火
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到 `讯飞星火` 的设置项
+  - 在`AI 服务商`下找到 `讯飞星火` 的设置项
 
   <Image alt={'填入 API 密钥'} inStep src={'https://github.com/user-attachments/assets/d693be02-e08c-43ae-8bde-1294f180aaf6'} />
 

package/docs/usage/providers/stepfun.mdx

@@ -29,7 +29,7 @@ This document will guide you on how to use Stepfun in LobeChat:
   ### Step 2: Configure Stepfun in LobeChat
 
   - Visit the `Settings` interface in LobeChat
-  - Find the setting for Stepfun under `Language Models`
+  - Find the setting for Stepfun under `AI Service Provider`
 
   <Image alt={'Enter API Key'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/470e5669-650b-46cf-8024-a1476c166059'} />
 

package/docs/usage/providers/stepfun.zh-CN.mdx

@@ -27,7 +27,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置 Stepfun Stepfun 阶跃星辰
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到` Stepfun 阶跃星辰`的设置项
+  - 在`AI 服务商`下找到` Stepfun 阶跃星辰`的设置项
 
   <Image alt={'填写 API 密钥'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/470e5669-650b-46cf-8024-a1476c166059'} />
 

package/docs/usage/providers/taichu.mdx

@@ -27,7 +27,7 @@ This article will guide you on how to use Taichu in LobeChat:
   ### Step 2: Configure Taichu in LobeChat
 
   - Go to the `Settings` interface in LobeChat
-  - Find the setting for `Taichu` under `Language Model`
+  - Find the setting for `Taichu` under `AI Service Provider`
 
   <Image alt={'Enter API Key'} inStep src={'https://github.com/user-attachments/assets/55028fe5-44db-49e2-93c5-5dabbd664f10'} />
 

package/docs/usage/providers/taichu.zh-CN.mdx

@@ -26,7 +26,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置紫东太初
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到`紫东太初`的设置项
+  - 在`AI 服务商`下找到`紫东太初`的设置项
 
   <Image alt={'填入 API 密钥'} inStep src={'https://github.com/user-attachments/assets/55028fe5-44db-49e2-93c5-5dabbd664f10'} />
 

package/docs/usage/providers/togetherai.mdx

@@ -32,7 +32,7 @@ This document will guide you on how to use Together AI in LobeChat:
   ### Step 2: Configure Together AI in LobeChat
 
   - Visit the `Settings` interface in LobeChat
-  - Find the setting for `together.ai` under `Language Model`
+  - Find the setting for `together.ai` under `AI Service Provider`
 
   <Image alt={'Enter Together AI API key in LobeChat'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/0cc6c9b8-4688-472b-a80f-f84c5ebbc719'} />
 

package/docs/usage/providers/togetherai.zh-CN.mdx

@@ -31,7 +31,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置 Together AI
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到`together.ai`的设置项
+  - 在`AI 服务商`下找到`together.ai`的设置项
 
   <Image alt={'LobeChat 中填写 Together AI API 密钥'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/0cc6c9b8-4688-472b-a80f-f84c5ebbc719'} />
 

package/docs/usage/providers/upstage.mdx

@@ -29,7 +29,7 @@ This article will guide you on how to use Upstage in LobeChat.
   ### Step 2: Configure Upstage in LobeChat
 
   - Access the `Settings` interface in LobeChat
-  - Locate the `Upstage` settings under `Language Models`
+  - Locate the `Upstage` settings under `AI Service Provider`
 
   <Image alt={'Enter API Key'} inStep src={'https://github.com/user-attachments/assets/e89d2a56-4bf0-4bff-ac39-0d44789fa858'} />
 

package/docs/usage/providers/upstage.zh-CN.mdx

@@ -29,7 +29,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置 Upstage
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到 `Upstage` 的设置项
+  - 在`AI 服务商`下找到 `Upstage` 的设置项
 
   <Image alt={'填入 API 密钥'} inStep src={'https://github.com/user-attachments/assets/e89d2a56-4bf0-4bff-ac39-0d44789fa858'} />
 

package/docs/usage/providers/vllm.mdx

@@ -81,7 +81,7 @@ This document will guide you on how to use vLLM in LobeChat:
   ### Step 4: Configure vLLM in LobeChat
 
   - Access the `Application Settings` interface of LobeChat.
-  - Find the `vLLM` settings item under `Language Model`.
+  - Find the `vLLM` settings item under `AI Service Provider`.
 
