WebMind SDK

🚀 The easiest way to add AI to your website

The official WebMind SDK provides simple, powerful integration with AI models from OpenAI, Anthropic, Google, and more through a unified API.

✨ Features

• 🎯 Simple Integration - Add AI to your website in minutes
• 🤖 Multiple AI Providers - Access GPT-4, Claude 3, Gemini Pro, and 50+ models
• 🔄 Automatic Failover - Never worry about downtime
• 💰 Transparent Pricing - Clear usage and billing
• 🔒 Enterprise Security - Bank-level security and encryption
• 📊 Real-time Analytics - Monitor usage and performance
• 🧠 AI Training Support - Contribute to AI improvement with anonymized data collection (opt-in)

🚀 Quick Start

Installation

npm install withwebmind

Basic Usage

import { WebMind } from 'withwebmind'

const ai = new WebMind('your-api-key-here')

// Simple query
const response = await ai.query('Hello, how are you?')
console.log(response.response)

Advanced Usage

import { WebMind } from 'withwebmind'

const ai = new WebMind('your-api-key', {
  baseUrl: 'https://api.withwebmind.com',
  timeout: 30000,
  retries: 3
})

// Query with options
const response = await ai.query('Write a haiku about programming', {
  model: 'gpt-4',
  temperature: 0.8,
  maxTokens: 200,
  systemPrompt: 'You are a creative poet who loves technology'
})

console.log(response.response)
console.log(`Cost: $${response.cost}`)
console.log(`Tokens used: ${response.usage?.totalTokens}`)

Data Collection for AI Training

Help improve AI models by opting into anonymized data collection. Your personal information is never stored.

// Enable data collection for AI training
const response = await ai.query('Explain quantum computing', {
  model: 'gpt-4',
  dataCollection: {
    enabled: true,
    // Optional: provide custom anonymized user ID
    anonymizedUserId: 'user_anonymous_123',
    // Optional: additional metadata
    metadata: {
      category: 'education',
      difficulty: 'intermediate'
    }
  }
})

📚 API Reference

WebMind Class

Constructor

const ai = new WebMind(apiKey: string, config?: WebMindConfig)

Parameters:

• apiKey (string): Your WebMind API key
• config (optional): Configuration options

Config Options:

interface WebMindConfig {
  baseUrl?: string        // API base URL (default: 'https://api.withwebmind.com')
  timeout?: number       // Request timeout in ms (default: 30000)
  retries?: number       // Number of retries on failure (default: 3)
}

Methods

query(prompt, options?)

Query the AI with a prompt.

const response = await ai.query(prompt: string, options?: QueryOptions): Promise<QueryResponse>

Parameters:

• prompt (string): The prompt to send to the AI
• options (optional): Query configuration options

Options:

interface QueryOptions {
  model?: string          // AI model to use (default: 'gpt-3.5-turbo')
  temperature?: number    // Creativity (0-2, default: 0.7)
  maxTokens?: number      // Maximum response length (default: 1000)
  systemPrompt?: string   // System message for context
  stream?: boolean        // Enable streaming response
  webhookUrl?: string     // Webhook URL for notifications
  metadata?: object       // Additional metadata
  dataCollection?: {      // AI training data collection (opt-in)
    enabled?: boolean     // Enable anonymized data collection
    anonymizedUserId?: string // Custom anonymous user ID
    metadata?: object     // Additional training metadata
  }
}

Returns:

interface QueryResponse {
  id: string              // Unique response ID
  response: string        // AI response text
  model: string          // Model used
  usage?: {
    promptTokens: number
    completionTokens: number
    totalTokens: number
  }
  cost: number           // Cost in USD
  responseTime: number   // Response time in ms
  timestamp: string      // ISO timestamp
}

getUsage()

Get current usage statistics.

const usage = await ai.getUsage()
console.log(`Credits: $${usage.credits}`)
console.log(`Spent this month: $${usage.totalSpent}`)

addCredits(amount)

