@creai/shared-core

CreAI Shared Core Library

Core shared library for CreAI assistant services. This library provides essential functionality for building AI-powered assistants with support for various messaging platforms, vector databases, and LLM integrations.

Features

• 🤖 AI Assistant Process Context Management
• 🔄 Message Queue Integration
• 📊 Vector Database Support
• 🎯 LLM Integration
• 🔌 Channel Providers (WhatsApp, Signal, WebSocket)
• 🔒 PII Sanitization
• 🎙️ Audio Transcription
• 🔄 Integration Framework

Installation

npm install @creai/shared-core

Usage

import { AIAssistantProcessContext } from '@creai/shared-core';

// Initialize the assistant context
const assistantContext = {
  // Your assistant configuration
  specialist: 'Customer Support',
  domainTopic: 'Product Support',
  businessName: 'Your Company',
  communicationStyle: 'Professional',
  openAIConfig: {
    api_key: 'your-api-key',
    model: 'gpt-4',
    temperature: 0.7,
    max_tokens: 1000,
  },
  pineconeConfig: {
    apiKey: 'your-pinecone-key',
    environment: 'your-environment',
    projectId: 'your-project-id',
    indexName: 'your-index',
  },
  whatsappConfig: {
    phoneNumberId: 'your-phone-number-id',
    accessToken: 'your-access-token',
  },
};

// Create a message object
const message = {
  message: 'Hello, I need help with my order',
  channelId: 'whatsapp',
  assistantId: 'support-bot',
  product: 'whatsapp_business_account',
};

// Initialize the process context
const processContext = new AIAssistantProcessContext(message, assistantContext);

// Process the message
await processContext.question(message);

Documentation

Assistant Context

The IAssistantContext interface defines the configuration for your assistant:

interface IAssistantContext {
  specialist: string;
  domainTopic: string;
  businessName: string;
  communicationStyle: string;
  openAIConfig: {
    api_key: string;
    model: string;
    temperature: number;
    max_tokens: number;
    top_p?: number;
    presence_penalty?: number;
    frequency_penalty?: number;
    streaming?: boolean;
  };
  pineconeConfig: {
    apiKey: string;
    environment: string;
    projectId: string;
    indexName: string;
  };
  whatsappConfig?: {
    phoneNumberId: string;
    accessToken: string;
  };
  integrationConfig?: {
  salesforce?: {
    instanceUrl: string;
    accessToken: string;
  };
  zendesk?: {
    subdomain: string;
    email: string;
    apiToken: string;
  };
  };
  externalId?: string;
  interactionFlow?: string;
  fallbackResponse?: string;
  timePeriod?: string;
  knowledgeDepth?: string;
  sourcePreference?: string;
  ethicalLimitations?: string[];
  greeting?: string;
}

AIAssistantProcessContext

The main class for handling assistant interactions.

Key methods:

• question(body: IMessageFromQueue): Promise<void> - Process a user question
• transcription(audio: Buffer): Promise<string> - Transcribe audio to text
• queue(message: string, assistantId: string, channelId: string, product: string): Promise<any> - Queue a message for processing
• streamHandler(): (chunk: any) => Promise<void> - Handle streaming responses
• answer(): (chunk: any) => Promise<void> - Handle final responses

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

For support, please open an issue in the GitHub repository.