Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/phpaisdk/ollama/llms.txt

Use this file to discover all available pages before exploring further.

The PHP AI SDK Ollama provider connects your PHP application to any model running on a local or remote Ollama server. It supports the full generation surface — text, streaming, embeddings, and experimental image generation — through a clean, framework-agnostic interface that works with any PSR-18 HTTP client.

Installation

Install via Composer and get the provider running in under a minute

Quickstart

Generate your first response from a local Ollama model

Guides

Explore text generation, streaming, embeddings, and image generation

API Reference

Full reference for the Ollama facade, provider, models, and types

​
What’s included

Text Generation

Chat Completions and Responses API support, with vision, tool calling, reasoning, and structured output

Streaming

Real-time server-sent event streaming for any installed text model

Embeddings

Native batch embeddings via Ollama’s /api/embed endpoint with dimension control

Image Generation

Experimental image generation through Ollama’s OpenAI-compatible endpoint

Model Discovery

List installed models and inspect their capabilities from the live server

Configuration

Base URL, native URL, API key, and per-request API endpoint overrides

​
Getting started

1

Install the package

Add the provider to your project with Composer:
composer require aisdk/ollama
2

Start Ollama

Make sure Ollama is running locally with at least one model pulled:
ollama pull llama3.2
ollama serve
3

Generate your first response

use AiSdk\Generate;
use AiSdk\Ollama;

$result = Generate::text()
    ->model(Ollama::model('llama3.2'))
    ->prompt('Explain closures in PHP.')
    ->run();

echo $result->text;
No API key is required for a local Ollama server. The provider defaults to http://localhost:11434/v1. See Configuration if your server runs elsewhere or requires authentication.

Build docs developers (and LLMs) love

Get started for freeTalk to us