IntelliNode v1.8.8

What's New 🌟

• Enhanced the HTML and dashboard generate functions to support GPT omni model.
• Increased the input size capacity for improved performance.

Using the New Features 💻

• Upload any csv file and generate html dashboards with one click: Intellinode analyst.
• Write a prompt and generate html pages ready to download: Intellinode coder.

IntelliNode v1.8.5

What's New 🌟

• Support ANTHROPIC Models: Our chatbot integration supports advanced Claude models, including those with large context windows.

For usage instructions check the chatbot docs.

IntelliNode v1.8.1

What's New 🌟

• Updated to the latest version of openai embedding: text-embedding-3.
• Introduced document name reference in chatbot responses for source clarity.

Getting Started with the New Features 💻

• Data Upload: Go to IntelliNode App to upload your documents.
• Intellinode Key: Generate the one key for integrating the data with the chatbot.
• Implementation: Use the attachReference option when interacting with the chatbot to include document references in responses.

For detailed instructions, visit our Connecting Your Data to Chatbots guide.

Contributors

@gutyoh @Barqawiz

IntelliNode v1.7.9

New Changes 🌟

• Add google gemini embedding function.
• Update the evaluator to include the latest chatbot models (Gemini and Mistral AI).

Using the New Features 💻

LLM evaluator example:

1. Imports and chatbot config

const { LLMEvaluation, SupportedChatModels } = require('intellinode')

// prepare the configurations
const openaiChat = { apiKey: process.env.OPENAI_API_KEY, provider: SupportedChatModels.OPENAI, type: 'chat', model: 'gpt-3.5-turbo' };
const geminiChat = { apiKey: process.env.GEMINI_API_KEY, provider: SupportedChatModels.GEMINI, type: 'chat', model: 'gemini' };
const mistralChat = { apiKey: process.env.MISTRAL_API_KEY, provider: SupportedChatModels.MISTRAL, type: 'chat', model: 'mistral-medium' };

const providerSets = [openaiChat, geminiChat, mistralChat];

2. Prepare the testing data

// pivot string to test the models
const inputString = "Explain the process of photosynthesis in simple terms.";

// optimal answers - adding more answers will make the evaluation more robust
const targetAnswers = ["Photosynthesis is the process where green plants use sunlight to turn carbon dioxide and water into glucose and oxygen. The glucose provides food for the plant, and the oxygen gets released back into the air.",
    "Photosynthesis is how plants make their own food. They take in water and carbon dioxide, use the energy from sunlight to transform them into glucose (their food) and oxygen, which they release into the air."];

3. Call the evaluator and print the results

const results = await llmEvaluation.compareModels(inputString, targetAnswers, providerSets);
console.log('Model Evaluation Results:', results);

Contributors

• @Barqawiz
• @gutyoh

IntelliNode v1.7.7

New Changes 🌟

• Expand our list of supported models to include Google Gemini chat and vision.
• Add Gemini as a provider for the chatbot function.
• Add fine-tuning function starting with chatGPT.

Using the New Features 💻

Example to call Gemini chatbot:

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

const chatbot = new Chatbot(apiKey, SupportedChatModels.GEMINI);

// prepare the input
const input = new GeminiInput();
input.addUserMessage('What is the distance between the Earth and the Moon?');

// get the responses
const responses = await chatbot.chat(input);

// print all candidates
responses.forEach(response => console.log('- ', response));

Available chatbot providers

• SupportedChatModels.OPENAI
• SupportedChatModels.REPLICATE
• SupportedChatModels.SAGEMAKER
• SupportedChatModels.COHERE
• SupportedChatModels.MISTRAL
• SupportedChatModels.GEMINI

IntelliNode v1.7.2

New Changes 🌟

• Add Mistral AI's embedding and text generation models.
• Expand the chatbot versatility by adding Mistral AI model as provider.
• Resolve an issue integrating semantic search with Next.js applications.

