PHPackages                             ardagnsrn/ollama-php - PHPackages - PHPackages  [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register)

1. [Directory](/)
2. /
3. [Utility & Helpers](/categories/utility)
4. /
5. ardagnsrn/ollama-php

ActiveLibrary[Utility & Helpers](/categories/utility)

ardagnsrn/ollama-php
====================

This is a PHP library for Ollama. Ollama is an open-source project that serves as a powerful and user-friendly platform for running LLMs on your local machine. It acts as a bridge between the complexities of LLM technology and the desire for an accessible and customizable AI experience.

1.0.5(11mo ago)20755.8k—0%21[5 issues](https://github.com/ArdaGnsrn/ollama-php/issues)[1 PRs](https://github.com/ArdaGnsrn/ollama-php/pulls)MITPHPPHP ^8.1CI passing

Since Aug 14Pushed 11mo ago3 watchersCompare

[ Source](https://github.com/ArdaGnsrn/ollama-php)[ Packagist](https://packagist.org/packages/ardagnsrn/ollama-php)[ Docs](https://github.com/ardagnsrn/ollama-php)[ RSS](/packages/ardagnsrn-ollama-php/feed)WikiDiscussions master Synced 1mo ago

READMEChangelogDependencies (4)Versions (7)Used By (0)

Ollama PHP Library
==================

[](#ollama-php-library)

This is a PHP library for Ollama. Ollama is an open-source project that serves as a powerful and user-friendly platform for running LLMs on your local machine. It acts as a bridge between the complexities of LLM technology and the desire for an accessible and customizable AI experience.

[![Total Downloads](https://camo.githubusercontent.com/ad01a8c1c6e466a7a93c75d1363d36102061fafff866c6bbc1baad27de966e7a/68747470733a2f2f696d672e736869656c64732e696f2f7061636b61676973742f64742f61726461676e73726e2f6f6c6c616d612d706870)](https://packagist.org/packages/ardagnsrn/ollama-php)[![Latest Version](https://camo.githubusercontent.com/58bace4e89b934d35ae09cad87a23592e4bbf4be468e5ebf82765c9712328d3e/68747470733a2f2f696d672e736869656c64732e696f2f7061636b61676973742f762f61726461676e73726e2f6f6c6c616d612d706870)](https://packagist.org/packages/ardagnsrn/ollama-php)[![License](https://camo.githubusercontent.com/0fe4a9acc16df01ff709e2b9ce23197123e3c8f6ecf6d0b02fe83532a2f70791/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f6c6963656e73652f61726461676e73726e2f6f6c6c616d612d706870)](https://packagist.org/packages/ardagnsrn/ollama-php)

☕️ Buy me a coffee
------------------

[](#️-buy-me-a-coffee)

Whether you use this project, have learned something from it, or just like it, please consider supporting it by buying me a coffee, so I can dedicate more time on open-source projects like this :)

[![Buy Me A Coffee](https://camo.githubusercontent.com/9f44ce2dc3b3eecdd02598900866ffc518801df1932849703dae1e5ce5031070/68747470733a2f2f7777772e6275796d6561636f666665652e636f6d2f6173736574732f696d672f637573746f6d5f696d616765732f6f72616e67655f696d672e706e67)](https://www.buymeacoffee.com/ardagnsrn)

Table of Contents
-----------------

[](#table-of-contents)

- [Get Started](#get-started)
- [Usage](#usage)
    - [Completions Resource](#completions-resource)
        - [create()](#create)
        - [createStreamed()](#createstreamed)
    - [Chat Resource](#chat-resource)
        - [create()](#create-1)
        - [createStreamed()](#createstreamed-1)
    - [Models Resource](#models-resource)
        - [list()](#list)
        - [show()](#show)
        - [create()](#create-2)
        - [createStreamed()](#createstreamed-2)
        - [copy()](#copy)
        - [delete()](#delete)
        - [pull()](#pull)
        - [pullStreamed()](#pullstreamed)
        - [push()](#push)
        - [pushStreamed()](#pushstreamed)
        - [runningList()](#runninglist)
    - [Blobs Resource](#blobs-resource)
        - [exists()](#exists)
        - [create()](#create-3)
    - [Embed Resource](#embed-resource)
        - [create()](#create-4)
- [Testing](#testing)
- [Changelog](#changelog)
- [Contributing](#contributing)
- [Credits](#credits)
- [License](#license)

Get Started
-----------

[](#get-started)

> **Requires [PHP 8.1+](https://php.net/releases/)**
> **Requires [Ollama](https://ollama.com/)**

> You can find Official Ollama documentation [here](https://github.com/ollama/ollama/blob/main/docs/api.md).

First, install Ollama PHP via the [Composer](https://getcomposer.org/) package manager:

```
composer require ardagnsrn/ollama-php
```

Then, you can create a new Ollama client instance:

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

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

Usage
-----

[](#usage)

### `Completions` Resource

[](#completions-resource)

#### `create`

[](#create)

Generate a response for a given prompt with a provided model.

```
$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`

[](#createstreamed)

Generate a response for a given prompt with a provided model and stream the response.

