@lobehub/chat 1.74.0 → 1.74.2

package/CHANGELOG.md

@@ -2,6 +2,57 @@
 
 # Changelog
 
+### [Version 1.74.2](https://github.com/lobehub/lobe-chat/compare/v1.74.1...v1.74.2)
+
+<sup>Released on **2025-03-22**</sup>
+
+#### 🐛 Bug Fixes
+
+- **misc**: CheckModel change clears other configs, update input and output prices.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### What's fixed
+
+- **misc**: CheckModel change clears other configs, closes [#7083](https://github.com/lobehub/lobe-chat/issues/7083) ([a416c64](https://github.com/lobehub/lobe-chat/commit/a416c64))
+- **misc**: Update input and output prices, closes [#7094](https://github.com/lobehub/lobe-chat/issues/7094) ([460c56f](https://github.com/lobehub/lobe-chat/commit/460c56f))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.74.1](https://github.com/lobehub/lobe-chat/compare/v1.74.0...v1.74.1)
+
+<sup>Released on **2025-03-22**</sup>
+
+#### 💄 Styles
+
+- **misc**: Fix `deepseek-r1-70b-online` search tag missing from Search1API.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Fix `deepseek-r1-70b-online` search tag missing from Search1API, closes [#7085](https://github.com/lobehub/lobe-chat/issues/7085) ([0a06a7a](https://github.com/lobehub/lobe-chat/commit/0a06a7a))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ## [Version 1.74.0](https://github.com/lobehub/lobe-chat/compare/v1.73.2...v1.74.0)
 
 <sup>Released on **2025-03-21**</sup>

package/README.md

@@ -196,7 +196,7 @@ We have implemented support for the following model service providers:
 - **[OpenRouter](https://lobechat.com/discover/provider/openrouter)**: OpenRouter is a service platform providing access to various cutting-edge large model interfaces, supporting OpenAI, Anthropic, LLaMA, and more, suitable for diverse development and application needs. Users can flexibly choose the optimal model and pricing based on their requirements, enhancing the AI experience.
 - **[Cloudflare Workers AI](https://lobechat.com/discover/provider/cloudflare)**: Run serverless GPU-powered machine learning models on Cloudflare's global network.
 
-<details><summary><kbd>See more providers (+28)</kbd></summary>
+<details><summary><kbd>See more providers (+30)</kbd></summary>
 
 - **[GitHub](https://lobechat.com/discover/provider/github)**: With GitHub Models, developers can become AI engineers and leverage the industry's leading AI models.
 - **[Novita](https://lobechat.com/discover/provider/novita)**: Novita AI is a platform providing a variety of large language models and AI image generation API services, flexible, reliable, and cost-effective. It supports the latest open-source models like Llama3 and Mistral, offering a comprehensive, user-friendly, and auto-scaling API solution for generative AI application development, suitable for the rapid growth of AI startups.
@@ -226,11 +226,12 @@ We have implemented support for the following model service providers:
 - **[Gitee AI](https://lobechat.com/discover/provider/giteeai)**: Gitee AI's Serverless API provides AI developers with an out of the box large model inference API service.
 - **[Taichu](https://lobechat.com/discover/provider/taichu)**: The Institute of Automation, Chinese Academy of Sciences, and Wuhan Artificial Intelligence Research Institute have launched a new generation of multimodal large models, supporting comprehensive question-answering tasks such as multi-turn Q\&A, text creation, image generation, 3D understanding, and signal analysis, with stronger cognitive, understanding, and creative abilities, providing a new interactive experience.
 - **[360 AI](https://lobechat.com/discover/provider/ai360)**: 360 AI is an AI model and service platform launched by 360 Company, offering various advanced natural language processing models, including 360GPT2 Pro, 360GPT Pro, 360GPT Turbo, and 360GPT Turbo Responsibility 8K. These models combine large-scale parameters and multimodal capabilities, widely applied in text generation, semantic understanding, dialogue systems, and code generation. With flexible pricing strategies, 360 AI meets diverse user needs, supports developer integration, and promotes the innovation and development of intelligent applications.
-- **[Infini-AI](https://lobechat.com/discover/provider/infiniai)**: Infini-AI is a leading AI infrastructure enterprise in China, committed to becoming the preferred computing power operator in the large model era. Leveraging its core technological advantages of "multi-heterogeneous, software-hardware synergy," it has created a new "MxN" AI infrastructure paradigm connecting "M types of models" and "N types of chips," enabling efficient collaborative deployment of various large model algorithms on diverse chips. The Infini-AI heterogeneous cloud platform, based on a multi-chip computing foundation, provides large model developers with high-performance computing power and native toolchains with exceptional cost-effectiveness, reducing costs and improving efficiency throughout the entire lifecycle of large models from development to deployment.
+- **[Search1API](https://lobechat.com/discover/provider/search1api)**:
+- **[InfiniAI](https://lobechat.com/discover/provider/infiniai)**: Provides high-performance, easy-to-use, and secure large model services for application developers, covering the entire process from large model development to service deployment.
 
