Text

Generate text directly using Prism's text generation API without agents.

Prism Reference

Atlas text generation wraps Prism's text API. For detailed documentation including all options, see Prism Text Generation.

Basic Usage

use Atlasphp\Atlas\Atlas;

$response = Atlas::text()
    ->using('openai', 'gpt-4o')
    ->withSystemPrompt('You are a helpful assistant.')
    ->withPrompt('What is Laravel?')
    ->asText();

echo $response->text;

With Options

$response = Atlas::text()
    ->using('anthropic', 'claude-sonnet-4-20250514')
    ->withSystemPrompt('You are a technical writer.')
    ->withPrompt('Explain dependency injection in PHP.')
    ->withMaxTokens(1000)
    ->withTemperature(0.7)
    ->asText();

With Messages

$response = Atlas::text()
    ->using('openai', 'gpt-4o')
    ->withMessages([
        ['role' => 'user', 'content' => 'Hello!'],
        ['role' => 'assistant', 'content' => 'Hi there! How can I help?'],
        ['role' => 'user', 'content' => 'What is PHP?'],
    ])
    ->asText();

Pipeline Hooks

Text generation supports pipeline middleware for observability:

Pipeline	Trigger
text.before_text	Before text generation
text.after_text	After text generation

use Atlasphp\Atlas\Contracts\PipelineContract;

class LogTextGeneration implements PipelineContract
{
    public function handle(mixed $data, Closure $next): mixed
    {
        $result = $next($data);

        Log::info('Text generated', [
            'user_id' => $data['metadata']['user_id'] ?? null,
        ]);

        return $result;
    }
}

$registry->register('text.after_text', LogTextGeneration::class);

Next Steps

• Chat — Agent-based conversations
• Streaming — Real-time streaming responses
• Prism Text Generation — Complete text generation reference