@lobehub/chat 1.68.3 → 1.68.5

package/CHANGELOG.md

@@ -2,6 +2,56 @@
 
 # Changelog
 
+### [Version 1.68.5](https://github.com/lobehub/lobe-chat/compare/v1.68.4...v1.68.5)
+
+<sup>Released on **2025-03-04**</sup>
+
+#### 💄 Styles
+
+- **misc**: Fix provider order.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Fix provider order, closes [#6702](https://github.com/lobehub/lobe-chat/issues/6702) ([27e4980](https://github.com/lobehub/lobe-chat/commit/27e4980))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.68.4](https://github.com/lobehub/lobe-chat/compare/v1.68.3...v1.68.4)
+
+<sup>Released on **2025-03-04**</sup>
+
+#### 💄 Styles
+
+- **misc**: Support to show token usages.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Support to show token usages, closes [#6693](https://github.com/lobehub/lobe-chat/issues/6693) ([71a638e](https://github.com/lobehub/lobe-chat/commit/71a638e))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.68.3](https://github.com/lobehub/lobe-chat/compare/v1.68.2...v1.68.3)
 
 <sup>Released on **2025-03-03**</sup>

package/README.md

@@ -191,7 +191,6 @@ We have implemented support for the following model service providers:
 - **[Bedrock](https://lobechat.com/discover/provider/bedrock)**: Bedrock is a service provided by Amazon AWS, focusing on delivering advanced AI language and visual models for enterprises. Its model family includes Anthropic's Claude series, Meta's Llama 3.1 series, and more, offering a range of options from lightweight to high-performance, supporting tasks such as text generation, conversation, and image processing for businesses of varying scales and needs.
 - **[Google](https://lobechat.com/discover/provider/google)**: Google's Gemini series represents its most advanced, versatile AI models, developed by Google DeepMind, designed for multimodal capabilities, supporting seamless understanding and processing of text, code, images, audio, and video. Suitable for various environments from data centers to mobile devices, it significantly enhances the efficiency and applicability of AI models.
 - **[DeepSeek](https://lobechat.com/discover/provider/deepseek)**: DeepSeek is a company focused on AI technology research and application, with its latest model DeepSeek-V2.5 integrating general dialogue and code processing capabilities, achieving significant improvements in human preference alignment, writing tasks, and instruction following.
-- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO supports stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc.
 - **[HuggingFace](https://lobechat.com/discover/provider/huggingface)**: The HuggingFace Inference API provides a fast and free way for you to explore thousands of models for various tasks. Whether you are prototyping for a new application or experimenting with the capabilities of machine learning, this API gives you instant access to high-performance models across multiple domains.
 - **[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.
@@ -199,6 +198,7 @@ We have implemented support for the following model service providers:
 <details><summary><kbd>See more providers (+27)</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.
+- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO supports stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc.
 - **[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.
 - **[Together AI](https://lobechat.com/discover/provider/togetherai)**: Together AI is dedicated to achieving leading performance through innovative AI models, offering extensive customization capabilities, including rapid scaling support and intuitive deployment processes to meet various enterprise needs.
 - **[Fireworks AI](https://lobechat.com/discover/provider/fireworksai)**: Fireworks AI is a leading provider of advanced language model services, focusing on functional calling and multimodal processing. Its latest model, Firefunction V2, is based on Llama-3, optimized for function calling, conversation, and instruction following. The visual language model FireLLaVA-13B supports mixed input of images and text. Other notable models include the Llama series and Mixtral series, providing efficient multilingual instruction following and generation support.
@@ -570,7 +570,7 @@ $ mkdir lobe-chat-db && cd lobe-chat-db
 2. init the LobeChat infrastructure
 
 ```fish
-bash <(curl -fsSL https://lobe.li/setup.sh) -l zh_CN
+bash <(curl -fsSL https://lobe.li/setup.sh)
 ```
 
 3. Start the LobeChat service
@@ -799,7 +799,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
 [docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square&sort=semver
 [docs]: https://lobehub.com/docs/usage/start
 [docs-dev-guide]: https://github.com/lobehub/lobe-chat/wiki/index
-[docs-docker]: https://lobehub.com/docs/self-hosting/platform/docker
+[docs-docker]: https://lobehub.com/docs/self-hosting/server-database/docker-compose
 [docs-env-var]: https://lobehub.com/docs/self-hosting/environment-variables
 [docs-feat-agent]: https://lobehub.com/docs/usage/features/agent-market
 [docs-feat-artifacts]: https://lobehub.com/docs/usage/features/artifacts

