view release on metacpan or  search on metacpan

lib/Langertha/Engine/Ollama.pm  view on Meta::CPAN

      my $r = $_;
      {
        role    => 'tool',
        content => $self->json->encode($r->{result}{content}),
      }
    } @$results
  );
}

__PACKAGE__->meta->make_immutable;


1;

__END__

=pod

=encoding UTF-8

=head1 NAME

Langertha::Engine::Ollama - Ollama API

=head1 VERSION

version 0.502

=head1 SYNOPSIS

    use Langertha::Engine::Ollama;

    my $ollama = Langertha::Engine::Ollama->new(
        url          => $ENV{OLLAMA_URL},
        model        => 'llama3.3',
        system_prompt => 'You are a helpful assistant',
        context_size => 2048,
        temperature  => 0.5,
    );

    print $ollama->simple_chat('Say something nice');

    my $embedding = $ollama->embedding($content);

    # Get OpenAI-compatible API access to Ollama
    my $ollama_openai = $ollama->openai;

    # List available models
    my $models = $ollama->simple_tags;

    # Show running models
    my $running = $ollama->simple_ps;

=head1 DESCRIPTION

Provides access to Ollama, which runs large language models locally. Ollama
supports many popular open-source models including C<llama3.3> (default),
C<qwen2.5>, C<deepseek-coder-v2>, C<mixtral>, and C<mxbai-embed-large>
(default embedding model).

Supports chat, embeddings, streaming, MCP tool calling (OpenAI-compatible
format), and an OpenAI-compatible API via L</openai>. Not all models support
tool calling; known working models include C<qwen3:8b> and C<llama3.2:3b>.

For Hermes-format tool calling in models without API-level tool support,
compose L<Langertha::Role::HermesTools>. See L<Langertha::Role::HermesTools>
for details.

B<THIS API IS WORK IN PROGRESS>

=head2 openai

    my $oai = $ollama->openai;
    my $oai = $ollama->openai(model => 'different_model');

Returns a L<Langertha::Engine::OllamaOpenAI> instance configured for Ollama's
C</v1> OpenAI-compatible endpoint, inheriting the current model, embedding
model, system prompt, and temperature settings. Supports streaming, embeddings,
and MCP tool calling.

=head2 new_openai

    my $oai = Langertha::Engine::Ollama->new_openai(
        url   => 'http://localhost:11434',
        model => 'llama3.3',
        tools => \@mcp_tools,
    );

Class method. Constructs a native Ollama engine and immediately returns an
L<Langertha::Engine::OllamaOpenAI> instance from its C<openai()> method.
The optional C<tools> list is passed to C<openai()>.

=head2 json_format

When set to a true value, passes C<format => 'json'> to the Ollama API,
requesting JSON-formatted output from the model. Defaults to C<0>.

=head2 tags

    my $request = $ollama->tags;

Returns an HTTP request object for the Ollama C<GET /api/tags> endpoint.
Execute it with C<simple_tags> or pass it to an async HTTP client.

=head2 simple_tags

    my $models = $ollama->simple_tags;
    # Returns: [{name => 'llama3.3', model => 'llama3.3', ...}, ...]

Synchronously fetches and returns the list of locally available models from
the Ollama C</api/tags> endpoint. Also updates the engine's C<models> list.

=head2 ps

    my $request = $ollama->ps;

Returns an HTTP request object for the Ollama C<GET /api/ps> endpoint which
lists currently loaded (running) models.

=head2 simple_ps

    my $running = $ollama->simple_ps;
    # Returns: [{name => 'llama3.3', ...}, ...]

Synchronously fetches and returns the list of models currently loaded in
Ollama's memory from the C</api/ps> endpoint.

=head2 list_models

    my $model_ids = $ollama->list_models;
    my $models    = $ollama->list_models(full => 1);
    my $models    = $ollama->list_models(force_refresh => 1);

Fetches locally available models from Ollama via L</simple_tags> with caching.
Returns an ArrayRef of model name strings by default, or full model objects
when C<full => 1> is passed. Results are cached for C<models_cache_ttl>
seconds (default: 3600).