README

这是一个用于Ollama的PHP库。Ollama是一个开源项目，它是一个强大且用户友好的平台，可在本地机器上运行LLM。它充当LLM技术的复杂性与对可访问和可定制AI体验的需求之间的桥梁。

☕️ 买我一杯咖啡

无论您是否使用此项目，是否从中学习到东西，或者只是喜欢它，请考虑通过购买我一杯咖啡来支持它，这样我可以花更多的时间在像这样的开源项目上 :)

目录

• 入门
• 用法
  • 完成资源
    • create()
    • createStreamed()
  • 聊天资源
    • create()
    • createStreamed()
  • 模型资源
    • list()
    • show()
    • create()
    • createStreamed()
    • copy()
    • delete()
    • pull()
    • pullStreamed()
    • push()
    • pushStreamed()
    • runningList()
  • 块资源
    • exists()
    • create()
  • 嵌入资源
    • create()
• 测试
• 变更日志
• 贡献
• 致谢
• 许可

入门

需要 PHP 8.1+
需要 Ollama

您可以在这里找到官方Ollama文档。

首先，通过Composer包管理器安装Ollama PHP

composer require ardagnsrn/ollama-php

然后，您可以创建一个新的Ollama客户端实例

// with default base URL
$client = \ArdaGnsrn\Ollama\Ollama::client();

// or with custom base URL
$client = \ArdaGnsrn\Ollama\Ollama::client('https://:11434');

用法

Completions 资源

create

使用提供的模型为给定的提示生成响应。

$completions = $client->completions()->create([
    'model' => 'llama3.1',
    'prompt' => 'Once upon a time',
]);

$completions->response; // '...in a land far, far away...'

$response->toArray(); // ['model' => 'llama3.1', 'response' => '...in a land far, far away...', ...]

createStreamed

使用提供的模型和流式传输响应为给定的提示生成响应。

$completions = $client->completions()->createStreamed([
    'model' => 'llama3.1',
    'prompt' => 'Once upon a time',
]);


foreach ($completions as $completion) {
    echo $completion->response;
}
// 1. Iteration: '...in'
// 2. Iteration: ' a'
// 3. Iteration: ' land'
// 4. Iteration: ' far,'
// ...

Chat 资源

create

使用提供的模型为给定的提示生成响应。

$response = $client->chat()->create([
    'model' => 'llama3.1',
    'messages' => [
        ['role' => 'system', 'content' => 'You are a llama.'],
        ['role' => 'user', 'content' => 'Hello!'],
        ['role' => 'assistant', 'content' => 'Hi! How can I help you today?'],
        ['role' => 'user', 'content' => 'I need help with my taxes.'],
    ],
]);

$response->message->content; // 'Ah, taxes... *chew chew* Hmm, not really sure how to help with that.'

$response->toArray(); // ['model' => 'llama3.1', 'message' => ['role' => 'assistant', 'content' => 'Ah, taxes...'], ...]

此外，您还可以使用 tools 参数向聊天提供自定义函数。tools 参数不能与 createStreamed 方法一起使用。

$response = $client->chat()->create([
    'model' => 'llama3.1',
    'messages' => [
        ['role' => 'user', 'content' => 'What is the weather today in Paris?'],
    ],
    'tools' => [
        [
            'type' => 'function',
            'function' => [
                'name' => 'get_current_weather',
                'description' => 'Get the current weather',
                'parameters' => [
                    'type' => 'object',
                    'properties' => [
                        'location' => [
                            'type' => 'string',
                            'description' => 'The location to get the weather for, e.g. San Francisco, CA',
                        ],
                        'format' => [
                            'type' => 'string',
                            'description' => 'The location to get the weather for, e.g. San Francisco, CA',
                            'enum' => ['celsius', 'fahrenheit']
                        ],
                    ],
                    'required' => ['location', 'format'],
                ],
            ],
        ]
    ]
]);

$toolCall = $response->message->toolCalls[0];

