ox-ai-workers 0.9.6 → 0.9.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '09fdb6954c507cc0d70433141a70a4974b42feb625719c525d2b7c093d9e1ce5'
-  data.tar.gz: e93b4e8040e831c73d8dd0379466f70e48eafd07513d7e78fee3f19985ef4331
+  metadata.gz: 768550f6fde8e654917a2b01404856abcbe643429ba725d7c86c853b472f4bed
+  data.tar.gz: 9444f8c6869caa2e7039d3632605885579364942de95ba2fa6b201d5ca00c3e5
 SHA512:
-  metadata.gz: c7b1f5a861cc8b4536fd22d6dbe479f0886ebb260317d585bf80ba19c0b1e5dbb6d9c5998ab1e25f367a112a5a7e3dce6bca1a48d2edecb9a6db8af3aa19b1bb
-  data.tar.gz: d7e64a09aa0351a62fdb74c52a25c99db79a4fd7c2765001cd715e8ac32deb6cd2b81aef5e385e57c66aa4b9fb3ef616145eb7953e5eefadc3321ae9678e697f
+  metadata.gz: 6a0c8f3622ab30d8a199b367ad3b0bab3c985a292cc786d3c38380515b5adbe02b945eaff4606073b199a59bf4237bb36c86a0a89b07f6c62c0bc0b738ed7593
+  data.tar.gz: 491720defa83f4b26cccc0d389975f1125c8636821c37314814fdbe9bf714d9233f22456a09b2f8ec890e2b52d3fcb96065295563b1272336316f34461fe6667

data/README.md

@@ -88,6 +88,7 @@ For a more robust setup, you can configure the gem with your API keys, for examp
 OxAiWorkers.configure do |config|
     config.access_token_openai = ENV.fetch("OPENAI")
     config.access_token_deepseek = ENV.fetch("DEEPSEEK")
+    config.access_token_stability = ENV.fetch("STABILITY")
     config.max_tokens = 4096   # Default
     config.temperature = 0.7   # Default
     config.wait_for_complete = true # Default
@@ -420,10 +421,50 @@ image_data = File.read('local_image.jpg')
 iterator.add_image(
   text: 'Image from binary data',
   binary: image_data,
-  mime_type: 'image/jpeg' # Defaults to 'image/jpeg'
+  mime_type: 'image/jpeg' # Defaults to 'image/png'
 )
 ```
 
+#### Image Input Requirements
+
+When using images with the API, your input images must meet the following requirements:
+
+**Supported file types:**
+
+- PNG (.png)
+- JPEG (.jpeg and .jpg)
+- WEBP (.webp)
+- Non-animated GIF (.gif)
+
+**Size limits:**
+
+- Up to 20MB per image
+- Low-resolution: 512px x 512px
+- High-resolution: 768px (short side) x 2000px (long side)
+
+**Other requirements:**
+
+- No watermarks or logos
+- No text
+- No NSFW content
+- Clear enough for a human to understand
+
+**Image detail level:**
+
+The `detail` parameter controls what level of detail the model uses when processing the image:
+
+```ruby
+iterator.add_image(
+  text: 'Nature boardwalk image',
+  url: 'https://example.com/nature.jpg',
+  detail: 'high' # Options: 'auto', 'low', or 'high'
+)
+```
+
+- `detail: 'low'`: Uses less tokens (85) and processes a low-resolution 512px x 512px version of the image. Best for simple use cases like identifying dominant colors or shapes.
+- `detail: 'high'`: Provides better image understanding for complex tasks requiring higher resolution detail.
+- `detail: 'auto'`: Lets the model decide the appropriate detail level (default if not specified).
+
 ### Handling State Transitions with Callbacks
 
 You can track and respond to state transitions with callbacks:
@@ -519,7 +560,7 @@ OxAiWorkers provides several specialized tools to extend functionality:
   pixels = OxAiWorkers::Tool::Pixels.new(
     worker: worker,                 # Required: Request or DelayedRequest instance
     current_dir: Dir.pwd,           # Optional: Directory to save generated images
-    image_model: 'dall-e-3',        # Optional: 'dall-e-3' or 'gpt-image-1'
+    image_model: OxAiWorkers::Models::StabilityImages.new,       # Optional, default is OpenaiDalle3
     only: [:generate_image]         # Optional: Limit available functions
   )
   ```
@@ -654,6 +695,92 @@ module OxAiWorkers
 end
 ```
 
+## Image Generation
+
+OxAiWorkers supports image generation through the Painter assistant and Pixels tool, with multiple AI image generation models.