package/README.zh-CN.md

@@ -191,7 +191,6 @@ LobeChat 支持文件上传与知识库功能，你可以上传文件、图片
 - **[Bedrock](https://lobechat.com/discover/provider/bedrock)**: Bedrock 是亚马逊 AWS 提供的一项服务，专注于为企业提供先进的 AI 语言模型和视觉模型。其模型家族包括 Anthropic 的 Claude 系列、Meta 的 Llama 3.1 系列等，涵盖从轻量级到高性能的多种选择，支持文本生成、对话、图像处理等多种任务，适用于不同规模和需求的企业应用。
 - **[Google](https://lobechat.com/discover/provider/google)**: Google 的 Gemini 系列是其最先进、通用的 AI 模型，由 Google DeepMind 打造，专为多模态设计，支持文本、代码、图像、音频和视频的无缝理解与处理。适用于从数据中心到移动设备的多种环境，极大提升了 AI 模型的效率与应用广泛性。
 - **[DeepSeek](https://lobechat.com/discover/provider/deepseek)**: DeepSeek 是一家专注于人工智能技术研究和应用的公司，其最新模型 DeepSeek-V3 多项评测成绩超越 Qwen2.5-72B 和 Llama-3.1-405B 等开源模型，性能对齐领军闭源模型 GPT-4o 与 Claude-3.5-Sonnet。
-- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO 派欧云提供稳定、高性价比的开源模型 API 服务，支持 DeepSeek 全系列、Llama、Qwen 等行业领先大模型。
 - **[HuggingFace](https://lobechat.com/discover/provider/huggingface)**: HuggingFace Inference API 提供了一种快速且免费的方式，让您可以探索成千上万种模型，适用于各种任务。无论您是在为新应用程序进行原型设计，还是在尝试机器学习的功能，这个 API 都能让您即时访问多个领域的高性能模型。
 - **[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。
@@ -199,6 +198,7 @@ LobeChat 支持文件上传与知识库功能，你可以上传文件、图片
 <details><summary><kbd>See more providers (+27)</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。
+- **[PPIO](https://lobechat.com/discover/provider/ppio)**: PPIO 派欧云提供稳定、高性价比的开源模型 API 服务，支持 DeepSeek 全系列、Llama、Qwen 等行业领先大模型。
 - **[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。
 - **[Together AI](https://lobechat.com/discover/provider/togetherai)**: Together AI 致力于通过创新的 AI 模型实现领先的性能，提供广泛的自定义能力，包括快速扩展支持和直观的部署流程，满足企业的各种需求。
 - **[Fireworks AI](https://lobechat.com/discover/provider/fireworksai)**: Fireworks AI 是一家领先的高级语言模型服务商，专注于功能调用和多模态处理。其最新模型 Firefunction V2 基于 Llama-3，优化用于函数调用、对话及指令跟随。视觉语言模型 FireLLaVA-13B 支持图像和文本混合输入。其他 notable 模型包括 Llama 系列和 Mixtral 系列，提供高效的多语言指令跟随与生成支持。
@@ -541,27 +541,24 @@ LobeChat 提供了 Vercel 的 自托管版本 和 [Docker 镜像][docker-release
 [![][docker-size-shield]][docker-size-link]
 [![][docker-pulls-shield]][docker-pulls-link]
 
-我们提供了 Docker 镜像，供你在自己的私有设备上部署 LobeChat 服务。使用以下命令即可使用一键启动 LobeChat 服务：
+We provide a Docker image for deploying the LobeChat service on your own private device. Use the following command to start the LobeChat service:
+
+1. create a folder to for storage files
 
 ```fish
-$ docker run -d -p 3210:3210 \
-  -e OPENAI_API_KEY=sk-xxxx \
-  -e ACCESS_CODE=lobe66 \
-  --name lobe-chat \
-  lobehub/lobe-chat
+$ mkdir lobe-chat-db && cd lobe-chat-db
 ```
 
-> \[!TIP]
->
-> 如果你需要通过代理使用 OpenAI 服务，你可以使用 `OPENAI_PROXY_URL` 环境变量来配置代理地址：
+2. 启动一键脚本
+
+```fish
+bash <(curl -fsSL https://lobe.li/setup.sh) -l zh_CN
+```
+
+3. 启动 LobeChat
 
 ```fish
-$ docker run -d -p 3210:3210 \
-  -e OPENAI_API_KEY=sk-xxxx \
-  -e OPENAI_PROXY_URL=https://api-proxy.com/v1 \
-  -e ACCESS_CODE=lobe66 \
-  --name lobe-chat \
-  lobehub/lobe-chat
+docker compose up -d
 ```
 
