@lobehub/chat 1.15.2 → 1.15.4

package/CHANGELOG.md

@@ -2,6 +2,58 @@
 
 # Changelog
 
+### [Version 1.15.4](https://github.com/lobehub/lobe-chat/compare/v1.15.3...v1.15.4)
+
+<sup>Released on **2024-09-01**</sup>
+
+#### 💄 Styles
+
+- **misc**: Update Novita AI model info & add `NOVITA_MODEL_LIST` support.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Update Novita AI model info & add `NOVITA_MODEL_LIST` support, closes [#3715](https://github.com/lobehub/lobe-chat/issues/3715) ([4ab33f6](https://github.com/lobehub/lobe-chat/commit/4ab33f6))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
+### [Version 1.15.3](https://github.com/lobehub/lobe-chat/compare/v1.15.2...v1.15.3)
+
+<sup>Released on **2024-09-01**</sup>
+
+#### 💄 Styles
+
+- **misc**: Add `*_MODEL_LIST` for Qwen and ZeroOne, fix model info, update Claude 3.5 Sonnet maxOutput vaule.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **misc**: Add `*_MODEL_LIST` for Qwen and ZeroOne, closes [#3704](https://github.com/lobehub/lobe-chat/issues/3704) ([05419dc](https://github.com/lobehub/lobe-chat/commit/05419dc))
+- **misc**: Fix model info, closes [#3696](https://github.com/lobehub/lobe-chat/issues/3696) ([4d98037](https://github.com/lobehub/lobe-chat/commit/4d98037))
+- **misc**: Update Claude 3.5 Sonnet maxOutput vaule, closes [#3705](https://github.com/lobehub/lobe-chat/issues/3705) ([685bd74](https://github.com/lobehub/lobe-chat/commit/685bd74))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.15.2](https://github.com/lobehub/lobe-chat/compare/v1.15.1...v1.15.2)
 
 <sup>Released on **2024-08-30**</sup>

package/Dockerfile

@@ -127,7 +127,7 @@ ENV \
     # Moonshot
     MOONSHOT_API_KEY="" MOONSHOT_PROXY_URL="" \
     # Novita
-    NOVITA_API_KEY="" \
+    NOVITA_API_KEY="" NOVITA_MODEL_LIST="" \
     # Ollama
     OLLAMA_MODEL_LIST="" OLLAMA_PROXY_URL="" \
     # OpenAI
@@ -137,7 +137,7 @@ ENV \
     # Perplexity
     PERPLEXITY_API_KEY="" PERPLEXITY_PROXY_URL="" \
     # Qwen
-    QWEN_API_KEY="" \
+    QWEN_API_KEY="" QWEN_MODEL_LIST="" \
     # SiliconCloud
     SILICONCLOUD_API_KEY="" SILICONCLOUD_MODEL_LIST="" SILICONCLOUD_PROXY_URL="" \
     # Stepfun
@@ -149,7 +149,7 @@ ENV \
     # Upstage
     UPSTAGE_API_KEY="" \
     # 01.AI
-    ZEROONE_API_KEY="" \
+    ZEROONE_API_KEY="" ZEROONE_MODEL_LIST="" \
     # Zhipu
     ZHIPU_API_KEY="" ZHIPU_MODEL_LIST=""
 

package/Dockerfile.database

@@ -159,7 +159,7 @@ ENV \
     # Moonshot
     MOONSHOT_API_KEY="" MOONSHOT_PROXY_URL="" \
     # Novita
-    NOVITA_API_KEY="" \
+    NOVITA_API_KEY="" NOVITA_MODEL_LIST="" \
     # Ollama
     OLLAMA_MODEL_LIST="" OLLAMA_PROXY_URL="" \
     # OpenAI
@@ -169,7 +169,7 @@ ENV \
     # Perplexity
     PERPLEXITY_API_KEY="" PERPLEXITY_PROXY_URL="" \
     # Qwen
-    QWEN_API_KEY="" \
+    QWEN_API_KEY="" QWEN_MODEL_LIST="" \
     # SiliconCloud
     SILICONCLOUD_API_KEY="" SILICONCLOUD_MODEL_LIST="" SILICONCLOUD_PROXY_URL="" \
     # Stepfun
@@ -181,7 +181,7 @@ ENV \
     # Upstage
     UPSTAGE_API_KEY="" \
     # 01.AI
-    ZEROONE_API_KEY="" \
+    ZEROONE_API_KEY="" ZEROONE_MODEL_LIST="" \
     # Zhipu
     ZHIPU_API_KEY=""
 

package/README.md

@@ -52,18 +52,19 @@ One-click **FREE** deployment of your private OpenAI ChatGPT/Claude/Gemini/Groq/
 
