Black Friday Sale 40% Off•Sale end soon

PaceUI

  • Components
  • Blocks
  • Templates
  • Studio
  • Resources
Docs
  • Introduction
  • Installation
Starter
  • Overview
  • Getting Started
  • Folder Structure
  • AI
  • Auth Basic
  • Auth OAuth
  • Database
  • Documentation
  • Email Resend
  • Payment Creem
  • Payment Polar
  • Storage
  1. Docs
PreviousNext

AI

Vercel AI SDK text and image generation wired into the PaceUI Starter.

Starter comes with a pre-configured Chat And Image generation AI features set using the Vercel AI SDK. It includes built-in support for Gemini and a robust mocking system for local development.

1. Add AI Environment Variables

Generate a Gemini API key from Google AI Studio and add it to your .env file.

.env
GOOGLE_GENERATIVE_AI_API_KEY=your_gemini_key

2.Model Configuration

To switch providers (e.g., to OpenAI), simply update the provider factory and model strings in this file (its also type-safe).

config.ts
const openAIModel = openai("model-of-your-choice");

Architecture

The AI feature is split into server-side logic and client-side state management:

1. Server Actions (chat.ts, image.ts)

These files export generateTextFn and generateImageFn. They interact directly with the AI SDK.

  • Security: These functions utilize "use server" to ensure AI logic and environment variables are executed exclusively on the server, preventing sensitive configurations from being exposed to the client.
  • Mocking: By default, these import models from config.mock.ts. To use real AI, change the import to ./config.

2. Client Hooks (use-image-gen.ts)

We use TanStack Form and TanStack Query to manage the AI lifecycle:

  • Validation: zod handles prompt length, image constraints and form reset.
  • Mutation: useMutation triggers the server action and handles the loading state.
  • State: The history state keeps track of generations within the current session.

AI Image Studio

The ImageGeneration component is a complete "Studio" UI:

  • GenerationForm: A controlled form for prompts, dimensions, and image counts.
  • GenerationGallery: A real-time feed that displays generated images as base64 strings.
  • Auto scroll: The gallery automatically scrolls to the newest generation upon success.

Common Tasks

TaskAction
Go LiveChange imports in chat.ts/image.ts from ./config.mock to ./config.
Change ConstraintsUpdate the Zod schema in user-image-gen.ts.
Switch ProviderInstall the SDK (e.g., @ai-sdk/openai) and update config.ts.

Best Practices

  • Mocking: Keep using config.mock.ts during UI development to avoid unnecessary costs.
  • Data Persistence: The default setup does not store images in a database. If you need persistence, integrate the response from generateImageFn with your database and S3 bucket.
Folder StructureAuth Basic

PaceUI

Animated blocks, components, and templates for Next.js and TanStack Start. Built with Motion and shadcn - clean code you own.

GitHubTwitterDiscord

Products

BlocksComponentsTemplatesCraftsTanStack ChartsMCP ServerStarter KitsStyleX Components

Resources

DocumentationMotion ComponentsGSAP AnimationsNative AIBlogChangelog

Pricing & Account

PricingManage AccountLicensesAPI KeysAffiliate Program

Company

Contact UsDiscord CommunityPrivacy PolicyTerms of Service

© 2026 PaceUI. All rights reserved. Built by indie developer, Denish

PACEUI