 > \[!NOTE]
@@ -822,7 +819,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
 [docker-size-shield]: https://img.shields.io/docker/image-size/lobehub/lobe-chat-database?color=369eff&labelColor=black&style=flat-square&sort=semver
 [docs]: https://lobehub.com/zh/docs/usage/start
 [docs-dev-guide]: https://github.com/lobehub/lobe-chat/wiki/index
-[docs-docker]: https://lobehub.com/docs/self-hosting/platform/docker
+[docs-docker]: https://lobehub.com/zh/docs/self-hosting/server-database/docker-compose
 [docs-env-var]: https://lobehub.com/docs/self-hosting/environment-variables
 [docs-feat-agent]: https://lobehub.com/docs/usage/features/agent-market
 [docs-feat-artifacts]: https://lobehub.com/docs/usage/features/artifacts

package/changelog/v1.json

@@ -1,4 +1,22 @@
 [
+  {
+    "children": {
+      "improvements": [
+        "Fix provider order."
+      ]
+    },
+    "date": "2025-03-04",
+    "version": "1.68.5"
+  },
+  {
+    "children": {
+      "improvements": [
+        "Support to show token usages."
+      ]
+    },
+    "date": "2025-03-04",
+    "version": "1.68.4"
+  },
   {
     "children": {
       "fixes": [

package/docs/usage/providers/azureai.mdx

@@ -0,0 +1,69 @@
+---
+title: Using Azure AI API Key in LobeChat
+description: Learn how to configure and use Azure AI models in LobeChat, get the API key, and start a conversation.
+tags:
+  - LobeChat
+  - Azure AI
+  - API Key
+  - Web UI
+---
+
+# Using Azure AI in LobeChat
+
+<Image alt={'Using Azure AI in LobeChat'} cover src={'https://github.com/user-attachments/assets/81d0349a-44fe-4dfc-bbc4-8e9a1e09567d'} />
+
+[Azure AI](https://azure.microsoft.com) is an open artificial intelligence technology platform based on the Microsoft Azure cloud platform. It provides various AI functionalities, including natural language processing, machine learning, and computer vision, helping businesses easily develop and deploy AI applications.
+
+This document will guide you on how to integrate Azure AI models into LobeChat:
+
+<Steps>
+  ### Step 1: Deploy Azure AI Project and Model
+
+  - First, visit [Azure AI Foundry](https://ai.azure.com/) and complete the registration and login process.
+  - After logging in, select `Browse models` on the homepage.
+
+  <Image alt={'Accessing Azure AI Foundry'} inStep src={'https://github.com/user-attachments/assets/1c6a3e42-8e24-4148-b2c3-0bfe60a8cf77'} />
+
+  - Choose the model you want in the model marketplace.
+  - Enter the model details and click the `Deploy` button.
+
+  <Image alt={'Browsing Models'} inStep src={'https://github.com/user-attachments/assets/3ed3226c-3d4c-49ef-b2c0-8953dac8a92e'} />
+
+  - In the pop-up dialog, create a new project.
+
+  <Image alt={'Creating a New Project'} inStep src={'https://github.com/user-attachments/assets/199b862a-5de4-4a54-83b2-f4dbf69be902'} />
+
+  <Callout type={'note'}>
+    For detailed configuration of Azure AI Foundry, please refer to the [official documentation](https://learn.microsoft.com/azure/ai-foundry/model-inference/).
+  </Callout>
+
+  ### Step 2: Obtain the Model's API Key and Endpoint
+
+  - In the details of the deployed model, you can find the Endpoint and API Key information.
+  - Copy and save the obtained information.
+
+  <Image alt={'Obtaining API Key'} inStep src={'https://github.com/user-attachments/assets/30c33426-412d-4dec-b096-317fe5880e79'} />
+
+  ### Step 3: Configure Azure AI in LobeChat
+
+  - Visit the `App Settings` and `AI Service Provider` interface in LobeChat.
+  - Find the settings for `Azure AI` in the list of providers.
+
+  <Image alt={'Entering Azure AI API Key'} inStep src={'https://github.com/user-attachments/assets/eb41f77f-ccdd-4a48-a8a2-7badac868c03'} />
+
+  - Enable the Azure AI service provider and fill in the obtained Endpoint and API Key.
+
+  <Callout type={'warning'}>
+    For the Endpoint, you only need to fill in the first part: `https://xxxxxx.services.ai.azure.com/models`.
+  </Callout>
+
+  - Choose an Azure AI model for your assistant and start the conversation.
+
+  <Image alt={'Selecting Azure AI Model'} inStep src={'https://github.com/user-attachments/assets/a1ba8ec0-e259-4da4-8980-0cf82ca5f52b'} />
+
+  <Callout type={'warning'}>
+    You may need to pay the API service provider for usage. Please refer to Azure AI's relevant pricing policies.
+  </Callout>
+</Steps>
+
+Now you can use the models provided by Azure AI in LobeChat for conversations.

