generate_image 0.1.2 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 462b48a0798e5e6d50bffb2386d428b69d43b2c547a0e1bcc7ef01e1ada2fdb3
-  data.tar.gz: 9f6bf6aac0c92744f538aee95c82a64dab88200370891918a6406c77cb047e93
+  metadata.gz: 2de351fd26b27b162f1cadf99e8bebec19eab834a7326add766aa99494ef72d1
+  data.tar.gz: 7fd43c333077f86d8fef116b80b6868ea7da18b1d22ba82b7c43c77a211ea14a
 SHA512:
-  metadata.gz: 3682a51b886ecf2808b6f826bb30243e0b08a2628e93b6011c241fa201ab8abaaecc2195f9f5e46423a347330dbab8286e28fd3795417fb2661c0cf23c939f46
-  data.tar.gz: 5426a9c7093f85c6078f9d6d3deaab45253ca5d538dabe5ffd01c53317e8c452e623f0b071f693367c29702990b313499023ec047c62513bd599996100f5ded7
+  metadata.gz: 20050a7726574a61d88718d29b0f1fb3dde18968a07cd4191f0f4bfaef9bc41b294378da6464e8456008d1804a0960061457dac6baf1e83f32e4d2be3dcf0fb7
+  data.tar.gz: 4ccd64ccd20b3393f471a0df141427e302a0b59d50e051739624ba7df16c81485845dc07d9cb8c8ea67a90a9890a830ee4e5961e35ba5848874bd2357af9fedf

data/README.md

@@ -1,21 +1,31 @@
 # GenerateImage
-The GenerateImage gem is a Ruby gem that provides a simple and easy-to-use interface for generating images using the OpenAI DALL-E API. This gem can be used in Ruby on Rails projects or any other Ruby projects.
+The GenerateImage gem is a Ruby gem that provides an interface for generating images using the OpenAI DALL-E API. This gem can be used in Ruby on Rails projects or any other Ruby projects.
 
-## Usage
-The gem provides a generate_image method, which takes a text argument and returns the generated image URL as a hash. The method makes a request to the DALL-E API to generate an image based on the provided text.
+## Installation
+Add this line to your application's Gemfile:
+
+    gem 'generate_image'
+
+And then execute:
+
+    bundle install
 
-Before using the generate_image method, you must set your OpenAI API key as an environment variable named DALL_E_API_KEY. The gem uses the Net::HTTP library to make API requests and includes error handling to ensure successful image generation. In case of any errors, the method will return a hash with an error key and a message.
+Or install it directly by running:
 
-## Setting the API Key
+    gem install generate_image
+## Usage
+The gem provides a generate_image method, which takes a text argument and returns the generated image URL or image base64 as a hash. The method makes a request to the DALL-E API to generate an image based on the provided text.
 
-Before you can use the generate_image method, you must set your OpenAI API key as an environment variable named DALL_E_API_KEY.
+Before using the generate_image method, you must set your OpenAI API key as an environment variable named DALL_E_API_KEY. The gem uses the Net::HTTP library to make API requests and includes error handling to ensure successful image generation. In case of any errors, the method will raise a RequestFailed exception.
 
-Here's an example of how you can set the environment variable
+### Examples
 
-    DALL_E_API_KEY=your_api_key
+    require 'generate_image'
 
-## Example Usage
+    # Set the DALL-E API key
+    ENV['DALL_E_API_KEY'] = 'your_api_key'
 
+    # Generate a single image with default options
     result = GenerateImage.generate_image('A three-story castle made of ice cream')
     if result[:error]
       puts result[:error]
@@ -23,16 +33,38 @@ Here's an example of how you can set the environment variable
       puts result[:image_url]
     end
 
-## Installation
-### Add this line to your application's Gemfile:
+    # Generate a single image with custom options
+    result = GenerateImage.generate_image('A cat playing the piano', model: 'image-alpha-001', num_images: 2, size: '1024x1024', response_format: 'base64', quality: 90)
+    if result[:error]
+      puts result[:error]
+    else
+      puts result[:image_base64]
+    end
+## Options
+The generate_image method accepts a hash of options to customize the generated images. Here are the available options:
 
-    gem 'generate_image'
-### And then execute:
+`model` - The name of the model to use for generating the images. Default is `image-alpha-001`.
 
