IntelliNode: AI-Powered Node.js Framework for Building Smart Apps

IntelliNode

Unified prompt, evaluation, and production integration to any large model

Intelligent Node

IntelliNode is a javascript module that integrates cutting-edge AI into your project. With its intuitive functions, you can easily feed data to models like ChatGPT, LLaMA, WaveNet, and Stable diffusion and receive generated text, speech, or images. It also offers high-level functions such as semantic search, multi-model evaluation, and chatbot capabilities.

Access the module

Install

One command and get access to latest models:

npm i intellinode

Examples

Gen

The Gen function quickly generates tailored content in one line.

import:

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

call:

// 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');

Chatbot

import:

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

call:

// set the 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 the responses from the chatbot
const chatbot = new Chatbot(OPENAI_API_KEY, 'openai');
const responses = await chatbot.chat(input);

The documentation on how to switch the chatbot between ChatGPT and LLama in this wiki page.

Semantic search

import:

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

call:

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)

Prompt engineering

Generate improved prompts using LLMs:

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

Language models

import:

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

call openai model:

const langModel = new RemoteLanguageModel('openai-key', 'openai');
model_name = 'text-davinci-003'

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]);

change to call cohere models:

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

Image models

import:

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

call 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
}));

change to call Stable Diffusion:

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

Openai advanced access

To access Openai services from your Azure account, you have to call the following function at the beginning of your application:

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

To access Openai from a proxy for restricted regions:

ProxyHelper.getInstance().setOpenaiProxyValues(openaiProxyJson);

For more details and in-depth code, check the samples.

The code repository setup

First setup

Initiate the project:

cd IntelliNode
npm install

Create a .env file with the access keys:

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>

Test cases

run the remote language models test cases: node test/integration/RemoteLanguageModel.test.js

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

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

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

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

📕 Documentation

• 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.

Pillars

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.

Roadmap

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.
•  Add support to LLaMa AWS private deployment.
•  Add support to Anthropic claude.
•  Add support to Midjourney image generation.
•  Add support to Stable diffusion.
•  Add support to hugging face inference.
•  Add more high-level functions like semantic search, evaluation, etc.

Download Details:

Author: intelligentnode
Source Code: https://github.com/intelligentnode/IntelliNode 
License: Apache-2.0 license

#AI #node #chatgpt #speech #openai