Class: LLM::Ollama::Models

Inherits:

Object

• Object
• LLM::Ollama::Models

Defined in:

lib/llm/providers/ollama/models.rb

Overview

The LLM::Ollama::Models class provides a model object for interacting with Ollama’s models API. The models API allows a client to query Ollama for a list of models that are available for use with the Ollama API.

Examples:

#!/usr/bin/env ruby
require "llm"

llm = LLM.ollama(nil)
res = llm.models.all
res.each do |model|
  print "id: ", model.id, "\n"
end

Instance Method Summary

• #initialize(provider) ⇒ LLM::Ollama::Models constructor

  Returns a new Models object.

• #all(**params) ⇒ LLM::Response::ModelList

  List all models.

Constructor Details

#initialize(provider) ⇒ LLM::Ollama::Models

Returns a new Models object

Parameters:

• provider (LLM::Provider)

# File 'lib/llm/providers/ollama/models.rb', line 26

def initialize(provider)
  @provider = provider
end

Instance Method Details

#all(**params) ⇒ LLM::Response::ModelList

List all models

Examples:

llm = LLM.ollama(nil)
res = llm.models.all
res.each do |model|
  print "id: ", model.id, "\n"
end

Parameters:

• params (Hash) —

  Other parameters (see Ollama docs)

Returns:

• (LLM::Response::ModelList)

Raises:

• (LLM::Error::Unauthorized) —

  When authentication fails

• (LLM::Error::RateLimit) —

  When the rate limit is exceeded

• (LLM::Error::ResponseError) —

  When any other unsuccessful status code is returned

• (SystemCallError) —

  When there is a network error at the operating system level

See Also:

• Ollama docs
• Ollama library

# File 'lib/llm/providers/ollama/models.rb', line 43

def all(**params)
  query = URI.encode_www_form(params)
  req = Net::HTTP::Get.new("/api/tags?#{query}", headers)
  res = request(http, req)
  LLM::Response::ModelList.new(res).tap { |modellist|
    models = modellist.body["models"].map do |model|
      model = model.transform_keys { snakecase(_1) }
      LLM::Model.from_hash(model).tap { _1.provider = @provider }
    end
    modellist.models = models
  }
end