 </details>
 
-> 📊 Total providers: [<kbd>**38**</kbd>](https://lobechat.com/discover/providers)
+> 📊 Total providers: [<kbd>**40**</kbd>](https://lobechat.com/discover/providers)
 
  <!-- PROVIDER LIST -->
 
@@ -330,9 +331,9 @@ In addition, these plugins are not limited to news aggregation, but can also ext
 | [Web](https://lobechat.com/discover/plugin/web)<br/><sup>By **Proghit** on **2025-01-24**</sup>                              | Smart web search that reads and analyzes pages to deliver comprehensive answers from Google results.<br/>`web` `search` |
 | [MintbaseSearch](https://lobechat.com/discover/plugin/mintbasesearch)<br/><sup>By **mintbase** on **2024-12-31**</sup>       | Find any NFT data on the NEAR Protocol.<br/>`crypto` `nft`                                                              |
 | [Bing_websearch](https://lobechat.com/discover/plugin/Bingsearch-identifier)<br/><sup>By **FineHow** on **2024-12-22**</sup> | Search for information from the internet base BingApi<br/>`bingsearch`                                                  |
-| [PortfolioMeta](https://lobechat.com/discover/plugin/StockData)<br/><sup>By **portfoliometa** on **2024-12-22**</sup>        | Analyze stocks and get comprehensive real-time investment data and analytics.<br/>`stock`                               |
+| [Google CSE](https://lobechat.com/discover/plugin/google-cse)<br/><sup>By **vsnthdev** on **2024-12-02**</sup>               | Searches Google through their official CSE API.<br/>`web` `search`                                                      |
 
-> 📊 Total plugins: [<kbd>**46**</kbd>](https://lobechat.com/discover/plugins)
+> 📊 Total plugins: [<kbd>**45**</kbd>](https://lobechat.com/discover/plugins)
 
  <!-- PLUGIN LIST -->
 

package/README.zh-CN.md

@@ -196,7 +196,7 @@ LobeChat 支持文件上传与知识库功能，你可以上传文件、图片
 - **[OpenRouter](https://lobechat.com/discover/provider/openrouter)**: OpenRouter 是一个提供多种前沿大模型接口的服务平台，支持 OpenAI、Anthropic、LLaMA 及更多，适合多样化的开发和应用需求。用户可根据自身需求灵活选择最优的模型和价格，助力 AI 体验的提升。
 - **[Cloudflare Workers AI](https://lobechat.com/discover/provider/cloudflare)**: 在 Cloudflare 的全球网络上运行由无服务器 GPU 驱动的机器学习模型。
 
-<details><summary><kbd>See more providers (+28)</kbd></summary>
+<details><summary><kbd>See more providers (+30)</kbd></summary>
 
 - **[GitHub](https://lobechat.com/discover/provider/github)**: 通过 GitHub 模型，开发人员可以成为 AI 工程师，并使用行业领先的 AI 模型进行构建。
 - **[Novita](https://lobechat.com/discover/provider/novita)**: Novita AI 是一个提供多种大语言模型与 AI 图像生成的 API 服务的平台，灵活、可靠且具有成本效益。它支持 Llama3、Mistral 等最新的开源模型，并为生成式 AI 应用开发提供了全面、用户友好且自动扩展的 API 解决方案，适合 AI 初创公司的快速发展。
@@ -226,11 +226,12 @@ LobeChat 支持文件上传与知识库功能，你可以上传文件、图片
 - **[Gitee AI](https://lobechat.com/discover/provider/giteeai)**: Gitee AI 的 Serverless API 为 AI 开发者提供开箱即用的大模型推理 API 服务。
 - **[Taichu](https://lobechat.com/discover/provider/taichu)**: 中科院自动化研究所和武汉人工智能研究院推出新一代多模态大模型，支持多轮问答、文本创作、图像生成、3D 理解、信号分析等全面问答任务，拥有更强的认知、理解、创作能力，带来全新互动体验。
 - **[360 AI](https://lobechat.com/discover/provider/ai360)**: 360 AI 是 360 公司推出的 AI 模型和服务平台，提供多种先进的自然语言处理模型，包括 360GPT2 Pro、360GPT Pro、360GPT Turbo 和 360GPT Turbo Responsibility 8K。这些模型结合了大规模参数和多模态能力，广泛应用于文本生成、语义理解、对话系统与代码生成等领域。通过灵活的定价策略，360 AI 满足多样化用户需求，支持开发者集成，推动智能化应用的革新和发展。
-- **[Infini-AI](https://lobechat.com/discover/provider/infiniai)**: 无问芯穹 (InfinigenceAI) 作为国内领先的 AI 基础设施企业，致力于成为大模型时代首选的算力运营商。依托 “多元异构、软硬协同” 的核心技术优势，打造了连接 “M 种模型” 和 “N 种芯片” 的 “MxN” AI 基础设施新范式，实现多种大模型算法在多元芯片上的高效协同部署。无问芯穹 Infini-AI 异构云平台基于多元芯片算力底座，向大模型开发者提供极致性价比的高性能算力和原生工具链，为大模型从开发到部署的全生命流程降本增效。
+- **[Search1API](https://lobechat.com/discover/provider/search1api)**:
+- **[InfiniAI](https://lobechat.com/discover/provider/infiniai)**: 为应用开发者提供高性能、易上手、安全可靠的大模型服务，覆盖从大模型开发到大模型服务化部署的全流程。
 