   <Image alt={'Fill in the vLLM API Key'} inStep src={'https://github.com/user-attachments/assets/669c68bf-3f85-4a6f-bb08-d0d7fb7f7417'} />
 

package/docs/usage/providers/vllm.zh-CN.mdx

@@ -80,7 +80,7 @@ tags:
   ### 步骤四：在 LobeChat 中配置 vLLM
 
   - 访问 LobeChat 的 `应用设置`界面
-  - 在 `语言模型` 下找到 `vLLM` 的设置项
+  - 在 `AI 服务商` 下找到 `vLLM` 的设置项
 
   <Image alt={'填写 vLLM API 密钥'} inStep src={'https://github.com/user-attachments/assets/669c68bf-3f85-4a6f-bb08-d0d7fb7f7417'} />
 

package/docs/usage/providers/wenxin.mdx

@@ -41,7 +41,7 @@ This article will guide you on how to use Wenxin Qianfan in LobeChat.
   ### Step 2: Configure Wenxin Qianfan in LobeChat
 
   - Go to the `Settings` page of LobeChat
-  - Under `Language Models`, find the `Wenxin Qianfan` settings
+  - Under `AI Service Provider`, find the `Wenxin Qianfan` settings
 
   <Image alt={'Enter API Key'} inStep src={'https://github.com/user-attachments/assets/d7666e2a-0202-4b45-8338-9806ddffa44e'} />
 

package/docs/usage/providers/wenxin.zh-CN.mdx

@@ -39,7 +39,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置文心千帆
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到 `文心千帆` 的设置项
+  - 在`AI 服务商`下找到 `文心千帆` 的设置项
 
   <Image alt={'填入 API 密钥'} inStep src={'https://github.com/user-attachments/assets/d7666e2a-0202-4b45-8338-9806ddffa44e'} />
 

package/docs/usage/providers/xai.mdx

@@ -35,7 +35,7 @@ This article will guide you on how to use xAI in LobeChat.
   ### Step 2: Configure xAI in LobeChat
 
   - Go to the `Settings` menu in LobeChat
-  - Locate the `xAI` settings under `Language Model`
+  - Locate the `xAI` settings under `AI Service Provider`
 
   <Image alt={'Enter API Key'} inStep src={'https://github.com/user-attachments/assets/12863a0e-a1ee-406d-8dee-011b20701fd6'} />
 

package/docs/usage/providers/xai.zh-CN.mdx

@@ -32,7 +32,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置 xAI
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到 `xAI` 的设置项
+  - 在`AI 服务商`下找到 `xAI` 的设置项
 
   <Image alt={'填入 API 密钥'} inStep src={'https://github.com/user-attachments/assets/12863a0e-a1ee-406d-8dee-011b20701fd6'} />
 

package/docs/usage/providers/zeroone.mdx

@@ -39,7 +39,7 @@ This document will guide you on how to use 01 AI in LobeChat:
   ### Step 2: Configure 01 AI in LobeChat
 
   - Access the `Settings` interface in LobeChat
-  - Find the setting for `01 AI` under `Language Model`
+  - Find the setting for `01 AI` under `AI Service Provider`
 
   <Image alt={'Enter API Key'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/f539d104-6d64-4cc7-8781-3b36b00d32d0'} />
 

package/docs/usage/providers/zeroone.zh-CN.mdx

@@ -42,7 +42,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置零一万物
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到`零一万物`的设置项
+  - 在`AI 服务商`下找到`零一万物`的设置项
 
   <Image alt={'填入 API 密钥'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/f539d104-6d64-4cc7-8781-3b36b00d32d0'} />
 

package/docs/usage/providers/zhipu.mdx

@@ -30,7 +30,7 @@ This document will guide you on how to use Zhipu AI in LobeChat:
   ### Step 2: Configure Zhipu AI in LobeChat
 
   - Visit the `Settings` interface in LobeChat
-  - Under `Language Model`, locate the settings for Zhipu AI
+  - Under `AI Service Provider`, locate the settings for Zhipu AI
 
   <Image alt={'Enter Zhipu AI API Key in LobeChat'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/2afffe79-1d37-423c-9363-f09605d5e640'} />
 

package/docs/usage/providers/zhipu.zh-CN.mdx

@@ -28,7 +28,7 @@ tags:
   ### 步骤二：在 LobeChat 中配置智谱 AI
 
   - 访问 LobeChat 的`设置`界面
-  - 在`语言模型`下找到`智谱AI`的设置项
+  - 在`AI 服务商`下找到`智谱AI`的设置项
 
   <Image alt={'LobeChat 中填写智谱AI API 密钥'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/2afffe79-1d37-423c-9363-f09605d5e640'} />
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.99.1",
+  "version": "1.99.3",
   "description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",
@@ -210,7 +210,7 @@
     "mdast-util-to-markdown": "^2.1.2",
     "modern-screenshot": "^4.6.0",
     "nanoid": "^5.1.5",
-    "next": "^15.3.3",
+    "next": "~15.3.3",
     "next-auth": "5.0.0-beta.25",
     "next-mdx-remote": "^5.0.0",
     "nextjs-toploader": "^3.8.16",
@@ -326,7 +326,7 @@
     "crypto-js": "^4.2.0",
     "dbdocs": "^0.14.4",
     "dotenv": "^16.5.0",
-    "dpdm-fast": "^1.0.7",
+    "dpdm-fast": "1.0.7",
     "drizzle-dbml-generator": "^0.10.0",
     "drizzle-kit": "^0.31.0",
     "eslint": "^8.57.1",

package/src/app/[variants]/(main)/image/@menu/features/ConfigPanel/components/MultiImagesUpload/index.tsx

