💄 style: Add new model provider Novita AI (lobehub#3177)

README.md

@@ -134,6 +134,7 @@ We have implemented support for the following model service providers:
 - **Minimax**: Integrated the Minimax models, including the MoE model **abab6**, offers a broader range of choices. [Learn more](https://www.minimaxi.com/)
 - **DeepSeek**: Integrated with the DeepSeek series models, an innovative AI startup from China, The product has been designed to provide a model that balances performance with price. [Learn more](https://www.deepseek.com/)
 - **Qwen**: Integrated the Qwen series models, including the latest **qwen-turbo**, **qwen-plus** and **qwen-max**. [Lean more](https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction)
+- **Novita AI**: Access **Llama**, **Mistral**, and other leading open-source models at cheapest prices. Engage in uncensored role-play, spark creative discussions, and foster unrestricted innovation. **Pay For What You Use.** [Learn more](https://novita.ai/llm-api?utm_source=lobechat&utm_medium=ch&utm_campaign=api)
 
 At the same time, we are also planning to support more model service providers, such as Replicate and Perplexity, to further enrich our service provider library. If you would like LobeChat to support your favorite service provider, feel free to join our [community discussion](https://github.com/lobehub/lobe-chat/discussions/1284).
 

docs/usage/providers/novita.mdx

@@ -0,0 +1,80 @@
+---
+title: Using Novita AI API Key in LobeChat
+description: >-
+  Learn how to integrate Novita AI's language model APIs into LobeChat. Follow the steps to register, create an Novita AI API key,
+  configure settings, and chat with our various AI models.
+
+tags:
+  - Novita AI
+  - Llama3
+  - Mistral
+  - uncensored
+  - API key
+  - Web UI
+---
+
+# Using Novita AI in LobeChat
+
+<Image
+  alt={'Using Novita AI in LobeChat'}
+  cover
+  src={'https://github.com/user-attachments/assets/b2b36128-6a43-4a1f-9c08-99fe73fb565f'}
+/>
+
+[Novita AI](https://novita.ai/) is an AI API platform that provides a variety of LLM and image generation APIs, supporting Llama3 (8B, 70B), Mistral, and many other cutting-edge models. We offer a variety of censored and uncensored models to meet your different needs.
+
+This document will guide you on how to integrate Novita AI in LobeChat:
+
+<Steps>
+
+### Step 1: Register and Log in to Novita AI
+
+- Visit [Novita.ai](https://novita.ai/) and create an account
+- You can log in with your Google or Github account
+- Upon registration, Novita AI will provide a $0.5 credit.
+
+<Image
+  alt={'Register OpenRouter'}
+  height={457}
+  inStep
+  src={'https://github.com/user-attachments/assets/f3177ce2-281c-4ed4-a061-239547b466c6'}
+/>
+
+### Step 2: Obtain the API Key
+
+- Visit Novita AI's [key management page](https://novita.ai/dashboard/key), create and copy an API Key.
+
+<Image
+  alt={'Obtain Novita AI API key'}
+  inStep
+  src={'https://github.com/user-attachments/assets/1e33aff2-6186-4e1f-80a8-4a2c855d8cc1'}
+/>
+
+### Step 3: Configure Novita AI in LobeChat
+
+- Visit the `Settings` interface in LobeChat
+- Find the setting for `novita.ai` under `Language Model`
+
+<Image
+  alt={'Enter Novita AI API key in LobeChat'}
+  inStep
+  src={'https://github.com/user-attachments/assets/00c02637-873e-4e7e-9dc3-a95085b16dd7'}
+/>
+
+- Open novita.ai and enter the obtained API key
+- Choose a Novita AI model for your assistant to start the conversation
+
+<Image
+  alt={'Select and use Novita AI model'}
+  inStep
+  src={'https://github.com/user-attachments/assets/6f9f400a-72e0-49de-94cb-5069fddf1163'}
+/>
+
+<Callout type={'warning'}>
+  During usage, you may need to pay the API service provider, please refer to Novita AI's pricing
+  policy.
+</Callout>
+
+</Steps>
+
+You can now engage in conversations using the models provided by Novita AI in LobeChat.