$toolCall->function->name; // 'get_current_weather'
$toolCall->function->arguments; // ['location' => 'Paris', 'format' => 'celsius']

$response->toArray(); // ['model' => 'llama3.1', 'message' => ['role' => 'assistant', 'toolCalls' => [...]], ...]

createStreamed

使用提供的模型和流式传输响应为给定的提示生成响应。

$responses = $client->chat()->createStreamed([
    'model' => 'llama3.1',
    'messages' => [
        ['role' => 'system', 'content' => 'You are a llama.'],
        ['role' => 'user', 'content' => 'Hello!'],
        ['role' => 'assistant', 'content' => 'Hi! How can I help you today?'],
        ['role' => 'user', 'content' => 'I need help with my taxes.'],
    ],
]);


foreach ($responses as $response) {
    echo $response->message->content;
}
// 1. Iteration: 'Ah,'
// 2. Iteration: ' taxes'
// 3. Iteration: '... '
// 4. Iteration: ' *chew,'
// ...

Models 资源

list

列出所有可用的模型。

$response = $client->models()->list();

$response->toArray(); // ['models' => [['name' => 'llama3.1', ...], ['name' => 'llama3.1:80b', ...], ...]]

show

显示特定模型的详细信息。

$response = $client->models()->show('llama3.1');

$response->toArray(); // ['modelfile' => '...', 'parameters' => '...', 'template' => '...']

create

创建新模型。

$response = $client->models()->create([
    'name' => 'mario',
    'modelfile' => "FROM llama3.1\nSYSTEM You are mario from Super Mario Bros."
]);

$response->status; // 'success'

createStreamed

创建新模型并流式传输响应。

$responses = $client->models()->createStreamed([
    'name' => 'mario',
    'modelfile' => "FROM llama3.1\nSYSTEM You are mario from Super Mario Bros."
]);

foreach ($responses as $response) {
    echo $response->status;
}

copy

复制现有模型。

$client->models()->copy('llama3.1', 'llama3.2'); // bool

delete

删除模型。

$client->models()->delete('mario'); // bool

pull

从Ollama服务器拉取模型。

$response = $client->models()->pull('llama3.1'); 
$response->toArray() // ['status' => 'downloading digestname', 'digest' => 'digestname', 'total' => 2142590208, 'completed' => 241970]

pullStreamed

从Ollama服务器拉取模型并流式传输响应。

$responses = $client->models()->pullStreamed('llama3.1'); 

foreach ($responses as $response) {
    echo $response->status; 
}

push

将模型推送到Ollama服务器。

$response = $client->models()->push('llama3.1');
$response->toArray() // ['status' => 'uploading digestname', 'digest' => 'digestname', 'total' => 2142590208]

pushStreamed

将模型推送到Ollama服务器并流式传输响应。

$responses = $client->models()->pushStreamed('llama3.1');

foreach ($responses as $response) {
    echo $response->status; 
}

runningList

列出所有正在运行的模型。

$response = $client->models()->runningList();

$response->toArray(); // ['models' => [['name' => 'llama3.1', ...], ['name' => 'llama3.1:80b', ...], ...]]

Blobs 资源

exists

检查是否存在块。

$client->blobs()->exists('blobname'); // bool

create

创建新块。

$client->blobs()->create('blobname'); // bool

Embed 资源

create

使用提供的模型为给定的文本生成嵌入。

$response = $client->embed()->create([
    'model' => 'llama3.1',
    'input' => [
        "Why is the sky blue?",
    ]
]);

$response->toArray(); // ['model' => 'llama3.1', 'embedding' => [0.1, 0.2, ...], ...]

测试

composer test

变更日志

有关最近更改的更多信息，请参阅CHANGELOG。

贡献

有关详细信息，请参阅CONTRIBUTING。

致谢

• Arda GUNSUREN
• 所有贡献者

许可

MIT许可（MIT）。有关更多信息，请参阅许可文件。