 - [👋🏻 Getting Started & Join Our Community](#-getting-started--join-our-community)
 - [✨ Features](#-features)
-  - [`1` Multi-Model Service Provider Support](#1-multi-model-service-provider-support)
-  - [`2` Local Large Language Model (LLM) Support](#2-local-large-language-model-llm-support)
-  - [`3` Model Visual Recognition](#3-model-visual-recognition)
-  - [`4` TTS & STT Voice Conversation](#4-tts--stt-voice-conversation)
-  - [`5` Text to Image Generation](#5-text-to-image-generation)
-  - [`6` Plugin System (Function Calling)](#6-plugin-system-function-calling)
-  - [`7` Agent Market (GPTs)](#7-agent-market-gpts)
-  - [`8` Support Local / Remote Database](#8-support-local--remote-database)
-  - [`9` Support Multi-User Management](#9-support-multi-user-management)
-  - [`10` Progressive Web App (PWA)](#10-progressive-web-app-pwa)
-  - [`11` Mobile Device Adaptation](#11-mobile-device-adaptation)
-  - [`12` Custom Themes](#12-custom-themes)
+  - [`1` File Upload/Knowledge Base](#1-file-uploadknowledge-base)
+  - [`2` Multi-Model Service Provider Support](#2-multi-model-service-provider-support)
+  - [`3` Local Large Language Model (LLM) Support](#3-local-large-language-model-llm-support)
+  - [`4` Model Visual Recognition](#4-model-visual-recognition)
+  - [`5` TTS & STT Voice Conversation](#5-tts--stt-voice-conversation)
+  - [`6` Text to Image Generation](#6-text-to-image-generation)
+  - [`7` Plugin System (Function Calling)](#7-plugin-system-function-calling)
+  - [`8` Agent Market (GPTs)](#8-agent-market-gpts)
+  - [`9` Support Local / Remote Database](#9-support-local--remote-database)
+  - [`10` Support Multi-User Management](#10-support-multi-user-management)
+  - [`11` Progressive Web App (PWA)](#11-progressive-web-app-pwa)
+  - [`12` Mobile Device Adaptation](#12-mobile-device-adaptation)
+  - [`13` Custom Themes](#13-custom-themes)
   - [`*` What's more](#-whats-more)
 - [⚡️ Performance](#️-performance)
 - [🛳 Self Hosting](#-self-hosting)
@@ -110,9 +111,27 @@ Whether for users or professional developers, LobeHub will be your AI Agent play
 
 ## ✨ Features
 
+[![][image-feat-knowledgebase]][docs-feat-knowledgebase]
+
+### `1` [File Upload/Knowledge Base][docs-feat-knowledgebase]
+
+LobeChat supports file upload and knowledge base functionality. You can upload various types of files including documents, images, audio, and video, as well as create knowledge bases, making it convenient for users to manage and search for files. Additionally, you can utilize files and knowledge base features during conversations, enabling a richer dialogue experience.
+
+<https://github.com/user-attachments/assets/faa8cf67-e743-4590-8bf6-ebf6ccc34175>
+
+> \[!TIP]
+>
+> Learn more on [📘 LobeChat Knowledge Base Launch — From Now On, Every Step Counts](https://lobehub.com/blog/knowledge-base)
+
+<div align="right">
+
+[![][back-to-top]](#readme-top)
+
+</div>
+
 [![][image-feat-privoder]][docs-feat-provider]
 
-### `1` [Multi-Model Service Provider Support][docs-feat-provider]
+### `2` [Multi-Model Service Provider Support][docs-feat-provider]
 
 In the continuous development of LobeChat, we deeply understand the importance of diversity in model service providers for meeting the needs of the community when providing AI conversation services. Therefore, we have expanded our support to multiple model service providers, rather than being limited to a single one, in order to offer users a more diverse and rich selection of conversations.
 
@@ -146,7 +165,7 @@ At the same time, we are also planning to support more model service providers,
 
 [![][image-feat-local]][docs-feat-local]
 
-### `2` [Local Large Language Model (LLM) Support][docs-feat-local]
+### `3` [Local Large Language Model (LLM) Support][docs-feat-local]
 
 To meet the specific needs of users, LobeChat also supports the use of local models based on [Ollama](https://ollama.ai), allowing users to flexibly use their own or third-party models.
 
@@ -162,7 +181,7 @@ To meet the specific needs of users, LobeChat also supports the use of local mod
 
 [![][image-feat-vision]][docs-feat-vision]
 
-### `3` [Model Visual Recognition][docs-feat-vision]
+### `4` [Model Visual Recognition][docs-feat-vision]
 
 LobeChat now supports OpenAI's latest [`gpt-4-vision`](https://platform.openai.com/docs/guides/vision) model with visual recognition capabilities,
 a multimodal intelligence that can perceive visuals. Users can easily upload or drag and drop images into the dialogue box,
@@ -180,7 +199,7 @@ Whether it's sharing images in daily use or interpreting images within specific
 
 [![][image-feat-tts]][docs-feat-tts]
 
-### `4` [TTS & STT Voice Conversation][docs-feat-tts]
+### `5` [TTS & STT Voice Conversation][docs-feat-tts]
 
 LobeChat supports Text-to-Speech (TTS) and Speech-to-Text (STT) technologies, enabling our application to convert text messages into clear voice outputs,
 allowing users to interact with our conversational agent as if they were talking to a real person. Users can choose from a variety of voices to pair with the agent.
@@ -197,7 +216,7 @@ Users can choose the voice that suits their personal preferences or specific sce
 
 [![][image-feat-t2i]][docs-feat-t2i]
 
-### `5` [Text to Image Generation][docs-feat-t2i]
+### `6` [Text to Image Generation][docs-feat-t2i]
 
 With support for the latest text-to-image generation technology, LobeChat now allows users to invoke image creation tools directly within conversations with the agent. By leveraging the capabilities of AI tools such as [`DALL-E 3`](https://openai.com/dall-e-3), [`MidJourney`](https://www.midjourney.com/), and [`Pollinations`](https://pollinations.ai/), the agents are now equipped to transform your ideas into images.
 
@@ -211,7 +230,7 @@ This enables a more private and immersive creative process, allowing for the sea
 
 [![][image-feat-plugin]][docs-feat-plugin]
 
-### `6` [Plugin System (Function Calling)][docs-feat-plugin]
+### `7` [Plugin System (Function Calling)][docs-feat-plugin]
 
 The plugin ecosystem of LobeChat is an important extension of its core functionality, greatly enhancing the practicality and flexibility of the LobeChat assistant.
 
