Skip to main content

​
Configuration

'ollama' => [
    'url' => env('OLLAMA_URL', 'http://localhost:11434'),
],

​
Ollama Options

Ollama allows you to customize how the model is run via options. These options can be passed via the ->withProviderOptions() method: 
Prism::text()
  ->using(Provider::Ollama, 'gemma3:1b')
  ->withPrompt('Who are you?')
  ->withClientOptions(['timeout' => 60])
  ->withProviderOptions([
      'top_p' => 0.9,
      'num_ctx' => 4096,
  ])
Using withProviderOptions will override settings like topP and temperature

​
Streaming

Ollama supports streaming responses from your local models: 
return Prism::text()
    ->using('ollama', 'llama3.2')
    ->withPrompt(request('message'))
    ->withClientOptions(['timeout' => 120])
    ->asEventStreamResponse();
Remember to increase the timeout for local models to prevent premature disconnection.
For complete streaming documentation, see Streaming Output.

​
Considerations

​
Timeouts

Depending on your configuration, responses tend to time out. You may need to extend the client’s timeout using ->withClientOptions(['timeout' => $seconds]): 
Prism::text()
  ->using(Provider::Ollama, 'gemma3:1b')
  ->withPrompt('Who are you?')
  ->withClientOptions(['timeout' => 60])

​
Structured Output

Ollama doesn’t have native JSON mode or structured output like some providers. Prism implements a robust workaround:
  • We automatically append instructions to your prompt that guide the model to output valid JSON matching your schema
  • If the response isn’t valid JSON, Prism will raise a PrismException

​
Limitations

​
Image URL

Ollama does not support images using Image::fromUrl().

​
Tool Choice

Ollama does not currently support tool choice / required tools.

​
Running Local Models

Ollama is perfect for running models locally with complete privacy: 
use Prism\Prism\Facades\Prism;
use Prism\Prism\Enums\Provider;

$response = Prism::text()
    ->using(Provider::Ollama, 'llama3.2')
    ->withPrompt('Explain what a Laravel service provider is')
    ->withClientOptions(['timeout' => 120])
    ->asText();

echo $response->text;
Some popular models available through Ollama:
  • llama3.2 - Meta’s latest Llama model
  • gemma3 - Google’s Gemma models
  • mistral - Mistral AI models
  • phi3 - Microsoft’s Phi-3 models
  • codellama - Code-specialized Llama

​
Installation

To use Ollama:
  1. Install Ollama from ollama.ai
  2. Pull a model: ollama pull llama3.2
  3. Start the Ollama service
  4. Configure Prism with your local URL
# Pull a model
ollama pull llama3.2

# Verify it's running
curl http://localhost:11434

Build docs developers (and LLMs) love

Get started for freeTalk to us