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

@@ -0,0 +1,69 @@
+---
+title: 在 LobeChat 中使用 Azure AI API Key
+description: 学习如何在 LobeChat 中配置和使用 Azure AI 模型，获取 API 密钥并开始对话。
+tags:
+  - LobeChat
+  - Azure AI
+  - API密钥
+  - Web UI
+---
+
+# 在 LobeChat 中使用 Azure AI
+
+<Image alt={'在 LobeChat 中使用 Azure AI '} cover src={'https://github.com/user-attachments/assets/81d0349a-44fe-4dfc-bbc4-8e9a1e09567d'} />
+
+[Azure AI](https://azure.microsoft.com) 是一个基于 Microsoft Azure 云平台的开放式人工智能技术平台，提供包括自然语言处理、机器学习、计算机视觉等多种 AI 功能，帮助企业轻松开发和部署 AI 应用。
+
+本文档将指导你如何在 LobeChat 中接入 Azure AI 的模型:
+
+<Steps>
+  ### 步骤一：部署 Azure AI 项目以及模型
+
+  - 首先，访问[Azure AI Foundry](https://ai.azure.com/)并完成注册登录
+  - 登录后在首页选择`浏览模型`
+
+  <Image alt={'进入 Azure AI Foundry'} inStep src={'https://github.com/user-attachments/assets/1c6a3e42-8e24-4148-b2c3-0bfe60a8cf77'} />
+
+  - 在模型广场中选择你想要模型
+  - 进入模型详情，点击`部署`按钮
+
+  <Image alt={'浏览模型'} inStep src={'https://github.com/user-attachments/assets/3ed3226c-3d4c-49ef-b2c0-8953dac8a92e'} />
+
+  - 在弹出的对话框中创建一个新的项目
+
+  <Image alt={'创建新项目'} inStep src={'https://github.com/user-attachments/assets/199b862a-5de4-4a54-83b2-f4dbf69be902'} />
+
+  <Callout type={'note'}>
+    Azure AI Foundry 的详细配置请参考[官方文档](https://learn.microsoft.com/azure/ai-foundry/model-inference/)
+  </Callout>
+
+  ### 步骤二：获取模型的 API Key 及 Endpoint
+
+  - 在已部署的模型详情里，可以查询到 Endpoint 以及 API Key 信息
+  - 复制并保存好获取的信息
+
+  <Image alt={'获取 API Key'} inStep src={'https://github.com/user-attachments/assets/30c33426-412d-4dec-b096-317fe5880e79'} />
+
+  ### 步骤三：在 LobeChat 中配置 Azure AI
+
+  - 访问 LobeChat 的 `应用设置` 的 `AI 服务供应商` 界面
+  - 在供应商列表中找到 `Azure AI` 的设置项
+
+  <Image alt={'填写 Azure AI  API 密钥'} inStep src={'https://github.com/user-attachments/assets/eb41f77f-ccdd-4a48-a8a2-7badac868c03'} />
+
+  - 打开 Azure AI 服务商并填入获取的 Endpoint 以及 API 密钥
+
+  <Callout type={'warning'}>
+    Endpoint 只需要填入前面部分 `https://xxxxxx.services.ai.azure.com/models` 即可
+  </Callout>
+
+  - 为你的助手选择一个 Azure AI 模型即可开始对话
+
+  <Image alt={'选择 Azure AI 模型'} inStep src={'https://github.com/user-attachments/assets/a1ba8ec0-e259-4da4-8980-0cf82ca5f52b'} />
+
+  <Callout type={'warning'}>
+    在使用过程中你可能需要向 API 服务提供商付费，请参考 Azure AI 的相关费用政策。
+  </Callout>
+</Steps>
+
+至此你已经可以在 LobeChat 中使用 Azure AI 提供的模型进行对话了。

package/docs/usage/providers/deepseek.mdx

@@ -15,7 +15,7 @@ tags:
 
 <Image alt={'Using DeepSeek in LobeChat'} cover src={'https://github.com/lobehub/lobe-chat/assets/34400653/b4d12904-9d5d-46de-bd66-901eeb9c8e52'} />
 
-[DeepSeek](https://www.deepseek.com/) is an advanced open-source Large Language Model (LLM). The latest version, DeepSeek-V2, has made significant optimizations in architecture and performance, reducing training costs by 42.5% and inference costs by 93.3%.
+[DeepSeek](https://www.deepseek.com/) represents a cutting-edge open-source large language model. The latest versions, DeepSeek-V3 and DeepSeek-R1, have undergone substantial improvements in both architecture and performance, particularly shining in their inference capabilities. By leveraging innovative training methodologies and reinforcement learning, the model has effectively boosted its inference prowess, now nearly matching the pinnacle performance of OpenAI.
 