@@ -246,7 +265,7 @@ In addition, these plugins are not limited to news aggregation, but can also ext
 
 [![][image-feat-agent]][docs-feat-agent]
 
-### `7` [Agent Market (GPTs)][docs-feat-agent]
+### `8` [Agent Market (GPTs)][docs-feat-agent]
 
 In LobeChat Agent Marketplace, creators can discover a vibrant and innovative community that brings together a multitude of well-designed agents,
 which not only play an important role in work scenarios but also offer great convenience in learning processes.
@@ -291,7 +310,7 @@ Please tell me what issue you would like to explore?<br/>`backtracking-questions
 
 [![][image-feat-database]][docs-feat-database]
 
-### `8` [Support Local / Remote Database][docs-feat-database]
+### `9` [Support Local / Remote Database][docs-feat-database]
 
 LobeChat supports the use of both server-side and local databases. Depending on your needs, you can choose the appropriate deployment solution:
 
@@ -308,7 +327,7 @@ Regardless of which database you choose, LobeChat can provide you with an excell
 
 [![][image-feat-auth]][docs-feat-auth]
 
-### `9` [Support Multi-User Management][docs-feat-auth]
+### `10` [Support Multi-User Management][docs-feat-auth]
 
 LobeChat supports multi-user management and provides two main user authentication and management solutions to meet different needs:
 
@@ -326,7 +345,7 @@ Regardless of which user management solution you choose, LobeChat can provide yo
 
 [![][image-feat-pwa]][docs-feat-pwa]
 
-### `10` [Progressive Web App (PWA)][docs-feat-pwa]
+### `11` [Progressive Web App (PWA)][docs-feat-pwa]
 
 We deeply understand the importance of providing a seamless experience for users in today's multi-device environment.
 Therefore, we have adopted Progressive Web Application ([PWA](https://support.google.com/chrome/answer/9658361)) technology,
@@ -353,7 +372,7 @@ providing smooth animations, responsive layouts, and adapting to different devic
 
 [![][image-feat-mobile]][docs-feat-mobile]
 
-### `11` [Mobile Device Adaptation][docs-feat-mobile]
+### `12` [Mobile Device Adaptation][docs-feat-mobile]
 
 We have carried out a series of optimization designs for mobile devices to enhance the user's mobile experience. Currently, we are iterating on the mobile user experience to achieve smoother and more intuitive interactions. If you have any suggestions or ideas, we welcome you to provide feedback through GitHub Issues or Pull Requests.
 
@@ -365,7 +384,7 @@ We have carried out a series of optimization designs for mobile devices to enhan
 
 [![][image-feat-theme]][docs-feat-theme]
 
-### `12` [Custom Themes][docs-feat-theme]
+### `13` [Custom Themes][docs-feat-theme]
 
 As a design-engineering-oriented application, LobeChat places great emphasis on users' personalized experiences,
 hence introducing flexible and diverse theme modes, including a light mode for daytime and a dark mode for nighttime.
@@ -712,6 +731,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
 [docs-feat-agent]: https://lobehub.com/docs/usage/features/agent-market
 [docs-feat-auth]: https://lobehub.com/docs/usage/features/auth
 [docs-feat-database]: https://lobehub.com/docs/usage/features/database
+[docs-feat-knowledgebase]: https://lobehub.com/blog/knowledge-base
 [docs-feat-local]: https://lobehub.com/docs/usage/features/local-llm
 [docs-feat-mobile]: https://lobehub.com/docs/usage/features/mobile
 [docs-feat-plugin]: https://lobehub.com/docs/usage/features/plugin-system
@@ -755,6 +775,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
 [image-feat-agent]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png
 [image-feat-auth]: https://github.com/lobehub/lobe-chat/assets/17870709/8ce70e15-40df-451e-b700-66090fe5b8c2
 [image-feat-database]: https://github.com/lobehub/lobe-chat/assets/17870709/c27a0234-a4e9-40e5-8bcb-42d5ce7e40f9
+[image-feat-knowledgebase]: https://github.com/user-attachments/assets/77e58e1c-c82f-4341-b159-f4eeede9967f
 [image-feat-local]: https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c
 [image-feat-mobile]: https://gw.alipayobjects.com/zos/kitchen/R441AuFS4W/mobile.webp
 [image-feat-plugin]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670883-33c43a5c-a512-467e-855c-fa299548cce5.png

package/README.zh-CN.md

@@ -52,18 +52,19 @@
 
 - [👋🏻 开始使用 & 交流](#-开始使用--交流)
 - [✨ 特性一览](#-特性一览)
-  - [`1` 多模型服务商支持](#1-多模型服务商支持)
-  - [`2` 支持本地大语言模型 (LLM)](#2-支持本地大语言模型-llm)
-  - [`3` 模型视觉识别 (Model Visual)](#3-模型视觉识别-model-visual)
-  - [`4` TTS & STT 语音会话](#4-tts--stt-语音会话)
-  - [`5` Text to Image 文生图](#5-text-to-image-文生图)
-  - [`6` 插件系统 (Function Calling)](#6-插件系统-function-calling)
-  - [`7` 助手市场 (GPTs)](#7-助手市场-gpts)
-  - [`8` 支持本地 / 远程数据库](#8-支持本地--远程数据库)
-  - [`9` 支持多用户管理](#9-支持多用户管理)
-  - [`10` 渐进式 Web 应用 (PWA)](#10-渐进式-web-应用-pwa)
-  - [`11` 移动设备适配](#11-移动设备适配)
-  - [`12` 自定义主题](#12-自定义主题)
+  - [`1` 文件上传 / 知识库](#1-文件上传--知识库)
+  - [`2` 多模型服务商支持](#2-多模型服务商支持)
+  - [`3` 支持本地大语言模型 (LLM)](#3-支持本地大语言模型-llm)
+  - [`4` 模型视觉识别 (Model Visual)](#4-模型视觉识别-model-visual)
+  - [`5` TTS & STT 语音会话](#5-tts--stt-语音会话)
+  - [`6` Text to Image 文生图](#6-text-to-image-文生图)
+  - [`7` 插件系统 (Tools Calling)](#7-插件系统-tools-calling)
+  - [`8` 助手市场 (GPTs)](#8-助手市场-gpts)
+  - [`9` 支持本地 / 远程数据库](#9-支持本地--远程数据库)
+  - [`10` 支持多用户管理](#10-支持多用户管理)
+  - [`11` 渐进式 Web 应用 (PWA)](#11-渐进式-web-应用-pwa)
+  - [`12` 移动设备适配](#12-移动设备适配)
+  - [`13` 自定义主题](#13-自定义主题)
   - [更多特性](#更多特性)
 - [⚡️ 性能测试](#️-性能测试)
 - [🛳 开箱即用](#-开箱即用)
@@ -110,9 +111,27 @@
 