docs/usage/providers/novita.zh-CN.mdx

@@ -0,0 +1,76 @@
+---
+title: 在 LobeChat 中使用 Novita AI API Key
+description: 学习如何将 Novita AI 的大语言模型 API 集成到 LobeChat 中。跟随以下步骤注册 Novita AI 账号、创建 API Key、充值信用额度并在 LobeChat 中进行设置。并与我们的多种 AI 模型交谈。
+tags:
+  - Novita AI
+  - Llama3
+  - Mistral
+  - uncensored
+  - API key
+  - Web UI
+---
+
+# 在 LobeChat 中使用 Novita AI
+
+<Image
+  alt={'在 LobeChat 中使用 Novita AI'}
+  cover
+  src={'https://github.com/user-attachments/assets/b2b36128-6a43-4a1f-9c08-99fe73fb565f'}
+/>
+
+[Novita AI](https://novita.ai/) 是一个 AI API 平台，它提供多种大语言模型与 AI 图像生成的 API 服务。支持 Llama3 (8B, 70B)，Mistral 和其他最新的模型。
+
+本文档将指导你如何在 LobeChat 中使用 Novita AI:
+
+<Steps>
+
+### 步骤一：注册 Novita AI 账号并登录
+
+- 访问 [Novita.ai](https://novita.ai/) 并创建账号
+- 你可以使用 Google 或者 Github 账号登录
+- 注册后，Novita AI 会赠送 0.5 美元的使用额度
+
+<Image
+  alt={'注册 Novita AI'}
+  height={457}
+  inStep
+  src={'https://github.com/user-attachments/assets/f3177ce2-281c-4ed4-a061-239547b466c6'}
+/>
+
+### 步骤二：创建 API 密钥
+
+- 访问 Novita AI 的 [密钥管理页面](https://novita.ai/dashboard/key) ，创建并且复制一个 API 密钥.
+
+<Image
+  alt={'创建 Novita AI API 密钥'}
+  inStep
+  src={'https://github.com/user-attachments/assets/1e33aff2-6186-4e1f-80a8-4a2c855d8cc1'}
+/>
+
+### 步骤三：在 LobeChat 中配置 Novita AI
+
+- 访问 LobeChat 的 `设置` 界面
+- 在 `语言模型` 下找到 `novita.ai` 的设置项
+- 打开 novita.ai 并填入获得的 API 密钥
+
+<Image
+  alt={'在 LobeChat 中输入 Novita AI API 密钥'}
+  inStep
+  src={'https://github.com/user-attachments/assets/00c02637-873e-4e7e-9dc3-a95085b16dd7'}
+/>
+
+- 为你的助手选择一个 Novita AI 模型即可开始对话
+
+<Image
+  alt={'Select and use Novita AI model'}
+  inStep
+  src={'https://github.com/user-attachments/assets/6f9f400a-72e0-49de-94cb-5069fddf1163'}
+/>
+
+<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 Novita AI 的相关费用政策。
+</Callout>
+
+</Steps>
+
+至此你已经可以在 LobeChat 中使用 Novita AI 提供的模型进行对话了。

src/app/(main)/settings/llm/ProviderList/providers.tsx

@@ -11,6 +11,7 @@ import {
   Minimax,
   Mistral,
   Moonshot,
+  Novita,
   OpenRouter,
   Perplexity,
   Stepfun,
@@ -35,6 +36,7 @@ import {
   MinimaxProviderCard,
   MistralProviderCard,
   MoonshotProviderCard,
+  NovitaProviderCard,
   OpenRouterProviderCard,
   PerplexityProviderCard,
   QwenProviderCard,
@@ -126,6 +128,11 @@ export const useProviderList = (): ProviderItem[] => {
         docUrl: urlJoin(BASE_DOC_URL, 'openrouter'),
         title: <OpenRouter.Combine iconProps={{ color: OpenRouter.colorPrimary }} size={20} />,
       },
+      {
+        ...NovitaProviderCard,
+        docUrl: urlJoin(BASE_DOC_URL, 'novita'),
+        title: <Novita.Combine size={20} type={'color'} />,
+      },
       {
         ...TogetherAIProviderCard,
         docUrl: urlJoin(BASE_DOC_URL, 'togetherai'),
@@ -179,12 +186,12 @@ export const useProviderList = (): ProviderItem[] => {
       {
         ...BaichuanProviderCard,
         docUrl: urlJoin(BASE_DOC_URL, 'baichuan'),
-        title: <Baichuan.Combine size={ 20 } type={ 'color' } />,
+        title: <Baichuan.Combine size={20} type={'color'} />,
       },
       {
         ...TaichuProviderCard,
         docUrl: urlJoin(BASE_DOC_URL, 'taichu'),
-        title: <AiMass.Combine size={ 28 } type={ 'color' } />,
+        title: <AiMass.Combine size={28} type={'color'} />,
       },
       {
         ...Ai360ProviderCard,

src/app/api/chat/agentRuntime.ts

@@ -172,6 +172,13 @@ const getLlmOptionsFromPayload = (provider: string, payload: JWTPayload) => {
 
       return { apiKey };
     }
+    case ModelProvider.Novita: {
+      const { NOVITA_API_KEY } = getLLMConfig();
+
+      const apiKey = apiKeyManager.pick(payload?.apiKey || NOVITA_API_KEY);
+
+      return { apiKey };
+    }
     case ModelProvider.Baichuan: {
       const { BAICHUAN_API_KEY } = getLLMConfig();
 

src/components/ModelProviderIcon/index.tsx

@@ -12,6 +12,7 @@ import {
   Minimax,
   Mistral,
   Moonshot,
+  Novita,
   Ollama,
   OpenAI,
   OpenRouter,
@@ -117,6 +118,10 @@ const ModelProviderIcon = memo<ModelProviderIconProps>(({ provider }) => {
       return <Stepfun size={20} />;
     }
 