-    bundle install
-### Or install it directly by running:
+`num_images` - The number of images to generate. Default is `1`.
+
+`size` - The dimensions of the generated images in the format widthxheight. Default is `512x512`.
+
+`response_format` - The format of the response, either `url` or `base64`. Default is `url`.
+
+`style` - The model or style to use for generating the images. Default is `nil`, which uses the default style of the selected model.
+
+`scale` - The scaling factor for the generated image. Default is `1`.
+
+`seed` - The random seed to use for the generation process. Default is `nil`.
+
+`quality` - The JPEG compression quality of the generated image. Default is `80`.
+
+`text_model` - The name of the model to use for generating text prompts. Default is `text-davinci-002`.
+
+`text_prompt` - The text prompt to use for generating the image. Default is `nil`.
+
+`text_length` - The maximum length of the generated text. Default is `nil`.
 
-    gem install generate_image
 ## Development
 To contribute to the development of this gem, clone the repository and run the following commands to install dependencies and run tests:
 
@@ -40,13 +72,14 @@ To contribute to the development of this gem, clone the repository and run the f
     rake spec
 You can also run bin/console for an interactive prompt to experiment with the code.
 
-### To release a new version, update the version number in version.rb and run:
+To release a new version, update the version number in version.rb and run:
 
     bundle exec rake release
+
 This will create a git tag for the new version, push the git commits and tags, and upload the .gem file to RubyGems.org.
 
 ## Contributing
 Bug reports and pull requests are welcome on the GitHub repository. This project is intended to be a safe and welcoming space for collaboration, and all contributors are expected to adhere to the code of conduct.
 
 ## License
-The GenerateImage gem is open source software, released under the terms of the MIT License.
+The GenerateImage gem is open source software, released under the terms of the MIT License.

data/lib/generate_image/version.rb

@@ -1,3 +1,3 @@
 module GenerateImage
-  VERSION = "0.1.2"
+  VERSION = "1.0.0"
 end

data/lib/generate_image.rb

@@ -2,24 +2,35 @@ require 'net/http'
 require 'json'
 
 module GenerateImage
+  class RequestFailed < StandardError; end
+
   class << self
     API_ENDPOINT = 'https://api.openai.com/v1/images/generations'
-    MODEL_NAME = 'image-alpha-001'
+    IMAGE_MODEL_NAME = 'image-alpha-001'
+    TEXT_MODEL_NAME = 'text-davinci-002'
+    API_KEY = ENV['DALL_E_API_KEY']
 
-    def generate_image(text)
-      api_key = ENV['DALL_E_API_KEY']
-      unless api_key
+    def generate_image(text, options = {})
+      unless API_KEY
         raise StandardError, "API Key not set"
       end
-
       uri = URI(API_ENDPOINT)
       request = Net::HTTP::Post.new(uri)
       request['Content-Type'] = 'application/json'
-      request['Authorization'] = "Bearer #{api_key}"
+      request['Authorization'] = "Bearer #{API_KEY}"
       request.body = {
-        model: MODEL_NAME,
+        model: options[:model] || IMAGE_MODEL_NAME,
         prompt: text,
-        num_images: 1
+        num_images: options[:num_images] || 1,
+        size: options[:size] || '512x512',
+        response_format: options[:response_format] || 'url',
+        style: options[:style] || nil,
+        scale: options[:scale] || 1,
+        seed: options[:seed] || nil,
+        quality: options[:quality] || 80,
+        text_model: options[:text_model] || TEXT_MODEL_NAME,
+        text_prompt: options[:text_prompt] || nil,
+        text_length: options[:text_length] || nil
       }.to_json
 
       response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) do |http|
@@ -27,14 +38,16 @@ module GenerateImage
       end
 
       if response.code == '200'
-        image_url = JSON.parse(response.body)['data'][0]['url']
-        return { image_url: image_url }
+        if options[:response_format] == 'base64'
+          image_base64 = JSON.parse(response.body)['data'][0]['base64']
+          return { image_base64: image_base64 }
+        else
+          image_url = JSON.parse(response.body)['data'][0]['url']
+          return { image_url: image_url }
+        end
       else
-        message = "Failed to generate image. Response code: #{response.code}. Response body: #{response.body}"
-        Rails.logger.error(message) if defined?(Rails)
-        return { error: message }, 500
+        raise RequestFailed, "Failed to generate image. Response code: #{response.code}. Response body: #{response.body}"
       end
     end
   end
 end
-

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: generate_image
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 1.0.0
 platform: ruby
 authors:
 - AMQOR Merouane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-02-13 00:00:00.000000000 Z
+date: 2023-02-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: net-http