 ## ✨ 特性一览
 
+[![][image-feat-knowledgebase]][docs-feat-knowledgebase]
+
+### `1` [文件上传 / 知识库][docs-feat-knowledgebase]
+
+LobeChat 支持文件上传与知识库功能，你可以上传文件、图片、音频、视频等多种类型的文件，以及创建知识库，方便用户管理和查找文件。同时在对话中使用文件和知识库功能，实现更加丰富的对话体验。
+
+<https://github.com/user-attachments/assets/faa8cf67-e743-4590-8bf6-ebf6ccc34175>
+
+> \[!TIP]
+>
+> 查阅 [📘 LobeChat 知识库上线 —— 此刻起，跬步千里](https://lobehub.com/zh/blog/knowledge-base) 了解详情。
+
+<div align="right">
+
+[![][back-to-top]](#readme-top)
+
+</div>
+
 [![][image-feat-privoder]][docs-feat-provider]
 
-### `1` [多模型服务商支持][docs-feat-provider]
+### `2` [多模型服务商支持][docs-feat-provider]
 
 在 LobeChat 的不断发展过程中，我们深刻理解到在提供 AI 会话服务时模型服务商的多样性对于满足社区需求的重要性。因此，我们不再局限于单一的模型服务商，而是拓展了对多种模型服务商的支持，以便为用户提供更为丰富和多样化的会话选择。
 
@@ -145,7 +164,7 @@
 
 [![][image-feat-local]][docs-feat-local]
 
-### `2` [支持本地大语言模型 (LLM)][docs-feat-local]
+### `3` [支持本地大语言模型 (LLM)][docs-feat-local]
 
 为了满足特定用户的需求，LobeChat 还基于 [Ollama](https://ollama.ai) 支持了本地模型的使用，让用户能够更灵活地使用自己的或第三方的模型。
 
@@ -161,7 +180,7 @@
 
 [![][image-feat-vision]][docs-feat-vision]
 
-### `3` [模型视觉识别 (Model Visual)][docs-feat-vision]
+### `4` [模型视觉识别 (Model Visual)][docs-feat-vision]
 
 LobeChat 已经支持 OpenAI 最新的 [`gpt-4-vision`](https://platform.openai.com/docs/guides/vision) 支持视觉识别的模型，这是一个具备视觉识别能力的多模态应用。
 用户可以轻松上传图片或者拖拽图片到对话框中，助手将能够识别图片内容，并在此基础上进行智能对话，构建更智能、更多元化的聊天场景。
@@ -176,7 +195,7 @@ LobeChat 已经支持 OpenAI 最新的 [`gpt-4-vision`](https://platform.openai.
 
 [![][image-feat-tts]][docs-feat-tts]
 
-### `4` [TTS & STT 语音会话][docs-feat-tts]
+### `5` [TTS & STT 语音会话][docs-feat-tts]
 
 LobeChat 支持文字转语音（Text-to-Speech，TTS）和语音转文字（Speech-to-Text，STT）技术，这使得我们的应用能够将文本信息转化为清晰的语音输出，用户可以像与真人交谈一样与我们的对话助手进行交流。
 用户可以从多种声音中选择，给助手搭配合适的音源。 同时，对于那些倾向于听觉学习或者想要在忙碌中获取信息的用户来说，TTS 提供了一个极佳的解决方案。
@@ -191,7 +210,7 @@ LobeChat 支持文字转语音（Text-to-Speech，TTS）和语音转文字（Spe
 
 [![][image-feat-t2i]][docs-feat-t2i]
 
-### `5` [Text to Image 文生图][docs-feat-t2i]
+### `6` [Text to Image 文生图][docs-feat-t2i]
 
 支持最新的文本到图片生成技术，LobeChat 现在能够让用户在与助手对话中直接调用文生图工具进行创作。
 通过利用 [`DALL-E 3`](https://openai.com/dall-e-3)、[`MidJourney`](https://www.midjourney.com/) 和 [`Pollinations`](https://pollinations.ai/) 等 AI 工具的能力， 助手们现在可以将你的想法转化为图像。
@@ -205,7 +224,7 @@ LobeChat 支持文字转语音（Text-to-Speech，TTS）和语音转文字（Spe
 
 [![][image-feat-plugin]][docs-feat-plugin]
 
-### `6` [插件系统 (Function Calling)][docs-feat-plugin]
+### `7` [插件系统 (Tools Calling)][docs-feat-plugin]
 
 LobeChat 的插件生态系统是其核心功能的重要扩展，它极大地增强了 ChatGPT 的实用性和灵活性。
 
@@ -238,7 +257,7 @@ LobeChat 的插件生态系统是其核心功能的重要扩展，它极大地
 
 [![][image-feat-agent]][docs-feat-agent]
 
-### `7` [助手市场 (GPTs)][docs-feat-agent]
+### `8` [助手市场 (GPTs)][docs-feat-agent]
 