Using the New Features 💻

1. Obtain your Mistral API key from mistral.ai.

2. Import the chatbot functions:

const { Chatbot, MistralInput, SupportedChatModels } = require("intellinode");

3. Initiate the Chatbot with MISTRAL provider.

// Initialize the Mistral chatbot
const mistralBot = new Chatbot(mistralApiKey, SupportedChatModels.MISTRAL);

// Create your art assistant input
const input = new MistralInput("You are a helpful art assistant.");
input.addUserMessage("Who is the most renowned Italian painter?");

// Retrieve and log chatbot responses
const responses = await mistralBot.chat(input);

Available chatbot providers

• SupportedChatModels.OPENAI
• SupportedChatModels.REPLICATE
• SupportedChatModels.SAGEMAKER
• SupportedChatModels.COHERE
• SupportedChatModels.MISTRAL

Contributors

• @Barqawiz
• @gutyoh

IntelliNode v1.6.3

New Changes 🌟

• Create document agents by using a chatbot with intellinode one key, allowing you to chat with your files and documents. With this update, you can get answers related to PDF, word, epub, image, JSON, and any text file with minimum configurations.

Code Examples 💻

1. Upload your documents to indellinode.ai cloud and generate one key.
2. Create the chatbot with one key and get answers related to your documents.

const oneKey = process.env.INTELLI_ONE_KEY

// openai bot
const openaiBot = new Chatbot(openaiKey, SupportedChatModels.OPENAI, null, 
          {oneKey:oneKey});


// llama bot
const replicateBot = new Chatbot(replicateApiKey, SupportedChatModels.REPLICATE, null, 
          {oneKey:oneKey});


// cohere bot
const bot = new Chatbot(process.env.COHERE_API_KEY, SupportedChatModels.COHERE, null,
                  {oneKey:oneKey}); 

3. Example to get the naswers

const input = new ChatGPTInput("You are a helpful astronomy assistant.");
input.addUserMessage("Tell me about the Mars the Red Planet? summarize the context");
// get chatbot responses
const responses = await bot.chat(input);

Note that the one key access is limited seats at the moment, register on the intellinode.ai waiting list for an early trial.

IntelliNode v1.5.3

New Changes 🌟
The changes between v1.4.2 and v1.5.3 releases:

• Add support for OpenAI Text-to-Speech.
• Update OpenAI Vision model for DALL·E 3 integration.
• Introduce Cohere Web Search functionality.
• Added support for LLaMa embeddings.

Code Examples 💻
A sneak peek at web search with cohere model:

const CohereAIWrapper = require('intellinode');
const cohere = new CohereAIWrapper(process.env.COHERE_API_KEY);

const params = {
      model: 'command-nightly',
      message: 'what is the command to install intellinode npm module ?',
      stream: false,
      connectors: [{'id': 'web-search'}],
    };

 const result = await cohere.generateChatText(params);

IntelliNode v1.4.2

New Changes 🌟

• Add a chat context function to manage the relevant messages for chatbots.
• Update the module to support next.js integration.

Code Examples 💻

• Check example of next.js integration with a modern chatbot interface.

• Try the below Code to manage the chatbot history strategy.

const { ChatContext } = require('intellinode');
const context = new ChatContext(apiKey);

# Parameters
const userMessage = "Hello";
const historyMessages = ["Good morning", "Dinner time", "How can I help you?", "Hello"];
const n = 3;

# Execute the filter 
const resultContext = await context.getStringContext(userMessage, historyMessages, n);

This code manages the chatbot window size limitation by returning the relevant messages for the user input. Define a window size (n), and the function will filter the last two messages in addition to the relevant ones from the history fitting the window size.

Full chat context sample available here

Contributors 👏

• @Eytyy fixed next.js integration.
• @Barqawiz added the chat context functionality.

IntelliNode v1.3.9

New Changes 🌟

• ChatGPT Streaming: Added support for ChatGPT streaming, allowing users to receive a stream of responses instead of waiting for the entire conversation to complete.
• OpenAI Whisper Support: Added support for speech-to-text functionality.

Code Examples 💻

• Install the module: npm i intellinode
• Code example for ChatGPT streaming: test_chatbot.js.
• Chatbot documentation with streaming instructions.

Contributors 👏

• @Barqawiz updated the chatbot to support streaming.
• @pushoo-sharma added whisper integration.