 This document will guide you on how to use DeepSeek in LobeChat:
 
@@ -48,12 +48,12 @@ This document will guide you on how to use DeepSeek in LobeChat:
   - Access the `App Settings` interface in LobeChat.
   - Find the setting for `DeepSeek` under `Language Models`.
 
-  <Image alt={'Enter Deepseek API Key'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/bae262d6-0d49-47f3-bc9c-356cf6f3f34e'} />
+  <Image alt={'Enter Deepseek API Key'} inStep src={'https://github.com/user-attachments/assets/aaa3e2c5-7f16-4cfb-86b6-2814a1aafe3a'} />
 
   - Open DeepSeek and enter the obtained API key.
   - Choose a DeepSeek model for your assistant to start the conversation.
 
-  <Image alt={'Select Deepseek Model'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/84568505-6efe-4518-8888-682ccdd92197'} />
+  <Image alt={'Select Deepseek Model'} inStep src={'https://github.com/user-attachments/assets/84a5c971-1262-4639-b79f-c8b138530803'} />
 
   <Callout type={'warning'}>
     You may need to pay the API service provider during usage, please refer to DeepSeek's relevant

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

@@ -4,6 +4,7 @@ description: 学习如何在 LobeChat 中配置和使用 DeepSeek 语言模型
 tags:
   - LobeChat
   - DeepSeek
+  - DeepSeek R1
   - API密钥
   - Web UI
 ---
@@ -12,9 +13,9 @@ tags:
 
 <Image alt={'在 LobeChat 中使用 DeepSeek'} cover src={'https://github.com/lobehub/lobe-chat/assets/34400653/b4d12904-9d5d-46de-bd66-901eeb9c8e52'} />
 
-[DeepSeek](https://www.deepseek.com/) 是一款先进的开源大型语言模型（LLM）。最新版本 DeepSeek-V2 在架构和性能上进行了显著优化，同时训练成本降低了 42.5%, 推理成本降低了 93.3%。
+[DeepSeek](https://www.deepseek.com/) 是一款先进的开源大型语言模型（LLM）。最新的 DeepSeek-V3 和 DeepSeek-R1 在架构和性能上进行了显著优化，特别是在推理能力方面表现出色。它通过创新性的训练方法和强化学习技术，成功地提升了模型的推理能力，并且其性能已逼近 OpenAI 的顶尖水平。
 
-本文档将指导你如何在 LobeChat 中使用 DeepSeek:
+本文档将指导你如何在 LobeChat 中使用 DeepSeek：
 
 <Steps>
   ### 步骤一：获取 DeepSeek API 密钥
@@ -44,12 +45,12 @@ tags:
   - 访问 LobeChat 的 `应用设置`界面
   - 在 `语言模型` 下找到 `DeepSeek` 的设置项
 
-  <Image alt={'填写 Deepseek API 密钥'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/bae262d6-0d49-47f3-bc9c-356cf6f3f34e'} />
+  <Image alt={'填写 Deepseek API 密钥'} inStep src={'https://github.com/user-attachments/assets/aaa3e2c5-7f16-4cfb-86b6-2814a1aafe3a'} />
 
   - 打开 DeepSeek 并填入获取的 API 密钥
   - 为你的助手选择一个 DeepSeek 模型即可开始对话
 
-  <Image alt={'选择 Deepseek 模型'} inStep src={'https://github.com/lobehub/lobe-chat/assets/34400653/84568505-6efe-4518-8888-682ccdd92197'} />
+  <Image alt={'选择 Deepseek 模型'} inStep src={'https://github.com/user-attachments/assets/84a5c971-1262-4639-b79f-c8b138530803'} />
 
