OpenAI PHP for Laravel is a community-maintained PHP API client that allows you to interact with the Open AI API. If you or your business relies on this package, it's important to support the developers who have contributed their time and effort to create and maintain this valuable tool:
- Nuno Maduro: github.com/sponsors/nunomaduro
- Sandro Gehri: github.com/sponsors/gehrisandro
Note: This repository contains the integration code of the OpenAI PHP for Laravel. If you want to use the OpenAI PHP client in a framework-agnostic way, take a look at the openai-php/client repository.
Requires PHP 8.1+
First, install OpenAI via the Composer package manager:
composer require openai-php/laravel
Next, execute the install command:
php artisan openai:install
This will create a config/openai.php
configuration file in your project, which you can modify to your needs
using environment variables.
Blank environment variables for the OpenAI API key and organization id are already appended to your .env
file.
OPENAI_API_KEY=sk-...
OPENAI_ORGANIZATION=org-...
Finally, you may use the OpenAI
facade to access the OpenAI API:
use OpenAI\Laravel\Facades\OpenAI;
$result = OpenAI::chat()->create([
'model' => 'gpt-3.5-turbo',
'messages' => [
['role' => 'user', 'content' => 'Hello!'],
],
]);
echo $result->choices[0]->message->content; // Hello! How can I assist you today?
Configuration is done via environment variables or directly in the configuration file (config/openai.php
).
Specify your OpenAI API Key and organization. This will be used to authenticate with the OpenAI API - you can find your API key and organization on your OpenAI dashboard, at https://openai.com.
OPENAI_API_KEY=
OPENAI_ORGANIZATION=
The timeout may be used to specify the maximum number of seconds to wait for a response. By default, the client will time out after 30 seconds.
OPENAI_REQUEST_TIMEOUT=
For usage examples, take a look at the openai-php/client repository.
The OpenAI
facade comes with a fake()
method that allows you to fake the API responses.
The fake responses are returned in the order they are provided to the fake()
method.
All responses are having a fake()
method that allows you to easily create a response object by only providing the parameters relevant for your test case.
use OpenAI\Laravel\Facades\OpenAI;
use OpenAI\Responses\Completions\CreateResponse;
OpenAI::fake([
CreateResponse::fake([
'choices' => [
[
'text' => 'awesome!',
],
],
]),
]);
$completion = OpenAI::completions()->create([
'model' => 'gpt-3.5-turbo-instruct',
'prompt' => 'PHP is ',
]);
expect($completion['choices'][0]['text'])->toBe('awesome!');
After the requests have been sent there are various methods to ensure that the expected requests were sent:
// assert completion create request was sent
OpenAI::assertSent(Completions::class, function (string $method, array $parameters): bool {
return $method === 'create' &&
$parameters['model'] === 'gpt-3.5-turbo-instruct' &&
$parameters['prompt'] === 'PHP is ';
});
For more testing examples, take a look at the openai-php/client repository.
OpenAI PHP for Laravel is an open-sourced software licensed under the MIT license.