 在 LobeChat 的助手市场中，创作者们可以发现一个充满活力和创新的社区，它汇聚了众多精心设计的助手，这些助手不仅在工作场景中发挥着重要作用，也在学习过程中提供了极大的便利。
 我们的市场不仅是一个展示平台，更是一个协作的空间。在这里，每个人都可以贡献自己的智慧，分享个人开发的助手。
@@ -279,7 +298,7 @@ LobeChat 的插件生态系统是其核心功能的重要扩展，它极大地
 
 [![][image-feat-database]][docs-feat-database]
 
-### `8` [支持本地 / 远程数据库][docs-feat-database]
+### `9` [支持本地 / 远程数据库][docs-feat-database]
 
 LobeChat 支持同时使用服务端数据库和本地数据库。根据您的需求，您可以选择合适的部署方案：
 
@@ -296,7 +315,7 @@ LobeChat 支持同时使用服务端数据库和本地数据库。根据您的
 
 [![][image-feat-auth]][docs-feat-auth]
 
-### `9` [支持多用户管理][docs-feat-auth]
+### `10` [支持多用户管理][docs-feat-auth]
 
 LobeChat 支持多用户管理，提供了两种主要的用户认证和管理方案，以满足不同需求：
 
@@ -314,7 +333,7 @@ LobeChat 支持多用户管理，提供了两种主要的用户认证和管理
 
 [![][image-feat-pwa]][docs-feat-pwa]
 
-### `10` [渐进式 Web 应用 (PWA)][docs-feat-pwa]
+### `11` [渐进式 Web 应用 (PWA)][docs-feat-pwa]
 
 我们深知在当今多设备环境下为用户提供无缝体验的重要性。为此，我们采用了渐进式 Web 应用 [PWA](https://support.google.com/chrome/answer/9658361) 技术，
 这是一种能够将网页应用提升至接近原生应用体验的现代 Web 技术。通过 PWA，LobeChat 能够在桌面和移动设备上提供高度优化的用户体验，同时保持轻量级和高性能的特点。
@@ -337,7 +356,7 @@ LobeChat 支持多用户管理，提供了两种主要的用户认证和管理
 
 [![][image-feat-mobile]][docs-feat-mobile]
 
-### `11` [移动设备适配][docs-feat-mobile]
+### `12` [移动设备适配][docs-feat-mobile]
 
 针对移动设备进行了一系列的优化设计，以提升用户的移动体验。目前，我们正在对移动端的用户体验进行版本迭代，以实现更加流畅和直观的交互。如果您有任何建议或想法，我们非常欢迎您通过 GitHub Issues 或者 Pull Requests 提供反馈。
 
@@ -349,7 +368,7 @@ LobeChat 支持多用户管理，提供了两种主要的用户认证和管理
 
 [![][image-feat-theme]][docs-feat-theme]
 
-### `12` [自定义主题][docs-feat-theme]
+### `13` [自定义主题][docs-feat-theme]
 
 作为设计工程师出身，LobeChat 在界面设计上充分考虑用户的个性化体验，因此引入了灵活多变的主题模式，其中包括日间的亮色模式和夜间的深色模式。
 除了主题模式的切换，还提供了一系列的颜色定制选项，允许用户根据自己的喜好来调整应用的主题色彩。无论是想要沉稳的深蓝，还是希望活泼的桃粉，或者是专业的灰白，用户都能够在 LobeChat 中找到匹配自己风格的颜色选择。
@@ -733,6 +752,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
 [docs-feat-agent]: https://lobehub.com/docs/usage/features/agent-market
 [docs-feat-auth]: https://lobehub.com/docs/usage/features/auth
 [docs-feat-database]: https://lobehub.com/docs/usage/features/database
+[docs-feat-knowledgebase]: https://lobehub.com/blog/knowledge-base
 [docs-feat-local]: https://lobehub.com/docs/usage/features/local-llm
 [docs-feat-mobile]: https://lobehub.com/docs/usage/features/mobile
 [docs-feat-plugin]: https://lobehub.com/docs/usage/features/plugin-system
@@ -778,6 +798,7 @@ This project is [Apache 2.0](./LICENSE) licensed.
 [image-feat-agent]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670869-f1ffbf66-42b6-42cf-a937-9ce1f8328514.png
 [image-feat-auth]: https://github.com/lobehub/lobe-chat/assets/17870709/8ce70e15-40df-451e-b700-66090fe5b8c2
 [image-feat-database]: https://github.com/lobehub/lobe-chat/assets/17870709/c27a0234-a4e9-40e5-8bcb-42d5ce7e40f9
+[image-feat-knowledgebase]: https://github.com/user-attachments/assets/77e58e1c-c82f-4341-b159-f4eeede9967f
 [image-feat-local]: https://github.com/lobehub/lobe-chat/assets/28616219/ca9a21bc-ea6c-4c90-bf4a-fa53b4fb2b5c
 [image-feat-mobile]: https://gw.alipayobjects.com/zos/kitchen/R441AuFS4W/mobile.webp
 [image-feat-plugin]: https://github-production-user-asset-6210df.s3.amazonaws.com/17870709/268670883-33c43a5c-a512-467e-855c-fa299548cce5.png

package/docs/self-hosting/server-database/docker-compose.mdx

@@ -299,7 +299,7 @@ If you configure using the second method (which is also the default method), you
 
 You need to first access the WebUI for configuration:
 
-- If you configured the reverse proxy as mentioned earlier, open `https://lobe-s3-api.example.com`
+- If you configured the reverse proxy as mentioned earlier, open `https://lobe-s3-ui.example.com`
 - Otherwise, after port mapping, open `http://localhost:9001`
 