 </details>
 
-> 📊 Total providers: [<kbd>**38**</kbd>](https://lobechat.com/discover/providers)
+> 📊 Total providers: [<kbd>**40**</kbd>](https://lobechat.com/discover/providers)
 
  <!-- PROVIDER LIST -->
 
@@ -323,9 +324,9 @@ LobeChat 的插件生态系统是其核心功能的重要扩展，它极大地
 | [网页](https://lobechat.com/discover/plugin/web)<br/><sup>By **Proghit** on **2025-01-24**</sup>                           | 智能网页搜索，读取和分析页面，以提供来自 Google 结果的全面答案。<br/>`网页` `搜索` |
 | [MintbaseSearch](https://lobechat.com/discover/plugin/mintbasesearch)<br/><sup>By **mintbase** on **2024-12-31**</sup>     | 在 NEAR 协议上查找任何 NFT 数据。<br/>`加密货币` `nft`                             |
 | [必应网页搜索](https://lobechat.com/discover/plugin/Bingsearch-identifier)<br/><sup>By **FineHow** on **2024-12-22**</sup> | 通过 BingApi 搜索互联网上的信息<br/>`bingsearch`                                   |
-| [PortfolioMeta](https://lobechat.com/discover/plugin/StockData)<br/><sup>By **portfoliometa** on **2024-12-22**</sup>      | 分析股票并获取全面的实时投资数据和分析。<br/>`股票`                                |
+| [谷歌自定义搜索引擎](https://lobechat.com/discover/plugin/google-cse)<br/><sup>By **vsnthdev** on **2024-12-02**</sup>     | 通过他们的官方自定义搜索引擎 API 搜索谷歌。<br/>`网络` `搜索`                      |
 
-> 📊 Total plugins: [<kbd>**46**</kbd>](https://lobechat.com/discover/plugins)
+> 📊 Total plugins: [<kbd>**45**</kbd>](https://lobechat.com/discover/plugins)
 
  <!-- PLUGIN LIST -->
 

package/changelog/v1.json

@@ -1,4 +1,22 @@
 [
+  {
+    "children": {
+      "fixes": [
+        "CheckModel change clears other configs, update input and output prices."
+      ]
+    },
+    "date": "2025-03-22",
+    "version": "1.74.2"
+  },
+  {
+    "children": {
+      "improvements": [
+        "Fix deepseek-r1-70b-online search tag missing from Search1API."
+      ]
+    },
+    "date": "2025-03-22",
+    "version": "1.74.1"
+  },
   {
     "children": {
       "features": [

package/docs/self-hosting/environment-variables/model-provider.mdx

@@ -580,6 +580,15 @@ If you need to use Azure OpenAI to provide model services, you can refer to the
 - Default: `-`
 - Example: `-all,+deepseek-r1->deepseek-r1-250120,+deepseek-v3->deepseek-v3-241226,+doubao-1.5-pro-256k->doubao-1-5-pro-256k-250115,+doubao-1.5-pro-32k->doubao-1-5-pro-32k-250115,+doubao-1.5-lite-32k->doubao-1-5-lite-32k-250115`
 
+### `VOLCENGINE_PROXY_URL`
+
+- Type: Optional
+- Description: If you manually configure the Volcengine API proxy, you can use this configuration item to override the default Volcengine API request base URL
+- Default: `https://ark.cn-beijing.volces.com/api/v3`
+- Example: `https://my-volcengine-proxy.com/v1`
+
+## InfiniAI
+
 ### `INFINIAI_API_KEY`
 
 - Type: Required
@@ -595,10 +604,3 @@ If you need to use Azure OpenAI to provide model services, you can refer to the
 - Example: `-all,+qwq-32b,+deepseek-r1`
 
