Build Laravel AI Features in Minutes: A Guide to the Gemini Package

composer require hosseinhezami/laravel-gemini

php artisan vendor:publish --tag=gemini-config

# .env
GEMINI_API_KEY=your_gemini_api_key_here

use HosseinHezami\LaravelGemini\Facades\Gemini;

// Simple prompt
$response = Gemini::text()
    ->prompt('Write a tagline for a developer blog.')
    ->generate();

echo $response->content();

// Chat with history
$history = [
    ['role' => 'user', 'parts' => [['text' => 'Hello!']]],
    ['role' => 'model', 'parts' => [['text' => 'Hi there! How can I help?']]]
];

$response = Gemini::text()
    ->prompt('What’s the weather like?')
    ->history($history)
    ->temperature(0.7)
    ->generate();

echo $response->content();

$response = Gemini::text()
    ->structuredSchema([
        'type' => 'object',
        'properties' => [
            'sentiment' => [
                'type' => 'string',
                'enum' => ['positive', 'negative', 'neutral']
            ],
            'confidence' => ['type' => 'number'],
            'key_points' => {
                'type' => 'array',
                'items' => {'type' => 'string'}
            }
        ],
        'required' => ['sentiment']
    ])
    ->prompt('The product is amazing but the delivery was late. I love the features though.')
    ->generate();

$analysis = json_decode($response->content());
// $analysis->sentiment, $analysis->key_points, etc.

$response = Gemini::image()
    ->prompt('A minimalist logo for a tech startup called "Nexus", using blue and green')
    ->generate();

// Save the generated image directly
$response->save(storage_path('app/logo.png'));

// First, upload the file to Gemini's servers
$fileUri = Gemini::files()->upload('document', $pathToInvoicePdf);

// Then, use it in a prompt
$response = Gemini::text()
    ->upload('document', $pathToInvoicePdf) // or use the $fileUri
    ->prompt('What is the total amount due on this invoice?')
    ->generate();

echo $response->content();

$response = Gemini::audio()
    ->prompt('Welcome to our application. We are thrilled to have you on board.')
    ->voiceName('Kore') // Check docs for available voices
    ->generate();

// The package smartly handles the binary response,
// allowing you to save it directly.
$response->save(public_path('audio/welcome.mp3'));

// In your controller (e.g., app/Http/Controllers/ChatController.php)
public function stream(Request $request)
{
    return response()->stream(function () use ($request) {
        Gemini::text()
            ->model('gemini-2.5-flash-lite') // Use a fast model for streaming
            ->prompt($request->query('message'))
            ->stream(function ($chunk) {
                $text = $chunk['text'] ?? '';
                if (connection_aborted()) return;
                echo "data: " . json_encode(['text' => $text]) . "\n\n";
                ob_flush();
                flush();
            });
    }, 200, [
        'Content-Type' => 'text/event-stream',
        'Cache-Control' => 'no-cache',
        'Connection' => 'keep-alive',
        'X-Accel-Buffering' => 'no',
    ]);
}