   <Callout type={'warning'}>
     在使用过程中你可能需要向 API 服务提供商付费，请参考 DeepSeek 的相关费用政策。

package/docs/usage/providers/jina.mdx

@@ -0,0 +1,51 @@
+---
+title: Using Jina AI API Key in LobeChat
+description: Learn how to configure and use Jina AI models in LobeChat, obtain an API key, and start conversations.
+tags:
+  - LobeChat
+  - Jina AI
+  - API Key
+  - Web UI
+---
+
+# Using Jina AI in LobeChat
+
+<Image alt={'Using Jina AI in LobeChat'} cover src={'https://github.com/user-attachments/assets/840442b1-bf56-4a5f-9700-b3608b16a8a5'} />
+
+[Jina AI](https://jina.ai/) is an open-source neural search company founded in 2020. It focuses on using deep learning technology to process multimodal data, providing efficient information retrieval solutions and supporting search for various data types such as text, images, and videos.
+
+This document will guide you on how to use Jina AI in LobeChat:
+
+<Steps>
+  ### Step 1: Obtain a Jina AI API Key
+
+  - Visit the [Jina AI official website](https://jina.ai/) and click the `API` button on the homepage.
+
+  <Image alt={'Obtain a Jina AI API Key'} inStep src={'https://github.com/user-attachments/assets/5ea37821-4ea8-437c-a15e-3b182d10f19e'} />
+
+  - Find the API Key generated for you in the `API Key` menu below.
+  - Copy and save the generated API Key.
+
+  <Callout type={'info'}>
+    * Jina AI provides each user with 1M free API Tokens, and the API can be used without registration.
+    * If you need to manage the API Key or recharge the API, you need to register and log in to the [Jina AI Console](https://jina.ai/api-dashboard/).
+  </Callout>
+
+  ### Step 2: Configure Jina AI in LobeChat
+
+  - Visit LobeChat's `Application Settings` interface.
+  - Find the `Jina AI` setting under `Language Model`.
+
+  <Image alt={'Fill in Jina AI API Key'} inStep src={'https://github.com/user-attachments/assets/1077bee5-b379-4063-b7bd-23b98ec146e2'} />
+
+  - Enable Jina AI and fill in the obtained API Key.
+  - Select a Jina AI model for your assistant and start the conversation.
+
+  <Image alt={'Select Jina AI Model'} inStep src={'https://github.com/user-attachments/assets/be06e348-8d4c-440c-b59f-b71120f21335'} />
+
+  <Callout type={'warning'}>
+    You may need to pay the API service provider during use. Please refer to Jina AI's relevant fee policy.
+  </Callout>
+</Steps>
+
+Now you can use the models provided by Jina AI in LobeChat to have conversations.

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

@@ -0,0 +1,51 @@
+---
+title: 在 LobeChat 中使用 Jina AI API Key
+description: 学习如何在 LobeChat 中配置和使用 Jina AI 模型，获取 API 密钥并开始对话。
+tags:
+  - LobeChat
+  - Jina AI
+  - API密钥
+  - Web UI
+---
+
+# 在 LobeChat 中使用 Jina AI
+
+<Image alt={'在 LobeChat 中使用 Jina AI'} cover src={'https://github.com/user-attachments/assets/840442b1-bf56-4a5f-9700-b3608b16a8a5'} />
+
+[Jina AI](https://jina.ai/) 是一家成立于 2020 年的开源神经搜索公司，专注于利用深度学习技术处理多模态数据，提供高效的信息检索解决方案，支持文本、图像、视频等多种数据类型的搜索。
+
+本文档将指导你如何在 LobeChat 中使用 Jina AI:
+
+<Steps>
+  ### 步骤一：获取 Jina AI API 密钥
+
+  - 访问 [Jina AI 官方网站](https://jina.ai/)，点击首页的 `API` 按钮
+
+  <Image alt={'获取 Jina AI API 密钥'} inStep src={'https://github.com/user-attachments/assets/5ea37821-4ea8-437c-a15e-3b182d10f19e'} />
+
+  - 在下方的 `API Key` 菜单中找到系统为你生成的 API Key
+  - 复制并保存生成的 API Key
+
+  <Callout type={'info'}>
+    * Jina AI 会为每个用户提供 1M 免费的 API Token，无需注册即可使用 API
+    * 如果需要管理 API Key，或为 API 充值，你需要注册并登录 [Jina AI 控制台](https://jina.ai/api-dashboard/)
+  </Callout>
+
+  ### 步骤二：在 LobeChat 中配置 Jina AI
+
+  - 访问 LobeChat 的 `应用设置`界面
+  - 在 `语言模型` 下找到 `Jina AI` 的设置项
+
+  <Image alt={'填写 Jina AI API 密钥'} inStep src={'https://github.com/user-attachments/assets/1077bee5-b379-4063-b7bd-23b98ec146e2'} />
+
+  - 打开 Jina AI 并填入获取的 API 密钥
+  - 为你的助手选择一个 Jina AI 模型即可开始对话
+
+  <Image alt={'选择 Jina AI 模型'} inStep src={'https://github.com/user-attachments/assets/be06e348-8d4c-440c-b59f-b71120f21335'} />
+
+  <Callout type={'warning'}>
+    在使用过程中你可能需要向 API 服务提供商付费，请参考 Jina AI 的相关费用政策。
+  </Callout>
+</Steps>
+
+至此你已经可以在 LobeChat 中使用 Jina AI 提供的模型进行对话了。

