google-gemini-php / laravel
Google Gemini PHP for Laravel是一个增强的PHP API客户端,允许您与Google Gemini AI API交互
Requires
- php: ^8.1.0
- google-gemini-php/client: ^1.0
- laravel/framework: ^9.0|^10.0|^11.0
Requires (Dev)
- guzzlehttp/guzzle: ^7.8.1
- laravel/pint: ^1.13.6
- pestphp/pest: ^2.27.0
- pestphp/pest-plugin-arch: ^2.4.1
- phpstan/phpstan: ^1.10.47
- symfony/var-dumper: ^6.4.0|^7.0.1
This package is not auto-updated.
Last update: 2024-09-13 15:53:53 UTC
README
Gemini PHP for Laravel是一个社区维护的PHP API客户端,允许您与Gemini AI API交互。
- Fatih AYDIN github.com/aydinfatih
有关更多信息,请参阅google-gemini-php/client存储库。
目录
先决条件
为了完成此快速入门,请确保您的开发环境满足以下要求
设置
安装
首先,通过Composer包管理器安装Gemini
composer require google-gemini-php/laravel
接下来,执行安装命令
php artisan gemini:install
这将在您的项目中创建一个config/gemini.php配置文件,您可以使用环境变量进行修改以适应您的需求。Gemini API密钥的环境变量已附加到您的.env文件中。
GEMINI_API_KEY=
您还可以定义以下环境变量。
GEMINI_BASE_URL=
GEMINI_REQUEST_TIMEOUT=
设置您的API密钥
要使用Gemini API,您需要一个API密钥。如果您还没有,请在Google AI Studio中创建一个密钥。
使用
与Gemini的API交互
use Gemini\Laravel\Facades\Gemini; $result = Gemini::geminiPro()->generateContent('Hello'); $result->text(); // Hello! How can I assist you today?
聊天资源
纯文本输入
从给定的输入消息生成模型的响应。如果输入仅包含文本,则使用gemini-pro
模型。
$result = Gemini::geminiPro()->generateContent('Hello'); $result->text(); // Hello! How can I assist you today?
文本和图像输入
如果输入包含文本和图像,则使用gemini-pro-vision
模型。
$result = Gemini::geminiProVision() ->generateContent([ 'What is this picture?', new Blob( mimeType: MimeType::IMAGE_JPEG, data: base64_encode( file_get_contents('https://storage.googleapis.com/generativeai-downloads/images/scones.jpg') ) ) ]); $result->text(); // The picture shows a table with a white tablecloth. On the table are two cups of coffee, a bowl of blueberries, a silver spoon, and some flowers. There are also some blueberry scones on the table.
多轮对话(聊天)
使用Gemini,您可以构建多轮的自由对话。
$chat = Gemini::chat() ->startChat(history: [ Content::parse(part: 'The stories you write about what I have to say should be one line. Is that clear?'), Content::parse(part: 'Yes, I understand. The stories I write about your input should be one line long.', role: Role::MODEL) ]); $response = $chat->sendMessage('Create a story set in a quiet village in 1600s France'); echo $response->text(); // Amidst rolling hills and winding cobblestone streets, the tranquil village of Beausoleil whispered tales of love, intrigue, and the magic of everyday life in 17th century France. $response = $chat->sendMessage('Rewrite the same story in 1600s England'); echo $response->text(); // In the heart of England's lush countryside, amidst emerald fields and thatched-roof cottages, the village of Willowbrook unfolded a tapestry of love, mystery, and the enchantment of ordinary days in the 17th century.
对于文本和图像输入的
gemini-pro-vision
模型(用于聊天用例)尚未针对多轮对话进行优化。请确保使用gemini-pro和纯文本输入进行聊天。
流生成内容
默认情况下,模型在完成整个生成过程后返回响应。您可以通过不等待整个结果,而是使用流处理部分结果来实现更快的交互。
$stream = Gemini::geminiPro() ->streamGenerateContent('Write long a story about a magic backpack.'); foreach ($stream as $response) { echo $response->text(); }
计数令牌
在发送任何内容到模型之前,对于长提示,可能有用计数令牌。
$response = Gemini::geminiPro() ->countTokens('Write a story about a magic backpack.'); echo $response->totalTokens; // 9
配置
您发送给模型的每个提示都包含控制模型如何生成响应的参数值。模型可以根据不同的参数值生成不同的结果。有关模型参数的更多信息。
此外,您还可以使用安全设置来调整可能被认为有害的响应的可能性。默认情况下,安全设置阻止所有维度中中等和/或高度可能不安全的内容。有关安全设置的更多信息。
use Gemini\Data\GenerationConfig; use Gemini\Enums\HarmBlockThreshold; use Gemini\Data\SafetySetting; use Gemini\Enums\HarmCategory; $safetySettingDangerousContent = new SafetySetting( category: HarmCategory::HARM_CATEGORY_DANGEROUS_CONTENT, threshold: HarmBlockThreshold::BLOCK_ONLY_HIGH ); $safetySettingHateSpeech = new SafetySetting( category: HarmCategory::HARM_CATEGORY_HATE_SPEECH, threshold: HarmBlockThreshold::BLOCK_ONLY_HIGH ); $generationConfig = new GenerationConfig( stopSequences: [ 'Title', ], maxOutputTokens: 800, temperature: 1, topP: 0.8, topK: 10 ); $generativeModel = Gemini::geminiPro() ->withSafetySetting($safetySettingDangerousContent) ->withSafetySetting($safetySettingHateSpeech) ->withGenerationConfig($generationConfig) ->generateContent("Write a story about a magic backpack.");
