IntelliNode

统一的提示，评估和生产整合到任何大型模型

智能节点

Intellinode是一个JavaScript模块，将尖端AI集成到您的项目中。 With its intuitive functions, you can easily feed data to models like ChatGPT , LLaMA , WaveNet , Gemini and Stable diffusion and receive generated text, speech, or images.它还提供了高级功能，例如语义搜索，多模型评估和聊天机器人功能。

访问模块

安装

一个命令并访问最新型号：

 npm i intellinode

有关详细的用法说明，请参阅文档。

例子

Gen

Gen函数很快在一行中生成量身定制的内容。

进口：

 const { Gen } = require ( 'intellinode' ) ;

称呼：

 // one line to generate html page code (openai gpt4 is default)
text = 'a registration page with flat modern theme.'
await Gen . save_html_page ( text , folder , file_name , openaiKey ) ; 

 // or generate blog post (using cohere)
const blogPost = await Gen . get_blog_post ( prompt , apiKey , provider = 'cohere' ) ;

聊天机器人

进口：

 const { Chatbot , ChatGPTInput } = require ( 'intellinode' ) ;

称呼：

 // set chatGPT system mode and the user message.
const input = new ChatGPTInput ( 'You are a helpful assistant.' ) ;
input . addUserMessage ( 'What is the distance between the Earth and the Moon?' ) ;

// get chatGPT responses.
const chatbot = new Chatbot ( OPENAI_API_KEY , 'openai' ) ;
const responses = await chatbot . chat ( input ) ;

双子座聊天机器人

Intellinode可以轻松地交换AI模型。

1. 进口：

 const { Chatbot , GeminiInput , SupportedChatModels } = require ( 'intellinode' ) ;

2. 称呼：

 const input = new GeminiInput ( ) ;
input . addUserMessage ( 'Who painted the Mona Lisa?' ) ;

const geminiBot = new Chatbot ( apiKey , SupportedChatModels . GEMINI ) ;
const responses = await geminiBot . chat ( input ) ;

可以在Intellinode Wiki中找到Chatgpt，Llama，Cohere，Mistral等之间切换聊天机器人提供商的文档。

语义搜索

进口：

 const { SemanticSearch } = require ( 'intellinode' ) ;

称呼：

 const search = new SemanticSearch ( apiKey ) ;
// pivotItem is the item to search.
const results = await search . getTopMatches ( pivotItem , searchArray , numberOfMatches ) ;
const filteredArray = search . filterTopMatches ( results , searchArray )

及时的工程

使用LLMS生成改进的提示：

 const promptTemp = await Prompt . fromChatGPT ( "fantasy image with ninja jumping across buildings" , openaiApiKey ) ;
console . log ( promptTemp . getInput ( ) ) ;

语言模型

进口：

 const { RemoteLanguageModel , LanguageModelInput } = require ( 'intellinode' ) ;

致电OpenAI型号：

 const langModel = new RemoteLanguageModel ( 'openai-key' , 'openai' ) ;
model_name = 'gpt-3.5-turbo-instruct'

const results = await langModel . generateText ( new LanguageModelInput ( {
  prompt : 'Write a product description for smart plug that works with voice assistant.' ,
  model : model_name ,
  temperature : 0.7
} ) ) ;

console . log ( 'Generated text:' , results [ 0 ] ) ;

更改以调用Cohere模型：

 const langModel = new RemoteLanguageModel ( 'cohere-key' , 'cohere' ) ;
model_name = 'command-xlarge-20221108'
// ... same code

图像模型

进口：

 const { RemoteImageModel , SupportedImageModels , ImageModelInput } = require ( 'intellinode' ) ;

致电dall·e：

 provider = SupportedImageModels . OPENAI ;

const imgModel = new RemoteImageModel ( apiKey , provider ) ;
const images = await imgModel . generateImages ( new ImageModelInput ( {
    prompt : 'teddy writing a blog in times square' ,
    numberOfImages : 1
} ) ) ;

更改以调用稳定扩散：

 provider = SupportedImageModels . STABILITY ;
// ... same code

Openai高级访问

要从您的Azure帐户访问OpenAI Services，您必须在应用程序开始时调用以下功能：

 const { ProxyHelper } = require ( 'intellinode' ) ;
ProxyHelper . getInstance ( ) . setAzureOpenai ( resourceName ) ;

从限制区域的代理中访问OpenAI：

 ProxyHelper . getInstance ( ) . setOpenaiProxyValues ( openaiProxyJson ) ;

有关更多详细信息和深入代码，请检查样本。

代码存储库设置

第一个设置

1. 启动项目：

 cd IntelliNode
npm install

2. 使用访问键创建一个.ENV文件：
   

 OPENAI_API_KEY=<key_value>
COHERE_API_KEY=<key_value>
GOOGLE_API_KEY=<key_value>
STABILITY_API_KEY=<key_value>
HUGGING_API_KEY=<key_value>

测试用例

1. 运行远程语言模型测试用例： node test/integration/RemoteLanguageModel.test.js

2. run the remote image models test cases: node test/integration/RemoteImageModel.test.js

3. run the remote speech models test cases: node test/integration/RemoteSpeechModel.test.js

4. run the embedding test cases: node test/integration/RemoteEmbedModel.test.js

5. run the chatBot test cases: node test/integration/Chatbot.test.js

文档

• IntelliNode Wiki: Check the wiki page for indepeth instructions and practical use cases.
• Showcase: Experience the potential of Intellinode in action, and use your keys to generate content and html pages.
• Samples: Explore a code sample with detailed setup documentation to get started with Intellinode.
• Model Evaluation: Demonstrate a swift approach to compare the performance of multiple models against designated target answers.
• Semantic Search: In-memory semantic search with iterator over large data.

支柱

The module foundation:

• The wrapper layer provides low-level access to the latest AI models
• The controller layer offers a unified input to any AI model by handling the differences. So you can switch between models like Openai and Cohere without changing the code.
• The function layer provides abstract functionality that extends based on the app's use cases. For example, an easy-to-use chatbot or marketing content generation utilities.

路线图

Call for contributors: registration form .

• Add support to OpenAI completion & GPT4.
• Add support to OpenAI DALL·E 2.
• Add support to other OpenAI functions.
• Add support to cohere generate models.
• Add support to Google language models.
• Add support to Google speech models.
• 为Llama AWS私人部署增加支持。
• 为人类克劳德（Claude）增加支持。
• 为Midjourney图像生成增加支持。
• 增加支持稳定扩散。
• 为拥抱脸推理增加支持。
• 添加更多高级功能，例如语义搜索，评估等。

执照

Apache许可证

版权2023 github.com/barqawiz/intellinode

根据Apache许可证（版本2.0（“许可”）获得许可；除了符合许可外，您不得使用此文件。您可以在

   http://www.apache.org/licenses/LICENSE-2.0

除非适用法律要求或以书面形式同意，否则根据许可证分配的软件是按照“原样”分发的，没有任何明示或暗示的任何形式的保证或条件。请参阅许可证，以获取执行许可条款和限制的特定语言。