3527e732d4
Production-ready Next.js boilerplate with: - Runtime env validation (fail-fast on missing vars) - Feature-gated config (S3, Stripe, email, OAuth) - Docker + Coolify deployment pipeline - PostgreSQL + pgvector, MinIO S3, Better Auth - TypeScript strict mode (no ignoreBuildErrors) - i18n (en/es), AI modules, billing, monitoring Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
46 lines
2.1 KiB
Markdown
46 lines
2.1 KiB
Markdown
---
|
|
title: Overview
|
|
description: Get started with AI integration in your TurboStarter project.
|
|
url: /docs/web/ai/overview
|
|
---
|
|
|
|
# Overview
|
|
|
|
For AI integration, TurboStarter leverages the [Vercel AI SDK](https://sdk.vercel.ai/docs/introduction), which provides a comprehensive set of tools and utilities to help you build AI applications more easily and efficiently.
|
|
|
|
<Callout title="Why Vercel AI SDK?">
|
|
It's a simple yet powerful library that exposes a unified API for all major AI providers.
|
|
|
|
This allows you to build your AI application without worrying about the intricacies of each underlying provider's API.
|
|
</Callout>
|
|
|
|
You can learn more about the `ai` package in the [official documentation](https://sdk.vercel.ai/docs/introduction).
|
|
|
|
## Features
|
|
|
|
The starter comes with the most common AI features built-in, such as:
|
|
|
|
* **Chat**: Build chat applications with ease.
|
|
* **Streaming responses**: Stream responses from your AI provider in real-time.
|
|
* **Image generation**: Generate images using AI technology.
|
|
* **Embeddings**: Generate embeddings for your data.
|
|
* **Vector stores**: Store and query your embeddings efficiently.
|
|
|
|
You can easily compose your application using these building blocks or extend them to suit your specific needs.
|
|
|
|
## Providers
|
|
|
|
**TurboStarter relies on the AI SDK to provide support for various AI providers.**
|
|
|
|
This means you can easily switch between different AI providers without changing your code, as long as they are supported by the `ai` package.
|
|
|
|
You can find the list of supported providers in the [official documentation](https://sdk.vercel.ai/providers/ai-sdk-providers).
|
|
|
|
<Callout title="Custom providers">
|
|
There is also the possibility to add your own custom provider. It just needs to implement the common interface and provide all the necessary methods.
|
|
|
|
Read more about this in the [official guide](https://sdk.vercel.ai/providers/community-providers/custom-providers).
|
|
</Callout>
|
|
|
|
The configuration for each provider is straightforward and simple. We'll explore this in more detail in the [Configuration](/docs/web/ai/configuration) section.
|