@@ -3,6 +3,7 @@
 // Removed Image import - using img tags instead
 import { createStyles, useTheme } from 'antd-style';
 import { Image as ImageIcon, X } from 'lucide-react';
+import Image from 'next/image';
 import React, { type FC, memo, useEffect, useRef, useState } from 'react';
 import { useTranslation } from 'react-i18next';
 import { Center } from 'react-layout-kit';
@@ -429,10 +430,12 @@ const ImageThumbnails: FC<ImageThumbnailsProps> = memo(({ images, onClick, onDel
 
     return (
       <div className={styles.imageItem} key={imageUrl}>
-        <img
+        <Image
           alt={`Uploaded image ${index + 1}`}
+          fill
           src={imageUrl}
-          style={{ height: '100%', objectFit: 'cover', width: '100%' }}
+          style={{ objectFit: 'cover' }}
+          unoptimized
         />
         {!showOverlay && (
           <div
@@ -478,10 +481,12 @@ const SingleImageDisplay: FC<SingleImageDisplayProps> = memo(({ imageUrl, onClic
 
   return (
     <div className={styles.singleImageDisplay}>
-      <img
+      <Image
         alt="Uploaded image"
+        fill
         src={imageUrl}
-        style={{ height: '100%', objectFit: 'cover', width: '100%' }}
+        style={{ objectFit: 'contain' }}
+        unoptimized
       />
 
       {/* Delete button */}

package/src/app/[variants]/(main)/image/@menu/features/ConfigPanel/index.tsx

@@ -26,7 +26,7 @@ interface ConfigItemLayoutProps {
 const ConfigItemLayout = memo<ConfigItemLayoutProps>(({ label, children }) => {
   return (
     <Flexbox gap={8}>
-      {label && <Text weight={500}>{label.toUpperCase()}</Text>}
+      {label && <Text weight={500}>{label}</Text>}
       {children}
     </Flexbox>
   );

package/src/app/[variants]/(main)/image/features/ImageWorkspace/EmptyState.tsx

@@ -1,4 +1,3 @@
-import { AuroraBackground } from '@lobehub/ui/awesome';
 import { memo } from 'react';
 import { Center, Flexbox } from 'react-layout-kit';
 
@@ -6,31 +5,18 @@ import PromptInput from '../PromptInput';
 
 const EmptyState = memo(() => {
   return (
-    <>
-      <AuroraBackground
-        style={{
-          height: 400,
-          inset: 0,
-          overflow: 'hidden',
-          pointerEvents: 'none',
-          position: 'absolute',
-          width: '100%',
-          zIndex: 0,
-        }}
-      />
-      <Flexbox
-        flex={1}
-        height="100%"
-        style={{
-          overflow: 'hidden',
-          zIndex: 1,
-        }}
-      >
-        <Center flex={1} padding={24}>
-          <PromptInput showTitle={true} />
-        </Center>
-      </Flexbox>
-    </>
+    <Flexbox
+      flex={1}
+      height="100%"
+      style={{
+        overflow: 'hidden',
+        zIndex: 1,
+      }}
+    >
+      <Center flex={1} padding={24}>
+        <PromptInput showTitle={true} />
+      </Center>
+    </Flexbox>
   );
 });
 