```
$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` Resource

[](#chat-resource)

#### `create`

[](#create-1)

Generate a response for a given prompt with a provided model.

```
$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...'], ...]
```

Also, you can use the `tools` parameter to provide custom functions to the chat. **`tools` parameter can not be used with `createStreamed` method.**

```
$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`

[](#createstreamed-1)

Generate a response for a given prompt with a provided model and stream the response.

```
$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` Resource

[](#models-resource)

#### `list`

[](#list)

List all available models.

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

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

### `show`

[](#show)

Show details of a specific model.

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

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

### `create`

[](#create-2)

Create a new model.

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

$response->status; // 'success'
```

### `createStreamed`

[](#createstreamed-2)

Create a new model and stream the response.

```
$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`

[](#copy)

Copy an existing model.

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

### `delete`

[](#delete)

Delete a model.

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

### `pull`

[](#pull)

Pull a model from the Ollama server.

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

### `pullStreamed`

[](#pullstreamed)

Pull a model from the Ollama server and stream the response.

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

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

### `push`

[](#push)

Push a model to the Ollama server.

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

### `pushStreamed`

[](#pushstreamed)

Push a model to the Ollama server and stream the response.

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

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

### `runningList`

[](#runninglist)

List all running models.

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

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

### `Blobs` Resource

[](#blobs-resource)

#### `exists`

[](#exists)

Check if a blob exists.

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

#### `create`

[](#create-3)

Create a new blob.

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

### `Embed` Resource

[](#embed-resource)

#### `create`

[](#create-4)

Generate an embedding for a given text with a provided model.

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

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

Testing
-------

[](#testing)

```
composer test
```

Changelog
---------

[](#changelog)

Please see [CHANGELOG](CHANGELOG.md) for more information on what has changed recently.

Contributing
------------

[](#contributing)

Please see [CONTRIBUTING](https://github.com/spatie/.github/blob/main/CONTRIBUTING.md) for details.

Credits
-------

[](#credits)

- [Arda GUNSUREN](https://github.com/ArdaGnsrn)
- [All Contributors](../../contributors)

License
-------

[](#license)

The MIT License (MIT). Please see [License File](LICENSE.md) for more information.

###  Health Score

46

—

FairBetter than 93% of packages

Maintenance51

Moderate activity, may be stable

Popularity49

Moderate usage in the ecosystem

Community18

Small or concentrated contributor base

Maturity53

Maturing project, gaining track record

 Bus Factor1

Top contributor holds 87.9% of commits — single point of failure

How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window.

**Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores.

**Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement.

**Maturity (30%)** — Project age, version count, PHP version support, and release stability.

###  Release Activity

Cadence

Every ~60 days

Recently: every ~43 days

Total

6

Last Release

340d ago

### Community

Maintainers

![](https://www.gravatar.com/avatar/c03ebce320175d5f0ff949dce179582be2e34eadc0ee39e127ccfb36236ce451?d=identicon)[ArdaGnsrn](/maintainers/ArdaGnsrn)

---

Top Contributors

[![ArdaGnsrn](https://avatars.githubusercontent.com/u/52893305?v=4)](https://github.com/ArdaGnsrn "ArdaGnsrn (29 commits)")[![sixty-nine](https://avatars.githubusercontent.com/u/398679?v=4)](https://github.com/sixty-nine "sixty-nine (2 commits)")[![ChobPT](https://avatars.githubusercontent.com/u/45816945?v=4)](https://github.com/ChobPT "ChobPT (1 commits)")[![dependabot[bot]](https://avatars.githubusercontent.com/in/29110?v=4)](https://github.com/dependabot[bot] "dependabot[bot] (1 commits)")

---

Tags

llamallama3llmollamaollama-apiollama-phpopen-source-llmaillmllamamistralollamaArdaGnsrnllama3.1ollama-phpgemma2

###  Code Quality

TestsPest

Code StyleLaravel Pint

### Embed Badge

![Health badge](/badges/ardagnsrn-ollama-php/health.svg)

```
[![Health](https://phpackages.com/badges/ardagnsrn-ollama-php/health.svg)](https://phpackages.com/packages/ardagnsrn-ollama-php)
```

###  Alternatives

[symfony/ai-platform

PHP library for interacting with AI platform provider.

51927.7k136](/packages/symfony-ai-platform)[theodo-group/llphant

LLPhant is a library to help you build Generative AI applications.

1.5k311.5k5](/packages/theodo-group-llphant)[cognesy/instructor-php

The complete AI toolkit for PHP: unified LLM API, structured outputs, agents, and coding agent control

310107.9k1](/packages/cognesy-instructor-php)[soukicz/llm

LLM client with support for cache, tools and async requests

445.6k](/packages/soukicz-llm)[modelflow-ai/symfony-bundle

An integration of modelflow-ai via a bundle into the Symfony Framework.

1518.6k](/packages/modelflow-ai-symfony-bundle)

PHPackages © 2026

[Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)