嵌入资源
嵌入是一种技术,用于将信息表示为数组中浮点数的列表。使用 Gemini,您可以将文本(单词、句子和文本块)表示为矢量形式,从而更容易进行比较和对比。例如,主题或情感相似的两个文本应该有相似的嵌入,这可以通过余弦相似度等数学比较技术来识别。
使用 embedding-001
模型,可以选择使用 embedContents
或 batchEmbedContents
$response = Gemini::embeddingModel() ->embedContent("Write a story about a magic backpack."); print_r($response->embedding->values); //[ // [0] => 0.008624583 // [1] => -0.030451821 // [2] => -0.042496547 // [3] => -0.029230341 // [4] => 0.05486475 // [5] => 0.006694871 // [6] => 0.004025645 // [7] => -0.007294857 // [8] => 0.0057651913 // ... //]
模型
列出模型
使用列表模型查看可用的 Gemini 模型
$response = Gemini::models()->list(); $response->models; //[ // [0] => Gemini\Data\Model Object // ( // [name] => models/gemini-pro // [version] => 001 // [displayName] => Gemini Pro // [description] => The best model for scaling across a wide range of tasks // ... // ) // [1] => Gemini\Data\Model Object // ( // [name] => models/gemini-pro-vision // [version] => 001 // [displayName] => Gemini Pro Vision // [description] => The best image understanding model to handle a broad range of applications // ... // ) // [2] => Gemini\Data\Model Object // ( // [name] => models/embedding-001 // [version] => 001 // [displayName] => Embedding 001 // [description] => Obtain a distributed representation of a text. // ... // ) //]
获取模型
获取有关模型的信息,例如版本、显示名称、输入令牌限制等。
$response = Gemini::models()->retrieve(ModelType::GEMINI_PRO); $response->model; //Gemini\Data\Model Object //( // [name] => models/gemini-pro // [version] => 001 // [displayName] => Gemini Pro // [description] => The best model for scaling across a wide range of tasks // ... //)
测试
该软件包提供了一个假的 Gemini\Client
类实现,允许您模拟 API 响应。
为了测试您的代码,确保在测试用例中将 Gemini\Client
类替换为 Gemini\Testing\ClientFake
类。
假的响应以创建假客户端时提供的顺序返回。
所有响应都有一个 fake()
方法,允许您通过仅提供与您的测试用例相关的参数来轻松创建响应对象。
use Gemini\Testing\ClientFake; use Gemini\Responses\GenerativeModel\GenerateContentResponse; Gemini::fake([ GenerateContentResponse::fake([ 'candidates' => [ [ 'content' => [ 'parts' => [ [ 'text' => 'success', ], ], ], ], ], ]), ]); $result = Gemini::geminiPro()->generateContent('test'); expect($result->text())->toBe('success');
在流式响应的情况下,您可以选择提供包含假响应数据的资源。
use Gemini\Testing\ClientFake; use Gemini\Responses\GenerativeModel\GenerateContentResponse; Gemini::fake([ GenerateContentResponse::fakeStream(), ]); $result = Gemini::geminiPro()->streamGenerateContent('Hello'); expect($response->getIterator()->current()) ->text()->toBe('In the bustling city of Aethelwood, where the cobblestone streets whispered');
请求发送后,有多种方法可以确保发送了预期的请求。
// assert list models request was sent Gemini::models()->assertSent(callback: function ($method) { return $method === 'list'; }); // or Gemini::assertSent(resource: Models::class, callback: function ($method) { return $method === 'list'; }); Gemini::geminiPro()->assertSent(function (string $method, array $parameters) { return $method === 'generateContent' && $parameters[0] === 'Hello'; }); // or Gemini::assertSent(resource: GenerativeModel::class, model: ModelType::GEMINI_PRO, callback: function (string $method, array $parameters) { return $method === 'generateContent' && $parameters[0] === 'Hello'; }); // assert 2 generative model requests were sent Gemini::assertSent(resource: GenerativeModel::class, model: ModelType::GEMINI_PRO, callback: 2); // or Gemini::geminiPro()->assertSent(2); // assert no generative model requests were sent Gemini::assertNotSent(resource: GenerativeModel::class, model: ModelType::GEMINI_PRO); // or Gemini::geminiPro()->assertNotSent(); // assert no requests were sent Gemini::assertNothingSent();
要编写期望 API 请求失败的测试,您可以将 Throwable
对象作为响应提供。
Gemini::fake([ new ErrorException([ 'message' => 'The model `gemini-basic` does not exist', 'status' => 'INVALID_ARGUMENT', 'code' => 400, ]), ]); // the `ErrorException` will be thrown Gemini::geminiPro()->generateContent('test');