$git clone https://github.com/intelligentnode/IntelliNode</p>
| 1 | <!-- <p align="center"> |
| 2 | <img src="images/intellinode_new_header.png" width="400em"> |
| 3 | </p> --> |
| 4 | |
| 5 | <p align="center"> |
| 6 | <img src="images/multimodel-banner.png" width="650em"> |
| 7 | </p> |
| 8 | |
| 9 | <h3 align="center"> |
| 10 | Unified prompt, evaluation, and production integration to any large model |
| 11 | </h3> |
| 12 | |
| 13 | <p align="center"> |
| 14 | |
| 15 | <a href="https://www.npmjs.com/package/intellinode" alt="npm version"> |
| 16 | <img src="https://img.shields.io/npm/v/intellinode?style=flat-square" /> |
| 17 | </a> |
| 18 | |
| 19 | <a href="https://www.jsdelivr.com/package/npm/intellinode" alt="licenses tag"> |
| 20 | <img src="https://data.jsdelivr.com/v1/package/npm/intellinode/badge" /> |
| 21 | </a> |
| 22 | |
| 23 | <a href="https://opensource.org/licenses/Apache-2.0" alt="licenses tag"> |
| 24 | <img src="https://img.shields.io/github/license/intelligentnode/IntelliNode?style=flat-square" /> |
| 25 | </a> |
| 26 | |
| 27 | <a href="https://discord.gg/VYgCh2p3Ww" alt="Join our Discord community"> |
| 28 | <img src="https://img.shields.io/badge/Discord-join%20us-5865F2?style=flat-square&logo=discord&logoColor=white" /> |
| 29 | </a> |
| 30 | |
| 31 | </p> |
| 32 | |
| 33 | # Intelligent Node |
| 34 | |
| 35 | 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**, **Gemini** 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. |
| 36 | |
| 37 | # Access the module |
| 38 | ## Install |
| 39 | One command and get access to latest models: |
| 40 | ``` |
| 41 | npm i intellinode |
| 42 | ``` |
| 43 | |
| 44 | For detailed usage instructions, refer to the [documentation](https://docs.intellinode.ai/docs/npm). |
| 45 | |
| 46 | ## Examples |
| 47 | ### Gen |
| 48 | The `Gen` function quickly generates tailored content in one line.<br><br> |
| 49 | import: |
| 50 | ```js |
| 51 | const { Gen } = require('intellinode'); |
| 52 | ``` |
| 53 | call: |
| 54 | ```js |
| 55 | // one line to generate html page code (openai gpt4 is default) |
| 56 | text = 'a registration page with flat modern theme.' |
| 57 | await Gen.save_html_page(text, folder, file_name, openaiKey); |
| 58 | ``` |
| 59 | ```js |
| 60 | // or generate blog post (using cohere) |
| 61 | const blogPost = await Gen.get_blog_post(prompt, apiKey, provider='cohere'); |
| 62 | ``` |
| 63 | |
| 64 | ### Chatbot |
| 65 | import: |
| 66 | ```js |
| 67 | const { Chatbot, ChatGPTInput } = require('intellinode'); |
| 68 | ``` |
| 69 | call GPT-5 (default): |
| 70 | ```js |
| 71 | // set chatGPT system mode and the user message. |
| 72 | const input = new ChatGPTInput('You are a helpful assistant.'); |
| 73 | input.addUserMessage('What is the distance between the Earth and the Moon?'); |
| 74 | |
| 75 | // get chatGPT responses. |
| 76 | const chatbot = new Chatbot(OPENAI_API_KEY, 'openai'); |
| 77 | const responses = await chatbot.chat(input); |
| 78 | ``` |
| 79 | ### Gemini Chatbot |
| 80 | IntelliNode enable effortless swapping between AI models. |
| 81 | 1. imports: |
| 82 | ```js |
| 83 | const { Chatbot, GeminiInput, SupportedChatModels } = require('intellinode'); |
| 84 | ``` |
| 85 | 2. call: |
| 86 | ```js |
| 87 | const input = new GeminiInput(); |
| 88 | input.addUserMessage('Who painted the Mona Lisa?'); |
| 89 | |
| 90 | const geminiBot = new Chatbot(apiKey, SupportedChatModels.GEMINI); |
| 91 | const responses = await geminiBot.chat(input); |
| 92 | ``` |
| 93 | |
| 94 | ### Nvidia DeepSeek |
| 95 | |
| 96 | 1. Import: |
| 97 | ```js |
| 98 | const { Chatbot, NvidiaInput, SupportedChatModels } = require("intellinode"); |
| 99 | ``` |
| 100 | |
| 101 | 2. Call: |
| 102 | ```js |
| 103 | const input = new NvidiaInput("You are an insightful assistant.", {model: 'deepseek-ai/deepseek-r1'}); |
| 104 | input.addUserMessage("What's the summary of the Inception movie?"); |
| 105 | |
| 106 | // visit build.nvidia.com to get your key. |
| 107 | const nvidiaBot = new Chatbot(NVIDIA_API_KEY, SupportedChatModels.NVIDIA); |
| 108 | const responses = await nvidiaBot.chat(input); |
| 109 | ``` |
| 110 | |
| 111 | |
| 112 | The documentation to switch the chatbot between ChatGPT, LLama, Cohere, Mistral and more can be found in the [IntelliNode Wiki](https://github.com/Barqawiz/IntelliNode/wiki/ChatBot). |
| 113 | |
| 114 | ### Semantic search |
| 115 | import: |
| 116 | ```js |
| 117 | const { SemanticSearch } = require('intellinode'); |
| 118 | ``` |
| 119 | call: |
| 120 | ```js |
| 121 | const search = new SemanticSearch(apiKey); |
| 122 | // pivotItem is the item to search. |
| 123 | const results = await search.getTopMatches(pivotItem, searchArray, numberOfMatches); |
| 124 | const filteredArray = search.filterTopMatches(results, searchArray) |
| 125 | ``` |
| 126 | |
| 127 | ### Prompt engineering |
| 128 | Generate improved prompts using LLMs: |
| 129 | ```js |
| 130 | const promp |