> ## Documentation Index
> Fetch the complete documentation index at: https://docs.builderbox.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Integration Overview

> The Builder Box provides a powerful AI integration layer that makes it easy to build AI-powered features in your SaaS application. This documentation will guide you through setting up and using AI capabilities in your application. 

## Key Features

* **Unified AI SDK**: Built on top of Vercel's AI SDK for consistent AI interactions
* **OpenRouter Integration**: Access multiple LLMs through a single API
* **Server Actions**: Type-safe AI operations with Next.js server actions
* **Streaming Support**: Real-time AI responses with streaming capabilities
* **Type Safety**: Full TypeScript support for AI operations
* **RAG Support**: Built-in Retrieval Augmented Generation capabilities
* **Embeddings**: Text embeddings and semantic search functionality
* **Custom Models**: Extensible model registry for custom AI providers

## Getting Started

To start using AI features in your application:

1. Set up your environment variables
2. Configure OpenRouter
3. Use the AI SDK components
4. Implement server actions for AI operations

## Available AI Features

### Basic Features

* Chat interfaces
* Text generation
* Image generation
* Structured data extraction

### Advanced Features

* RAG (Retrieval Augmented Generation)
* Semantic search with embeddings
* Custom model integration
* Advanced streaming with progress tracking
* Circuit breaker and retry patterns

## Architecture

The AI integration follows a modular architecture:

```
lib/ai/
├── openrouter.ts     # OpenRouter client
├── sdk.ts           # AI SDK configuration
├── embeddings.ts    # Text embeddings
├── rag.ts          # RAG implementation
├── vector-store.ts  # Vector storage
└── models/         # Custom model implementations
```

## Best Practices

1. **Model Selection**
   * Choose models based on your use case
   * Consider cost and performance trade-offs
   * Use the most efficient model for your needs

2. **Error Handling**
   * Implement proper error boundaries
   * Use retry logic for transient failures
   * Monitor API usage and errors

3. **Performance**
   * Use streaming for long-running operations
   * Implement proper caching strategies
   * Monitor response times and costs

4. **Security**
   * Validate all inputs and outputs
   * Implement proper access controls
   * Monitor for abuse and rate limiting

## Next Steps

* [Setup Guide](/ai/setup)
* [OpenRouter Integration](/ai/open-router)
* [AI Components](/ai/components)
* [Use Cases](/ai/use-cases)
* [Advanced Features](/ai/advanced)