 1. Enter your `MINIO_ROOT_USER` and `MINIO_ROOT_PASSWORD` on the login screen, then click login.

package/docs/self-hosting/server-database/docker-compose.zh-CN.mdx

@@ -296,7 +296,7 @@ docker compose up -d # 重新启动
 
 你需要首先访问 WebUI 来进行配置：
 
-- 如果你按照前文配置了反向代理，打开 `https://lobe-s3-api.example.com`
+- 如果你按照前文配置了反向代理，打开 `https://lobe-s3-ui.example.com`
 - 否则，请在进行端口映射后，打开 `http://localhost:9001`
 
 1. 在登录界面输入你设置的 `MINIO_ROOT_USER` 和 `MINIO_ROOT_PASSWORD`，然后点击登录

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.15.2",
+  "version": "1.15.4",
   "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",
@@ -292,7 +292,7 @@
     "vitest": "~1.2.2",
     "vitest-canvas-mock": "^0.3.3"
   },
-  "packageManager": "pnpm@9.8.0",
+  "packageManager": "pnpm@9.9.0",
   "publishConfig": {
     "access": "public",
     "registry": "https://registry.npmjs.org"

package/src/config/llm.ts

@@ -57,6 +57,7 @@ export const getLLMConfig = () => {
 
       ENABLED_ZEROONE: z.boolean(),
       ZEROONE_API_KEY: z.string().optional(),
+      ZEROONE_MODEL_LIST: z.string().optional(),
 
       ENABLED_TOGETHERAI: z.boolean(),
       TOGETHERAI_API_KEY: z.string().optional(),
@@ -73,12 +74,14 @@ export const getLLMConfig = () => {
 
       ENABLED_QWEN: z.boolean(),
       QWEN_API_KEY: z.string().optional(),
+      QWEN_MODEL_LIST: z.string().optional(),
 
       ENABLED_STEPFUN: z.boolean(),
       STEPFUN_API_KEY: z.string().optional(),
 
       ENABLED_NOVITA: z.boolean(),
       NOVITA_API_KEY: z.string().optional(),
+      NOVITA_MODEL_LIST: z.string().optional(),
 
       ENABLED_BAICHUAN: z.boolean(),
       BAICHUAN_API_KEY: z.string().optional(),
@@ -154,6 +157,7 @@ export const getLLMConfig = () => {
 
       ENABLED_ZEROONE: !!process.env.ZEROONE_API_KEY,
       ZEROONE_API_KEY: process.env.ZEROONE_API_KEY,
+      ZEROONE_MODEL_LIST: process.env.ZEROONE_MODEL_LIST,
 
       ENABLED_AWS_BEDROCK: process.env.ENABLED_AWS_BEDROCK === '1',
       AWS_REGION: process.env.AWS_REGION,
@@ -166,12 +170,14 @@ export const getLLMConfig = () => {
 
       ENABLED_QWEN: !!process.env.QWEN_API_KEY,
       QWEN_API_KEY: process.env.QWEN_API_KEY,
+      QWEN_MODEL_LIST: process.env.QWEN_MODEL_LIST,
 
       ENABLED_STEPFUN: !!process.env.STEPFUN_API_KEY,
       STEPFUN_API_KEY: process.env.STEPFUN_API_KEY,
 
       ENABLED_NOVITA: !!process.env.NOVITA_API_KEY,
       NOVITA_API_KEY: process.env.NOVITA_API_KEY,
+      NOVITA_MODEL_LIST: process.env.NOVITA_MODEL_LIST,
 
       ENABLED_BAICHUAN: !!process.env.BAICHUAN_API_KEY,
       BAICHUAN_API_KEY: process.env.BAICHUAN_API_KEY,

package/src/config/modelProviders/anthropic.ts

@@ -10,7 +10,7 @@ const Anthropic: ModelProviderCard = {
       enabled: true,
       functionCall: true,
       id: 'claude-3-5-sonnet-20240620',
-      maxOutput: 4096,
+      maxOutput: 8192,
       tokens: 200_000,
       vision: true,
     },

package/src/config/modelProviders/novita.ts

@@ -1,30 +1,47 @@
 import { ModelProviderCard } from '@/types/llm';
 