package/docs/usage/providers/lmstudio.mdx

@@ -0,0 +1,75 @@
+---
+title: Using LM Studio in LobeChat
+description: Learn how to configure and use LM Studio, and run AI models for conversations in LobeChat through LM Studio.
+tags:
+  - LobeChat
+  - LM Studio
+  - Open Source Model
+  - Web UI
+---
+
+# Using LM Studio in LobeChat
+
+<Image alt={'Using LM Studio in LobeChat'} cover src={'https://github.com/user-attachments/assets/cc1f6146-8063-4a4d-947a-7fd6b9133c0c'} />
+
+[LM Studio](https://lmstudio.ai/) is a platform for testing and running large language models (LLMs), providing an intuitive and easy-to-use interface suitable for developers and AI enthusiasts. It supports deploying and running various open-source LLM models, such as Deepseek or Qwen, on local computers, enabling offline AI chatbot functionality, thereby protecting user privacy and providing greater flexibility.
+
+This document will guide you on how to use LM Studio in LobeChat:
+
+<Steps>
+  ### Step 1: Obtain and Install LM Studio
+
+  - Go to the [LM Studio official website](https://lmstudio.ai/)
+  - Choose your platform and download the installation package. LM Studio currently supports MacOS, Windows, and Linux platforms.
+  - Follow the prompts to complete the installation and run LM Studio.
+
+  <Image alt={'Install and run LM Studio'} inStep src={'https://github.com/user-attachments/assets/e887fa04-c553-45f1-917f-5c123ac9c68b'} />
+
+  ### Step 2: Search and Download Models
+
+  - Open the `Discover` menu on the left, search for and download the model you want to use.
+  - Find a suitable model (such as Deepseek R1) and click download.
+  - The download may take some time, please wait patiently for it to complete.
+
+  <Image alt={'Search and download models'} inStep src={'https://github.com/user-attachments/assets/f878355f-710b-452e-8606-0c75c47f29d2'} />
+
+  ### Step 3: Deploy and Run Models
+
+  - Select the downloaded model in the top model selection bar and load the model.
+  - Configure the model runtime parameters in the pop-up panel. Refer to the [LM Studio official documentation](https://lmstudio.ai/docs) for detailed parameter settings.
+
+  <Image alt={'Configure model runtime parameters'} inStep src={'https://github.com/user-attachments/assets/dba58ea6-7df8-4971-b6d4-b24d5f486ba7'} />
+
+  - Click the `Load Model` button and wait for the model to finish loading and running.
+  - Once the model is loaded, you can use it in the chat interface for conversations.
+
+  ### Step 4: Enable Local Service
+
+  - If you want to use the model through other programs, you need to start a local API service. Start the service through the `Developer` panel or the software menu. The LM Studio service starts on port `1234` on your local machine by default.
+
+  <Image alt={'Start local service'} inStep src={'https://github.com/user-attachments/assets/08ced88b-4968-46e8-b1da-0c04ddf5b743'} />
+
+  - After the local service is started, you also need to enable the `CORS (Cross-Origin Resource Sharing)` option in the service settings so that the model can be used in other programs.
+
+  <Image alt={'Enable CORS'} inStep src={'https://github.com/user-attachments/assets/8ce79bd6-f1a3-48bb-b3d0-5271c84801c2'} />
+
+  ### Step 5: Use LM Studio in LobeChat
+
+  - Visit the `AI Service Provider` interface in LobeChat's `Application Settings`.
+  - Find the settings for `LM Studio` in the list of providers.
+
+  <Image alt={'Fill in the LM Studio address'} inStep src={'https://github.com/user-attachments/assets/143ff392-97b5-427a-97a7-f2f577915728'} />
+
+  - Open the LM Studio service provider and fill in the API service address.
+
+  <Callout type={"warning"}>
+    If your LM Studio is running locally, make sure to turn on `Client Request Mode`.
+  </Callout>
+
+  - Add the model you are running in the model list below.
+  - Select a Volcano Engine model for your assistant to start the conversation.
+
+  <Image alt={'Select LM Studio model'} inStep src={'https://github.com/user-attachments/assets/bd399cef-283c-4706-bdc8-de9de662de41'} />
+</Steps>
+
+Now you can use the model running in LM Studio in LobeChat for conversations.