Add credits to your account.

const result = await ai.addCredits(10)
console.log(`New balance: $${result.newBalance}`)

🌐 HTTP API

If you prefer to use HTTP requests directly:

Query Endpoint

curl -X POST https://api.withwebmind.com/v1/query \\
  -H "Authorization: Bearer YOUR_API_KEY" \\
  -H "Content-Type: application/json" \\
  -d '{
    "prompt": "Hello, world!",
    "model": "gpt-4",
    "temperature": 0.7
  }'

Response Format

{
  "success": true,
  "data": {
    "id": "query_123",
    "response": "Hello! How can I help you today?",
    "model": "gpt-4",
    "usage": {
      "promptTokens": 10,
      "completionTokens": 8,
      "totalTokens": 18
    },
    "cost": 0.001,
    "responseTime": 450,
    "timestamp": "2024-01-01T12:00:00.000Z"
  }
}

🔧 Model Support

Free Models (No credits required)

• meta-llama/llama-3.1-8b-instruct:free
• microsoft/wizardlm-2-8x22b
• google/gemma-7b-it:free

Paid Models (Credits required)

• openai/gpt-4
• openai/gpt-3.5-turbo
• anthropic/claude-3-opus
• anthropic/claude-3-sonnet
• google/gemini-pro
• meta-llama/llama-3.1-70b-instruct

💰 Pricing

• Free Tier: 1,000 requests/month
• Paid Models: ~$0.045 per request (varies by model)
• Credits: $1 = 100 credits (never expire)
• No Hidden Fees: Transparent pricing with real-time cost calculation

🔒 Security

• API Key Authentication: Secure Bearer token authentication
• End-to-End Encryption: All requests encrypted in transit
• Rate Limiting: Built-in protection against abuse
• Audit Logging: Complete request/response logging

🚨 Error Handling

The SDK includes comprehensive error handling:

try {
  const response = await ai.query('Hello')
} catch (error) {
  if (error instanceof WebMindError) {
    console.log('Error code:', error.code)
    console.log('Status code:', error.statusCode)
  }
}

Common Error Codes

• MISSING_API_KEY: No API key provided
• INVALID_API_KEY: Invalid API key
• INSUFFICIENT_CREDITS: Not enough credits
• RATE_LIMIT_EXCEEDED: Too many requests
• MODEL_NOT_FOUND: Requested model unavailable

📊 Webhooks

Set up webhooks to receive real-time notifications:

const response = await ai.query('Hello', {
  webhookUrl: 'https://your-site.com/webhook',
  metadata: { userId: '123' }
})

Webhook Payload

{
  "event": "query.completed",
  "data": {
    "id": "query_123",
    "response": "Hello! How can I help?",
    "cost": 0.001
  },
  "metadata": {
    "userId": "123"
  }
}

🎯 Examples

Chatbot Integration

import { WebMind } from 'withwebmind'

const ai = new WebMind('your-api-key')

// Add to your chat interface
async function sendMessage(message: string) {
  try {
    const response = await ai.query(message, {
      model: 'gpt-4',
      temperature: 0.7
    })

    return response.response
  } catch (error) {
    console.error('Chat error:', error)
    return 'Sorry, I encountered an error. Please try again.'
  }
}

Content Generation

const ai = new WebMind('your-api-key')

const blogPost = await ai.query('Write a blog post about AI in healthcare', {
  model: 'claude-3-sonnet',
  maxTokens: 1500,
  systemPrompt: 'You are a professional healthcare technology writer'
})

Code Assistant

const ai = new WebMind('your-api-key')

const codeHelp = await ai.query('How do I implement a binary search in Python?', {
  model: 'gpt-4',
  temperature: 0.3
})

🛠️ Support

• 📖 Documentation
• 💬 Discord Community
• 📧 Email Support
• 🐛 GitHub Issues

📄 License

MIT License - see LICENSE file for details.

Made with ❤️ by the WebMind team