+// ref: https://novita.ai/model-api/product/llm-api
 const Novita: ModelProviderCard = {
   chatModels: [
     {
-      displayName: 'Llama3 8B Instruct',
+      displayName: 'Llama3.1 8B Instruct',
+      enabled: true,
+      id: 'meta-llama/llama-3.1-8b-instruct',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Llama3.1 70B Instruct',
       enabled: true,
+      id: 'meta-llama/llama-3.1-70b-instruct',
+      tokens: 131_072,
+    },
+    {
+      displayName: 'Llama3.1 405B Instruct',
+      enabled: true,
+      id: 'meta-llama/llama-3.1-405b-instruct',
+      tokens: 32_768,
+    },
+    {
+      displayName: 'Llama3 8B Instruct',
       id: 'meta-llama/llama-3-8b-instruct',
       tokens: 8192,
     },
     {
       displayName: 'Llama3 70B Instruct',
-      enabled: true,
       id: 'meta-llama/llama-3-70b-instruct',
       tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes 2 Pro - Llama3 8B',
+      displayName: 'Gemma 2 9B',
       enabled: true,
-      id: 'nousresearch/hermes-2-pro-llama-3-8b',
+      id: 'google/gemma-2-9b-it',
       tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes - Llama2 8B',
+      displayName: 'Mistral Nemo',
       enabled: true,
-      id: 'nousresearch/nous-hermes-llama2-13b',
-      tokens: 4096,
+      id: 'mistralai/mistral-nemo',
+      tokens: 32_768,
     },
     {
       displayName: 'Mistral 7B Instruct',
@@ -33,55 +50,44 @@ const Novita: ModelProviderCard = {
       tokens: 32_768,
     },
     {
-      displayName: 'Dolphin Mixtral 8x22B',
+      displayName: 'WizardLM 2 7B',
       enabled: true,
-      id: 'cognitivecomputations/dolphin-mixtral-8x22b',
-      tokens: 16_000,
+      id: 'microsoft/wizardlm 2-7b',
+      tokens: 32_768,
     },
     {
-      displayName: 'L3-70b-Euryale-v2.1',
+      displayName: 'WizardLM-2 8x22B',
       enabled: true,
-      id: 'sao10k/l3-70b-euryale-v2.1',
-      tokens: 16_000,
+      id: 'microsoft/wizardlm-2-8x22b',
+      tokens: 65_535,
     },
     {
-      displayName: 'Midnight Rose 70B',
-      enabled: true,
-      id: 'sophosympatheia/midnight-rose-70b',
-      tokens: 4096,
+      displayName: 'Dolphin Mixtral 8x22B',
+      id: 'cognitivecomputations/dolphin-mixtral-8x22b',
+      tokens: 16_000,
     },
     {
-      displayName: 'Mythomax L2 13b',
-      enabled: true,
-      id: 'gryphe/mythomax-l2-13b',
-      tokens: 4096,
+      displayName: 'Hermes 2 Pro Llama 3 8B',
+      id: 'nousresearch/hermes-2-pro-llama-3-8b',
+      tokens: 8192,
     },
     {
-      displayName: 'Nous Hermes 2 - Mixtral 8x7B-DPO',
-      enabled: true,
+      displayName: 'Hermes 2 Mixtral 8x7B DPO',
       id: 'Nous-Hermes-2-Mixtral-8x7B-DPO',
       tokens: 32_768,
     },
     {
-      displayName: 'Lzlv 70b',
-      enabled: true,
-      id: 'lzlv_70b',
+      displayName: 'MythoMax l2 13B',
+      id: 'gryphe/mythomax-l2-13b',
       tokens: 4096,
     },
     {
-      displayName: 'Open Hermes 2.5 Mistral 7B',
-      enabled: true,
-      id: 'teknium/openhermes-2.5-mistral-7b',
+      displayName: 'OpenChat 7B',
+      id: 'openchat/openchat-7b',
       tokens: 4096,
     },
-    {
-      displayName: 'Wizardlm2 8x22B',
-      enabled: true,
-      id: 'microsoft/wizardlm-2-8x22b',
-      tokens: 65_535,
-    },
   ],
-  checkModel: 'meta-llama/llama-3-70b-instruct',
+  checkModel: 'meta-llama/llama-3.1-8b-instruct',
   disableBrowserRequest: true,
   id: 'novita',
   modelList: { showModelFetcher: true },

package/src/config/modelProviders/qwen.ts

@@ -16,7 +16,7 @@ const Qwen: ModelProviderCard = {
       enabled: true,
       functionCall: true,
       id: 'qwen-turbo',
-      tokens: 8192,
+      tokens: 8000, // https://www.alibabacloud.com/help/zh/model-studio/developer-reference/use-qwen-by-calling-api
     },
     {
       description: '通义千问超大规模语言模型增强版，支持中文、英文等不同语言输入',
@@ -24,7 +24,7 @@ const Qwen: ModelProviderCard = {
       enabled: true,
       functionCall: true,
       id: 'qwen-plus',
-      tokens: 130_000,
+      tokens: 131_072, // https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction
     },
     {
       description:
@@ -33,7 +33,7 @@ const Qwen: ModelProviderCard = {
       enabled: true,
       functionCall: true,
       id: 'qwen-max',
-      tokens: 8192,
+      tokens: 8000,
     },
     {
       description:
@@ -41,7 +41,7 @@ const Qwen: ModelProviderCard = {
       displayName: 'Qwen Max LongContext',
       functionCall: true,
       id: 'qwen-max-longcontext',
-      tokens: 30_720,
+      tokens: 30_000,
     },
     {
       description:
@@ -70,36 +70,37 @@ const Qwen: ModelProviderCard = {
       tokens: 32_768,
       vision: true,
     },
+    // ref https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-7b-14b-72b-api-detailes
     {
       description: '通义千问2对外开源的7B规模的模型',
       displayName: 'Qwen2 7B',
       id: 'qwen2-7b-instruct',
-      tokens: 128_000,
+      tokens: 131_072, // https://huggingface.co/Qwen/Qwen2-7B-Instruct
     },
     {
       description: '通义千问2对外开源的57B规模14B激活参数的MOE模型',
       displayName: 'Qwen2 57B-A14B MoE',
       id: 'qwen2-57b-a14b-instruct',
-      tokens: 32_768,
+      tokens: 65_536, // https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct
     },
     {
       description: '通义千问2对外开源的72B规模的模型',
       displayName: 'Qwen2 72B',
       id: 'qwen2-72b-instruct',
-      tokens: 128_000,
+      tokens: 131_072, // https://huggingface.co/Qwen/Qwen2-72B-Instruct
     },
     {
       description: 'Qwen2-Math 模型具有强大的数学解题能力',
       displayName: 'Qwen2 Math 72B',
       id: 'qwen2-math-72b-instruct',
-      tokens: 128_000,
+      tokens: 4096, // https://help.aliyun.com/zh/dashscope/developer-reference/use-qwen2-math-by-calling-api
     },
     {
       description:
         '以 Qwen-7B 语言模型初始化，添加图像模型，图像输入分辨率为448的预训练模型。',
       displayName: 'Qwen VL',
       id: 'qwen-vl-v1',
-      tokens: 8192,
+      tokens: 8192, // https://huggingface.co/Qwen/Qwen-VL/blob/main/config.json
       vision: true,
     },
     {
@@ -107,12 +108,12 @@ const Qwen: ModelProviderCard = {
         '通义千问VL支持灵活的交互方式，包括多图、多轮问答、创作等能力的模型。',
       displayName: 'Qwen VL Chat',
       id: 'qwen-vl-chat-v1',
-      tokens: 8192,
+      tokens: 8192, // https://huggingface.co/Qwen/Qwen-VL-Chat/blob/main/config.json
       vision: true,
     },
   ],
   checkModel: 'qwen-turbo',
-  disableBrowserRequest: true,
+  disableBrowserRequest: true, // CORS issue
   id: 'qwen',
   modelList: { showModelFetcher: true },
   name: 'Qwen',

package/src/config/modelProviders/stepfun.ts

@@ -1,11 +1,12 @@
 import { ModelProviderCard } from '@/types/llm';
 