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

@@ -0,0 +1,75 @@
+---
+title: 在 LobeChat 中使用 LM Studio
+description: 学习如何配置和使用 LM Studio，并在 LobeChat 中 通过 LM Studio 运行 AI 模型进行对话。
+tags:
+  - LobeChat
+  - LM Studio
+  - 开源模型
+  - Web UI
+---
+
+# 在 LobeChat 中使用 LM Studio
+
+<Image alt={'在 LobeChat 中使用 LM Studio'} cover src={'https://github.com/user-attachments/assets/cc1f6146-8063-4a4d-947a-7fd6b9133c0c'} />
+
+[LM Studio](https://lmstudio.ai/) 是一个用于测试和运行大型语言模型（LLM）的平台，提供了直观易用的界面，适合开发人员和 AI 爱好者使用。它支持在本地电脑上部署和运行各种开源 LLM 模型，例如 Deepseek 或 Qwen，实现离线 AI 聊天机器人的功能，从而保护用户隐私并提供更大的灵活性。
+
+本文档将指导你如何在 LobeChat 中使用 LM Studio:
+
+<Steps>
+  ### 步骤一：获取并安装 LM Studio
+
+  - 前往 [LM Studio 官网](https://lmstudio.ai/)
+  - 选择你的平台并下载安装包，LM Studio 目前支持 MacOS、Windows 和 Linux 平台
+  - 按照提示完成安装，运行 LM Studio
+
+  <Image alt={'安装并运行 LM Studio'} inStep src={'https://github.com/user-attachments/assets/e887fa04-c553-45f1-917f-5c123ac9c68b'} />
+
+  ### 步骤二：搜索并下载模型
+
+  - 打开左侧的 `Discover` 菜单，搜索并下载你想要使用的模型
+  - 找到合适的模型（如 Deepseek R1），点击下载
+  - 下载可能需要一些时间，耐心等待完成
+
+  <Image alt={'搜索并下载模型'} inStep src={'https://github.com/user-attachments/assets/f878355f-710b-452e-8606-0c75c47f29d2'} />
+
+  ### 步骤三：部署并运行模型
+
+  - 在顶部的模型选择栏中选择下载好的模型，并加载模型
+  - 在弹出的面板中配置模型运行参数，详细的参数设置请参考 [LM Studio 官方文档](https://lmstudio.ai/docs)
+
+  <Image alt={'配置模型运行参数'} inStep src={'https://github.com/user-attachments/assets/dba58ea6-7df8-4971-b6d4-b24d5f486ba7'} />
+
+  - 点击 `加载模型` 按钮，等待模型完成加载并运行
+  - 模型加载完成后，你可以在聊天界面中使用该模型进行对话
+
+  ### 步骤四：启用本地服务
+
+  - 如果你希望通过其它程序使用该模型，需要启动一个本地 API 服务，通过 `Developer` 面板或软件菜单启动服务，LM Studio 服务默认启动在本机的 `1234` 端口
+
+  <Image alt={'启动本地服务'} inStep src={'https://github.com/user-attachments/assets/08ced88b-4968-46e8-b1da-0c04ddf5b743'} />
+
+  - 本地服务启动后，你还需要在服务设置中开启 `CORS（跨域资源共享）`选项，这样才能在其它程序中使用该模型
+
+  <Image alt={'开启 CORS'} inStep src={'https://github.com/user-attachments/assets/8ce79bd6-f1a3-48bb-b3d0-5271c84801c2'} />
+
+  ### 步骤五：在 LobeChat 中使用 LM Studio
+
+  - 访问 LobeChat 的 `应用设置` 的 `AI 服务供应商` 界面
+  - 在供应商列表中找到 `LM Studio` 的设置项
+
+  <Image alt={'填写 LM Studio 的地址'} inStep src={'https://github.com/user-attachments/assets/143ff392-97b5-427a-97a7-f2f577915728'} />
+
+  - 打开 LM Studio 服务商并填入 API 服务地址
+
+  <Callout type={"warning"}>
+    如果你的 LM Studio 运行在本地，请确保打开`客户端请求模式`
+  </Callout>
+
+  - 在下方的模型列表中添加你运行的模型
+  - 为你的助手选择一个火山引擎模型即可开始对话
+
+  <Image alt={'选择 LM Studio 模型'} inStep src={'https://github.com/user-attachments/assets/bd399cef-283c-4706-bdc8-de9de662de41'} />
+</Steps>
+
+至此你已经可以在 LobeChat 中使用 LM Studio 运行的模型进行对话了。