+    case ModelProvider.Novita: {
+      return <Novita size={20} />;
+    }
+
     case ModelProvider.Baichuan: {
       return <Baichuan size={20} />;
     }

src/config/llm.ts

@@ -76,6 +76,9 @@ export const getLLMConfig = () => {
       ENABLED_STEPFUN: z.boolean(),
       STEPFUN_API_KEY: z.string().optional(),
 
+      ENABLED_NOVITA: z.boolean(),
+      NOVITA_API_KEY: z.string().optional(),
+
       ENABLED_BAICHUAN: z.boolean(),
       BAICHUAN_API_KEY: z.string().optional(),
 
@@ -157,6 +160,9 @@ export const getLLMConfig = () => {
       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,
+
       ENABLED_BAICHUAN: !!process.env.BAICHUAN_API_KEY,
       BAICHUAN_API_KEY: process.env.BAICHUAN_API_KEY,
 

src/config/modelProviders/index.ts

@@ -11,6 +11,7 @@ import GroqProvider from './groq';
 import MinimaxProvider from './minimax';
 import MistralProvider from './mistral';
 import MoonshotProvider from './moonshot';
+import NovitaProvider from './novita';
 import OllamaProvider from './ollama';
 import OpenAIProvider from './openai';
 import OpenRouterProvider from './openrouter';
@@ -40,6 +41,7 @@ export const LOBE_DEFAULT_MODEL_LIST: ChatModelCard[] = [
   AnthropicProvider.chatModels,
   ZeroOneProvider.chatModels,
   StepfunProvider.chatModels,
+  NovitaProvider.chatModels,
   BaichuanProvider.chatModels,
   TaichuProvider.chatModels,
   Ai360Provider.chatModels,
@@ -64,6 +66,7 @@ export const DEFAULT_MODEL_PROVIDER_LIST = [
   ZeroOneProvider,
   ZhiPuProvider,
   StepfunProvider,
+  NovitaProvider,
   BaichuanProvider,
   TaichuProvider,
   Ai360Provider,
@@ -89,6 +92,7 @@ export { default as GroqProviderCard } from './groq';
 export { default as MinimaxProviderCard } from './minimax';
 export { default as MistralProviderCard } from './mistral';
 export { default as MoonshotProviderCard } from './moonshot';
+export { default as NovitaProviderCard } from './novita';
 export { default as OllamaProviderCard } from './ollama';
 export { default as OpenAIProviderCard } from './openai';
 export { default as OpenRouterProviderCard } from './openrouter';

src/config/modelProviders/novita.ts

@@ -0,0 +1,91 @@
+import { ModelProviderCard } from '@/types/llm';
+
+const Novita: ModelProviderCard = {
+  chatModels: [
+    {
+      displayName: 'Llama3 8B Instruct',
+      enabled: true,
+      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',
+      enabled: true,
+      id: 'nousresearch/hermes-2-pro-llama-3-8b',
+      tokens: 8192,
+    },
+    {
+      displayName: 'Nous Hermes - Llama2 8B',
+      enabled: true,
+      id: 'nousresearch/nous-hermes-llama2-13b',
+      tokens: 4096,
+    },
+    {
+      displayName: 'Mistral 7B Instruct',
+      enabled: true,
+      id: 'mistralai/mistral-7b-instruct',
+      tokens: 32_768,
+    },
+    {
+      displayName: 'Dolphin Mixtral 8x22B',
+      enabled: true,
+      id: 'cognitivecomputations/dolphin-mixtral-8x22b',
+      tokens: 16_000,
+    },
+    {
+      displayName: 'L3-70b-Euryale-v2.1',
+      enabled: true,
+      id: 'sao10k/l3-70b-euryale-v2.1',
+      tokens: 16_000,
+    },
+    {
+      displayName: 'Midnight Rose 70B',
+      enabled: true,
+      id: 'sophosympatheia/midnight-rose-70b',
+      tokens: 4096,
+    },
+    {
+      displayName: 'Mythomax L2 13b',
+      enabled: true,
+      id: 'gryphe/mythomax-l2-13b',
+      tokens: 4096,
+    },
+    {
+      displayName: 'Nous Hermes 2 - Mixtral 8x7B-DPO',
+      enabled: true,
+      id: 'Nous-Hermes-2-Mixtral-8x7B-DPO',
+      tokens: 32_768,
+    },
+    {
+      displayName: 'Lzlv 70b',
+      enabled: true,
+      id: 'lzlv_70b',
+      tokens: 4096,
+    },
+    {
+      displayName: 'Open Hermes 2.5 Mistral 7B',
+      enabled: true,
+      id: 'teknium/openhermes-2.5-mistral-7b',
+      tokens: 4096,
+    },
+    {
+      displayName: 'Wizardlm2 8x22B',
+      enabled: true,
+      id: 'microsoft/wizardlm-2-8x22b',
+      tokens: 65_535,
+    },
+  ],
+  checkModel: 'meta-llama/llama-3-70b-instruct',
+  disableBrowserRequest: true,
+  id: 'novita',
+  modelList: { showModelFetcher: true },
+  name: 'Novita',
+};
+
+export default Novita;