 // ref https://platform.stepfun.com/docs/llm/text
+// 根据文档，阶级星辰大模型的上下文长度，其 k 的含义为 1000
 const Stepfun: ModelProviderCard = {
   chatModels: [
     {
       id: 'step-2-16k-nightly',
-      tokens: 16_384,
+      tokens: 16_000,
     },
     {
       id: 'step-1-256k',
@@ -19,27 +20,31 @@ const Stepfun: ModelProviderCard = {
     {
       enabled: true,
       id: 'step-1-32k',
-      tokens: 32_768,
+      tokens: 32_000,
     },
     {
-      enabled: true,
       id: 'step-1-8k',
-      tokens: 8192,
+      tokens: 8000,
+    },
+    {
+      enabled: true,
+      id: 'step-1-flash',
+      tokens: 8000,
     },
     {
       enabled: true,
       id: 'step-1v-32k',
-      tokens: 32_768,
+      tokens: 32_000,
       vision: true,
     },
     {
       enabled: true,
       id: 'step-1v-8k',
-      tokens: 8192,
+      tokens: 8000,
       vision: true,
     },
   ],
-  checkModel: 'step-1-8k',
+  checkModel: 'step-1-flash',
   // after test, currently https://api.stepfun.com/v1/chat/completions has the CORS issue
   // So we should close the browser request mode
   disableBrowserRequest: true,

package/src/server/globalConfig/index.ts

@@ -4,11 +4,14 @@ import { fileEnv } from '@/config/file';
 import { langfuseEnv } from '@/config/langfuse';
 import { getLLMConfig } from '@/config/llm';
 import {
+  NovitaProviderCard,
   OllamaProviderCard,
   OpenAIProviderCard,
   OpenRouterProviderCard,
+  QwenProviderCard,
   SiliconCloudProviderCard,
   TogetherAIProviderCard,
+  ZeroOneProviderCard,
   ZhiPuProviderCard,
 } from '@/config/modelProviders';
 import { enableNextAuth } from '@/const/auth';
@@ -37,8 +40,13 @@ export const getServerGlobalConfig = () => {
     ENABLED_ANTHROPIC,
     ENABLED_MINIMAX,
     ENABLED_MISTRAL,
+
     ENABLED_NOVITA,
+    NOVITA_MODEL_LIST,
+
     ENABLED_QWEN,
+    QWEN_MODEL_LIST,
+
     ENABLED_STEPFUN,
     ENABLED_BAICHUAN,
     ENABLED_TAICHU,
@@ -60,6 +68,8 @@ export const getServerGlobalConfig = () => {
     OPENROUTER_MODEL_LIST,
 
     ENABLED_ZEROONE,
+    ZEROONE_MODEL_LIST,
+
     ENABLED_TOGETHERAI,
     TOGETHERAI_MODEL_LIST,
   } = getLLMConfig();
@@ -93,7 +103,14 @@ export const getServerGlobalConfig = () => {
       minimax: { enabled: ENABLED_MINIMAX },
       mistral: { enabled: ENABLED_MISTRAL },
       moonshot: { enabled: ENABLED_MOONSHOT },
-      novita: { enabled: ENABLED_NOVITA },
+      novita: {
+        enabled: ENABLED_NOVITA,
+        enabledModels: extractEnabledModels(NOVITA_MODEL_LIST),
+        serverModelCards: transformToChatModelCards({
+          defaultChatModels: NovitaProviderCard.chatModels,
+          modelString: NOVITA_MODEL_LIST,
+        }),
+      },
       ollama: {
         enabled: ENABLED_OLLAMA,
         fetchOnClient: !OLLAMA_PROXY_URL,
@@ -120,7 +137,14 @@ export const getServerGlobalConfig = () => {
         }),
       },
       perplexity: { enabled: ENABLED_PERPLEXITY },
-      qwen: { enabled: ENABLED_QWEN },
+      qwen: {
+        enabled: ENABLED_QWEN,
+        enabledModels: extractEnabledModels(QWEN_MODEL_LIST),
+        serverModelCards: transformToChatModelCards({
+          defaultChatModels: QwenProviderCard.chatModels,
+          modelString: QWEN_MODEL_LIST,
+        }),
+      },
       siliconcloud: {
         enabled: ENABLED_SILICONCLOUD,
         enabledModels: extractEnabledModels(SILICONCLOUD_MODEL_LIST),
@@ -141,7 +165,14 @@ export const getServerGlobalConfig = () => {
         }),
       },
       upstage: { enabled: ENABLED_UPSTAGE },
-      zeroone: { enabled: ENABLED_ZEROONE },
+      zeroone: {
+        enabled: ENABLED_ZEROONE,
+        enabledModels: extractEnabledModels(ZEROONE_MODEL_LIST),
+        serverModelCards: transformToChatModelCards({
+          defaultChatModels: ZeroOneProviderCard.chatModels,
+          modelString: ZEROONE_MODEL_LIST,
+        }),
+      },
       zhipu: { 
         enabled: ENABLED_ZHIPU, 
         enabledModels: extractEnabledModels(ZHIPU_MODEL_LIST),