Laravel AI Chat Starter Kit

The Laravel AI Chat starter kit, created by Pushpak Chhajed, is a modern starter kit that features real-time streaming responses using Prism, Inertia.js, Vue.js, and Tailwind CSS. If you want to quickly set up a new Laravel application with AI chat functionality, this is a good starting point.

#Main Features

• Real-time AI Responses: Stream AI responses as they're generated
• Reasoning Support: Built-in support for AI models with reasoning capabilities
• Multiple AI Providers: Support for OpenAI, Anthropic, Google Gemini, Ollama, Groq, Mistral, DeepSeek, xAI, and VoyageAI
• Authentication System: Built-in user authentication and management
• Appearance Settings: Light/dark mode support with system preference detection
• Custom Theming: Shadcn integration allows easy theme customisation via CSS variables
• Chat Sharing: Share conversations with other users

You can install this starter kit using laravel new:

laravel new --using=pushpak1300/ai-chat my-ai-chat
cd my-ai-chat
composer run dev

As part of this starter kit, there is an app/Enums/ModelName.php file for you to define the names of the models you would like to make available.

<?php
 
declare(strict_types=1);
 
namespace App\Enums;
 
use Prism\Prism\Enums\Provider;
 
enum ModelName: string
{
    case GPT_4O_MINI = 'gpt-4o-mini';
    case GPT_4_1_NANO = 'gpt-4.1-nano';
    case O4_MINI = 'o4-mini';
    // Adding other models
    case MY_NEW_MODEL = 'my-new-model-2-micro'
 
    /**
     * @return array{id: string, name: string, description: string, provider: string}[]
     */
    public static function getAvailableModels(): array
    {
        return array_map(
            fn (ModelName $model): array => $model->toArray(),
            self::cases()
        );
    }
 
    public function getName(): string
    {
        return match ($this) {
            self::GPT_4O_MINI => 'GPT-4o mini',
            self::GPT_4_1_NANO => 'GPT-4.1 Nano',
            self::O4_MINI => 'O4 mini',
            self::MY_NEW_MODEL => 'Human-Readable Name',
        };
    }
 
    public function getDescription(): string
    {
        return match ($this) {
            self::GPT_4O_MINI => 'Cheapest model, best for smarter tasks',
            self::GPT_4_1_NANO => 'Cheapest model, best for simpler tasks',
            self::O4_MINI => 'Reasoning model, best for complex tasks',
            self::MY_NEW_MODEL => 'Brief description of model capabilities',
        };
    }
 
    public function getProvider(): Provider
    {
        return match ($this) {
            self::GPT_4O_MINI => Provider::OpenAI,
            self::GPT_4_1_NANO => Provider::OpenAI,
            self::O4_MINI => Provider::OpenAI,
            self::MY_NEW_MODEL => Provider::YourProvider,
        };
    }
 
    /**
     * @return array{id: string, name: string, description: string, provider: string}
     */
    public function toArray(): array
    {
        return [
            'id' => $this->value,
            'name' => $this->getName(),
            'description' => $this->getDescription(),
            'provider' => $this->getProvider()->value,
        ];
    }
}

Pushpak has several other features on the Roadmap, including Multimodal Support, Tool Call Support, Image Generation, and Resumable Streams. Contributions are welcome, so if you'd like to lend a hand in making this starter kit better with these or any other features, you're invited to do so.

Learn more about this package and view the source code on GitHub.