Class: LLM::OpenAI::Images

Inherits:

Object

• Object
• LLM::OpenAI::Images

Defined in:

lib/llm/providers/openai/images.rb

Overview

The LLM::OpenAI::Images class provides an images object for interacting with OpenAI’s images API. OpenAI supports multiple response formats: temporary URLs, or binary strings encoded in base64. The default is to return temporary URLs.

Examples:

#!/usr/bin/env ruby
require "llm"
require "open-uri"
require "fileutils"

llm = LLM.openai(ENV["KEY"])
res = llm.images.create prompt: "A dog on a rocket to the moon"
FileUtils.mv OpenURI.open_uri(res.urls[0]).path,
             "rocket.png"

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

llm = LLM.openai(ENV["KEY"])
res = llm.images.create prompt: "A dog on a rocket to the moon",
                        response_format: "b64_json"
IO.copy_stream res.images[0], "rocket.png"

Instance Method Summary

• #initialize(provider) ⇒ LLM::OpenAI::Responses constructor

  Returns a new Images object.

• #create(prompt:, model: "dall-e-3", **params) ⇒ LLM::Response::Image

  Create an image.

• #create_variation(image:, model: "dall-e-2", **params) ⇒ LLM::Response::Image

  Create image variations.

• #edit(image:, prompt:, model: "dall-e-2", **params) ⇒ LLM::Response::Image

  Edit an image.

Constructor Details

#initialize(provider) ⇒ LLM::OpenAI::Responses

Returns a new Images object

Parameters:

• provider (LLM::Provider)

# File 'lib/llm/providers/openai/images.rb', line 33

def initialize(provider)
  @provider = provider
end

Instance Method Details

#create(prompt:, model: "dall-e-3", **params) ⇒ LLM::Response::Image

Create an image

Examples:

llm = LLM.openai(ENV["KEY"])
res = llm.images.create prompt: "A dog on a rocket to the moon"
p res.urls

Parameters:

• prompt (String) —

  The prompt

• model (String) (defaults to: "dall-e-3") —

  The model to use

• params (Hash) —

  Other parameters (see OpenAI docs)

Returns:

• (LLM::Response::Image)

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:

• OpenAI docs

# File 'lib/llm/providers/openai/images.rb', line 49

def create(prompt:, model: "dall-e-3", **params)
  req = Net::HTTP::Post.new("/v1/images/generations", headers)
  req.body = JSON.dump({prompt:, n: 1, model:}.merge!(params))
  res = request(http, req)
  LLM::Response::Image.new(res).extend(response_parser)
end

#create_variation(image:, model: "dall-e-2", **params) ⇒ LLM::Response::Image

Create image variations

Examples:

llm = LLM.openai(ENV["KEY"])
res = llm.images.create_variation(image: "/images/hat.png", n: 5)
p res.urls

Parameters:

• image (File) —

  The image to create variations from

• model (String) (defaults to: "dall-e-2") —

  The model to use

• params (Hash) —

  Other parameters (see OpenAI docs)

Returns:

• (LLM::Response::Image)

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:

• OpenAI docs

# File 'lib/llm/providers/openai/images.rb', line 68

def create_variation(image:, model: "dall-e-2", **params)
  image = LLM.File(image)
  multi = LLM::Multipart.new(params.merge!(image:, model:))
  req = Net::HTTP::Post.new("/v1/images/variations", headers)
  req["content-type"] = multi.content_type
  set_body_stream(req, multi.body)
  res = request(http, req)
  LLM::Response::Image.new(res).extend(response_parser)
end

#edit(image:, prompt:, model: "dall-e-2", **params) ⇒ LLM::Response::Image

Edit an image

Examples:

llm = LLM.openai(ENV["KEY"])
res = llm.images.edit(image: "/images/hat.png", prompt: "A cat wearing this hat")
p res.urls

Parameters:

• image (File) —

  The image to edit

• prompt (String) —

  The prompt

• model (String) (defaults to: "dall-e-2") —

  The model to use

• params (Hash) —

  Other parameters (see OpenAI docs)

Returns:

• (LLM::Response::Image)

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:

• OpenAI docs

# File 'lib/llm/providers/openai/images.rb', line 91

def edit(image:, prompt:, model: "dall-e-2", **params)
  image = LLM.File(image)
  multi = LLM::Multipart.new(params.merge!(image:, prompt:, model:))
  req = Net::HTTP::Post.new("/v1/images/edits", headers)
  req["content-type"] = multi.content_type
  set_body_stream(req, multi.body)
  res = request(http, req)
  LLM::Response::Image.new(res).extend(response_parser)
end