Merge pull request #590 from alexrudall/feat/multi-image

Add multi-image upload

Author: alexrudall

README.md

@@ -1564,6 +1564,21 @@ puts response.dig("data", 0, "url")
 
 ![Ruby](https://i.ibb.co/sWVh3BX/dalle-ruby.png)
 
+You can also upload arrays of images, eg.
+
+```ruby
+  client = OpenAI::Client.new
+  response = client.images.edit(
+    parameters: {
+      model: "gpt-image-1",
+      image: [File.open(base_image_path, "rb"), "image.png"],
+      prompt: "Take the first image as base and apply the second image as a watermark on the bottom right corner",
+      size: "1024x1024"
+      # Removed response_format parameter as it's not supported with gpt-image-1
+    }
+  )
+```
+
 ### Image Variations
 
 Create n variations of an image.

lib/openai/images.rb

@@ -19,9 +19,23 @@ def variations(parameters: {})
     private
 
     def open_files(parameters)
-      parameters = parameters.merge(image: File.open(parameters[:image]))
-      parameters = parameters.merge(mask: File.open(parameters[:mask])) if parameters[:mask]
-      parameters
+      params = parameters.dup
+
+      if params[:image].is_a?(Array)
+        process_image_array(params)
+      else
+        params[:image] = File.open(params[:image])
+      end
+
+      params[:mask] = File.open(params[:mask]) if params[:mask]
+      params
+    end
+
+    def process_image_array(params)
+      params[:image].each_with_index do |img_path, index|
+        params[:"image[#{index}]"] = File.open(img_path)
+      end
+      params.delete(:image)
     end
   end
 end

spec/fixtures/cassettes/images_edit_multiple.yml

@@ -123,5 +123,26 @@
         end
       end
     end
+
+    describe "with multiple images", :vcr do
+      let(:response) do
+        OpenAI::Client.new.images.edit(
+          parameters: {
+            image: [
+              File.join(RSPEC_ROOT, "fixtures/files", "image.png"),
+              File.join(RSPEC_ROOT, "fixtures/files", "mask.png")
+            ],
+            prompt: "Create a collage from these images",
+            model: "gpt-image-1" # Required for multiple images
+          }
+        )
+      end
+
+      it "converts array of images to image[] parameter" do
+        VCR.use_cassette("images edit multiple") do
+          expect(response.dig("data", 0, "b64_json")).to be_a(String)
+        end
+      end
+    end
   end
 end