+
+### Supported Image Models
+
+- **OpenaiDalle3** - OpenAI's DALL-E 3 model
+- **OpenaiGptImage** - OpenAI's GPT-Image-1 model
+- **StabilityImages** - Stability AI's image generation models
+
+### Using the Painter Assistant
+
+```ruby
+# Using DALL-E 3 (default)
+painter = OxAiWorkers::Assistant::Painter.new(current_dir: Dir.pwd)
+painter.task = "Create an image of a sunset over mountains"
+
+# Using GPT-Image-1
+painter = OxAiWorkers::Assistant::Painter.new(
+  image_model: OxAiWorkers::Models::OpenaiGptImage.new,
+  current_dir: Dir.pwd
+)
+painter.task = "Generate a photorealistic red apple"
+
+# Using Stability AI
+painter = OxAiWorkers::Assistant::Painter.new(
+  image_model: OxAiWorkers::Models::StabilityImages.new,
+  current_dir: Dir.pwd
+)
+painter.task = "Create a fantasy landscape with dragons"
+```
+
+### Using the Pixels Tool Directly
+
+For more direct control over image generation:
+
+```ruby
+# Initialize with DALL-E 3
+pixels = OxAiWorkers::Tool::Pixels.new(
+  worker: OxAiWorkers::Models::OpenaiDalle3.new,
+  current_dir: Dir.pwd
+)
+pixels.generate_image(
+  prompt: "A photorealistic red apple on a wooden table",
+  file_name: "apple.png",
+  size: "1024x1024",
+  quality: "hd"
+)
+
+# Initialize with GPT-Image-1
+pixels = OxAiWorkers::Tool::Pixels.new(
+  worker: OxAiWorkers::Models::OpenaiGptImage.new,
+  current_dir: Dir.pwd
+)
+pixels.generate_image(
+  prompt: "Futuristic cityscape at night",
+  file_name: "city.png",
+  size: "1536x1024",
+  quality: "high"
+)
+
+# Initialize with Stability AI
+pixels = OxAiWorkers::Tool::Pixels.new(
+  worker: OxAiWorkers::Models::StabilityImages.new,
+  current_dir: Dir.pwd
+)
+pixels.generate_image(
+  prompt: "Photorealistic mountain landscape",
+  file_name: "mountains.png"
+)
+```
+
+### Model-Specific Features
+
+- **OpenaiDalle3**
+  - Sizes: '1024x1024', '1024x1792', '1792x1024'
+  - Qualities: 'standard', 'hd'
+
+- **OpenaiGptImage**
+  - Sizes: 'auto', '1024x1024', '1536x1024', '1024x1536'
+  - Qualities: 'auto', 'low', 'medium', 'high'
+
+- **StabilityImages**
+  - Uses Stability AI's API with different engine options
+  - Configuration via options parameter
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at <https://github.com/neonix20b/ox-ai-workers>. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/neonix20b/ox-ai-workers/blob/main/CODE_OF_CONDUCT.md).

data/lib/oxaiworkers/assistant/painter.rb

@@ -29,12 +29,6 @@ module OxAiWorkers
           on_outer_voice: ->(text:) { puts "voice: #{text}".colorize(:green) }
         )
       end
-
-      def cleanup
-        Dir.glob(File.join(@current_dir, '*.png')).each do |file|
-          File.delete(file) if File.exist?(file)
-        end
-      end
     end
   end
 end

data/lib/oxaiworkers/iterator.rb

@@ -266,7 +266,7 @@ module OxAiWorkers
       add_raw_context({ role:, content: })
     end
 
-    def add_image(text:, url: nil, binary: nil, role: :user, detail: 'auto', mime_type: 'image/jpeg')
+    def add_image(text:, url: nil, binary: nil, role: :user, detail: 'auto', mime_type: 'image/png')
       content = []
       content << { type: 'text', text: } if text.present?
 

data/lib/oxaiworkers/module_request.rb

@@ -53,10 +53,11 @@ module OxAiWorkers
         frequency_penalty: @model.frequency_penalty
       }
       if @tools.present?
-        parameters[:tools] = @tools.reject do |f|
+        parameters[:tools] = @tools.select do |f|
           tool_name = f[:function][:name]
           tool_name == @last_call && @stop_double_calls.include?(tool_name)
         end
+        OxAiWorkers.logger.debug("tools: #{parameters[:tools]} last_call=#{@last_call} stop_double_calls=#{@stop_double_calls}", for: self.class)
         if @call_stack&.any?
           func1 = @call_stack.first
           @call_stack = @call_stack.drop(1)
@@ -146,7 +147,7 @@ module OxAiWorkers
           name: function['name'].split('__').last,
           args: args
         }
-        @last_call = function['name']
+        @last_call = function['name'].to_s
       end
     end
   end

data/lib/oxaiworkers/tool/pixels.rb

@@ -62,29 +62,9 @@ module OxAiWorkers
         end
       end
 
-      def edit_image(input_image:, prompt:, output_file_name: nil, size: nil, mask: nil)
-        size ||= @image_model['size'].first
-        mask ||= @mask
-
-        response = @worker.client.images.edit(
-          parameters: {
-            image: input_image,
-            model: @image_model['model'],
-            prompt:,
-            size:,
-            mask:
-          }
-        )
-
-        @url = response.dig('data', 0, 'url')
-        revised_prompt = response.dig('data', 0, 'revised_prompt')
-        if output_file_name.present?
-          path = save_generated_image(file_name: output_file_name)
-          "url: #{@url}\nfile_name: #{path}\n\nrevised_prompt: #{revised_prompt}"
-        else
-          "url: #{@url}\n\nrevised_prompt: #{revised_prompt}"
-        end
-      end
+      # def edit_image(input_image:, prompt:, output_file_name: nil, size: nil, mask: nil)
+      #   # TODO: Implement edit_image
+      # end
 
       def save_generated_image(file_name:, binary:)
         unless @current_dir.present?

data/lib/oxaiworkers/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module OxAiWorkers
-  VERSION = '0.9.6'
+  VERSION = '0.9.6.1'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ox-ai-workers
 version: !ruby/object:Gem::Version
-  version: 0.9.6
+  version: 0.9.6.1
 platform: ruby
 authors:
 - Denis Smolev