package/src/config/aiModels/openai.ts

@@ -835,11 +835,27 @@ export const openaiSTTModels: AISTTModelCard[] = [
 
 // 图像生成模型
 export const openaiImageModels: AIImageModelCard[] = [
+  // https://platform.openai.com/docs/models/gpt-image-1
+  {
+    description: 'ChatGPT 原生多模态图片生成模型',
+    displayName: 'GPT Image 1',
+    enabled: true,
+    id: 'gpt-image-1',
+    parameters: gptImage1ParamsSchema,
+    type: 'image',
+  },
   {
     description:
       '最新的 DALL·E 模型，于2023年11月发布。支持更真实、准确的图像生成，具有更强的细节表现力',
     displayName: 'DALL·E 3',
     id: 'dall-e-3',
+    parameters: {
+      prompt: { default: '' },
+      size: {
+        default: '1024x1024',
+        enum: ['1024x1024', '1792x1024', '1024x1792'],
+      },
+    },
     pricing: {
       hd: 0.08,
       standard: 0.04,
@@ -851,21 +867,20 @@ export const openaiImageModels: AIImageModelCard[] = [
     description: '第二代 DALL·E 模型，支持更真实、准确的图像生成，分辨率是第一代的4倍',
     displayName: 'DALL·E 2',
     id: 'dall-e-2',
+    parameters: {
+      imageUrl: { default: null },
+      prompt: { default: '' },
+      size: {
+        default: '1024x1024',
+        enum: ['256x256', '512x512', '1024x1024'],
+      },
+    },
     pricing: {
       input: 0.02, // $0.020 per image (1024×1024)
     },
     resolutions: ['256x256', '512x512', '1024x1024'],
     type: 'image',
   },
-  // https://platform.openai.com/docs/models/gpt-image-1
-  {
-    description: 'ChatGPT 原生多模态图片生成模型',
-    displayName: 'GPT Image 1',
-    enabled: true,
-    id: 'gpt-image-1',
-    parameters: gptImage1ParamsSchema,
-    type: 'image',
-  },
 ];
 
 // GPT-4o 和 GPT-4o-mini 实时模型

package/src/libs/model-runtime/BaseAI.ts

@@ -43,6 +43,7 @@ export abstract class LobeOpenAICompatibleRuntime {
   abstract client: OpenAI;
 
   abstract chat(payload: ChatStreamPayload, options?: ChatMethodOptions): Promise<Response>;
+  abstract createImage(payload: CreateImagePayload): Promise<CreateImageResponse>;
 
   abstract models(): Promise<ChatModelCard[]>;
 

package/src/libs/model-runtime/hunyuan/index.ts

@@ -12,7 +12,8 @@ export const LobeHunyuanAI = createOpenAICompatibleRuntime({
   chatCompletion: {
     handlePayload: (payload) => {
       // eslint-disable-next-line unused-imports/no-unused-vars, @typescript-eslint/no-unused-vars
-      const { enabledSearch, frequency_penalty, model, presence_penalty, thinking, ...rest } = payload;
+      const { enabledSearch, frequency_penalty, model, presence_penalty, thinking, ...rest } =
+        payload;
 
       return {
         ...rest,
@@ -30,11 +31,8 @@ export const LobeHunyuanAI = createOpenAICompatibleRuntime({
           search_info: true,
         }),
         ...(model === 'hunyuan-a13b' && {
-          enable_thinking: thinking?.type === 'enabled' 
-            ? true 
-            : thinking?.type === 'disabled' 
-              ? false 
-              : undefined
+          enable_thinking:
+            thinking?.type === 'enabled' ? true : thinking?.type === 'disabled' ? false : undefined,
         }),
       } as any;
     },

package/src/libs/model-runtime/novita/__snapshots__/index.test.ts.snap

@@ -11,6 +11,7 @@ exports[`NovitaAI > models > should get models 1`] = `
     "id": "meta-llama/llama-3-8b-instruct",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -22,6 +23,7 @@ exports[`NovitaAI > models > should get models 1`] = `
     "id": "meta-llama/llama-3-70b-instruct",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -33,6 +35,7 @@ exports[`NovitaAI > models > should get models 1`] = `
     "id": "meta-llama/llama-3.1-8b-instruct",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -44,6 +47,7 @@ exports[`NovitaAI > models > should get models 1`] = `
     "id": "meta-llama/llama-3.1-70b-instruct",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -55,6 +59,7 @@ exports[`NovitaAI > models > should get models 1`] = `
     "id": "meta-llama/llama-3.1-405b-instruct",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -67,6 +72,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "google/gemma-2-9b-it",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -78,6 +84,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "jondurbin/airoboros-l2-70b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -89,6 +96,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "nousresearch/hermes-2-pro-llama-3-8b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -100,6 +108,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "mistralai/mistral-7b-instruct",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -111,6 +120,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "cognitivecomputations/dolphin-mixtral-8x22b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -122,6 +132,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "sao10k/l3-70b-euryale-v2.1",
     "maxOutput": undefined,
     "reasoning": true,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -133,6 +144,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "sophosympatheia/midnight-rose-70b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -144,6 +156,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "gryphe/mythomax-l2-13b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -155,6 +168,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "nousresearch/nous-hermes-llama2-13b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -166,6 +180,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "Nous-Hermes-2-Mixtral-8x7B-DPO",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -177,6 +192,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "lzlv_70b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -188,6 +204,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "teknium/openhermes-2.5-mistral-7b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
   {
@@ -199,6 +216,7 @@ Designed for a wide variety of tasks, it empowers developers and researchers to
     "id": "microsoft/wizardlm-2-8x22b",
     "maxOutput": undefined,
     "reasoning": false,
+    "type": "chat",
     "vision": false,
   },
 ]