 [model-list]: /docs/self-hosting/advanced/model-list
-
-### `VOLCENGINE_PROXY_URL`
-
-- Type: Optional
-- Description: If you manually configure the Volcengine API proxy, you can use this configuration item to override the default Volcengine API request base URL
-- Default: `https://ark.cn-beijing.volces.com/api/v3`
-- Example: `https://my-volcengine-proxy.com/v1`

package/docs/self-hosting/environment-variables/model-provider.zh-CN.mdx

@@ -579,6 +579,15 @@ LobeChat 在部署时提供了丰富的模型服务商相关的环境变量，
 - 默认值：`-`
 - 示例：`-all,+deepseek-r1->deepseek-r1-250120,+deepseek-v3->deepseek-v3-241226,+doubao-1.5-pro-256k->doubao-1-5-pro-256k-250115,+doubao-1.5-pro-32k->doubao-1-5-pro-32k-250115,+doubao-1.5-lite-32k->doubao-1-5-lite-32k-250115`
 
+### `VOLCENGINE_PROXY_URL`
+
+- 类型：可选
+- 描述：如果你手动配置了 Volcengine 接口代理，可以使用此配置项来覆盖默认的 Volcengine API 请求基础 URL
+- 默认值：`https://ark.cn-beijing.volces.com/api/v3`
+- 示例：`https://my-volcengine-proxy.com/v1`
+
+## InfiniAI
+
 ### `INFINIAI_API_KEY`
 
 - 类型：必选
@@ -594,10 +603,3 @@ LobeChat 在部署时提供了丰富的模型服务商相关的环境变量，
 - 示例：`-all,+qwq-32b,+deepseek-r1`
 
 [model-list]: /zh/docs/self-hosting/advanced/model-list
-
-### `VOLCENGINE_PROXY_URL`
-
-- 类型：可选
-- 描述：如果你手动配置了 Volcengine 接口代理，可以使用此配置项来覆盖默认的 Volcengine API 请求基础 URL
-- 默认值：`https://ark.cn-beijing.volces.com/api/v3`
-- 示例：`https://my-volcengine-proxy.com/v1`

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.74.0",
+  "version": "1.74.2",
   "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",

package/src/app/[variants]/(main)/settings/provider/features/ProviderConfig/Checker.tsx

@@ -59,6 +59,7 @@ const Checker = memo<ConnectionCheckerProps>(
     );
     const totalModels = useAiInfraStore(aiModelSelectors.aiProviderChatModelListIds);
     const updateAiProviderConfig = useAiInfraStore((s) => s.updateAiProviderConfig);
+    const currentConfig = useAiInfraStore(aiProviderSelectors.providerConfigById(provider));
 
     const [loading, setLoading] = useState(false);
     const [pass, setPass] = useState(false);
@@ -126,7 +127,10 @@ const Checker = memo<ConnectionCheckerProps>(
             listItemHeight={36}
             onSelect={async (value) => {
               setCheckModel(value);
-              await updateAiProviderConfig(provider, { checkModel: value });
+              await updateAiProviderConfig(provider, {
+                ...currentConfig,
+                checkModel: value,
+              });
             }}
             optionRender={({ value }) => {
               return (

package/src/config/aiModels/qwen.ts

@@ -16,8 +16,8 @@ const qwenChatModels: AIChatModelCard[] = [
     organization: 'Qwen',
     pricing: {
       currency: 'CNY',
-      input: 0,
-      output: 0,
+      input: 1.6,
+      output: 4,
     },
     releasedAt: '2025-03-06',
     settings: {
@@ -253,8 +253,8 @@ const qwenChatModels: AIChatModelCard[] = [
     organization: 'Qwen',
     pricing: {
       currency: 'CNY',
-      input: 0,
-      output: 0,
+      input: 2,
+      output: 6,
     },
     releasedAt: '2025-03-06',
     type: 'chat',

package/src/config/aiModels/search1api.ts

@@ -4,6 +4,7 @@ const search1apiChatModels: AIChatModelCard[] = [
   {
     abilities: {
       reasoning: true,
+      search: true,
     },
     contextWindowTokens: 131_072,
     description: 'DeepSeek R1 70B 标准版，支持实时联网搜索，适合需要最新信息的对话和文本处理任务。',
@@ -50,7 +51,7 @@ const search1apiChatModels: AIChatModelCard[] = [
     description:
       'DeepSeek R1 满血快速版，支持实时联网搜索，结合了 671B 参数的强大能力和更快的响应速度。',
     displayName: 'DeepSeek R1 Fast',
-    enabled: false,
+    enabled: true,
     id: 'deepseek-r1-fast-online',
     maxOutput: 16_384,
     type: 'chat',

package/src/config/aiModels/volcengine.ts

@@ -20,8 +20,8 @@ const doubaoChatModels: AIChatModelCard[] = [
     maxOutput: 8000,
     pricing: {
       currency: 'CNY',
-      input: 2, // 2.24 恢复原价 4, 16
-      output: 8,
+      input: 4,
+      output: 16,
     },
     type: 'chat',
   },