ai-chat 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1b559dc1098b7391dbca24aea20c9c631ec770eecaf125dc118a1358d62fba39
-  data.tar.gz: 8e5c4b588ed741e7e07d7cbfa975764e7c8df6bb7ebb27ab7d3f1730924bdca7
+  metadata.gz: 6b050afeef6a27a67c0125c131e9f2825a0201cf1c1781f7f87750705b150ea8
+  data.tar.gz: d87412fd5c1439eaad5eba3d919b6cbb7dfc795e762199beaeb28825dc1d0281
 SHA512:
-  metadata.gz: 934e8b03fee2aade7ec67eb122d78c1d271af3681f8a4ac4712f4ec8e1132a36a2cf9291167d05a44fa2d0a7e7c9096e1ce767ccb277de929e5acc783bf1ff52
-  data.tar.gz: d9edb5b4a0a2fb8da9cab3ad380ef21f66a054438c57bcc202769e4b5688a90e9820ff77a73331b4dceccb7f06bbebfa675264856cc1810fb77eb686575373af
+  metadata.gz: d7e6064820465b1ce64d2fa551e5e92fdf4bb74f6a817e4473a28f69541e431cd84deec12dce1df08fba16041baf27f120e7b37ec6721d40201d138f7f563f69
+  data.tar.gz: f13ebe743b083cd8089fa28e1de37750416b03ce0414eb0b754454f16a1b0bd080abb71c6e2c5b966462b6bda5dc9893dfd530060997a177fce493b1e0782eee

data/README.md

@@ -241,6 +241,27 @@ h.last
 # => "Here's how to boil an egg..."
 ```
 
+## Web Search
+
+To give the model access to real-time information from the internet, we enable the `web_search` feature by default. This uses OpenAI's built-in `web_search_preview` tool.
+
+```ruby
+m = AI::Chat.new
+m.user("What are the latest developments in the Ruby language?")
+m.generate! # This may use web search to find current information
+```
+
+**Note:** This feature requires a model that supports the `web_search_preview` tool, such as `gpt-4o` or `gpt-4o-mini`. The gem will attempt to use a compatible model if you have `web_search` enabled.
+
+If you don't want the model to use web search, set `web_search` to `false`:
+
+```ruby
+m = AI::Chat.new
+m.web_search = false
+m.user("What are the latest developments in the Ruby language?")
+m.generate! # This definitely won't use web search to find current information
+```
+
 ## Structured Output
 
 Get back Structured Output by setting the `schema` attribute (I suggest using [OpenAI's handy tool for generating the JSON Schema](https://platform.openai.com/docs/guides/structured-outputs)):
@@ -412,18 +433,87 @@ l.generate!
 
 **Note**: Images should use `image:`/`images:` parameters, while documents should use `file:`/`files:` parameters.
 
-## Web Search
+## Re-sending old images and files
 
-To give the model access to real-time information from the internet, you can enable the `web_search` feature. This uses OpenAI's built-in `web_search_preview` tool.
+Note: if you generate another API request using the same chat, old images and files in the conversation history will not be re-sent by default. If you really want to re-send old images and files, then you must set `previous_response_id` to `nil`:
 
 ```ruby
-m = AI::Chat.new
-m.web_search = true
-m.user("What are the latest developments in the Ruby language?")
-m.generate! # This may use web search to find current information
+a = AI::Chat.new
+a.user("What color is the object in this photo?", image: "thing.png")
+a.generate! # => "Red"
+a.user("What is the object in the photo?")
+a.generate! # => "I don't see a photo"
+
+b = AI::Chat.new
+b.user("What color is the object in this photo?", image: "thing.png")
+b.generate! # => "Red"
+b.user("What is the object in the photo?")
+b.previous_response_id = nil
+b.generate! # => "An apple"
 ```
 
-**Note:** This feature requires a model that supports the `web_search_preview` tool, such as `gpt-4o` or `gpt-4o-mini`. The gem will attempt to use a compatible model if you have `web_search` enabled.
+If you don't set `previous_response_id` to `nil`, the model won't have the old image(s) to work with.
+
+## Image generation
+
+You can enable OpenAI's image generation tool:
+
+```ruby
+a = AI::Chat.new
+a.image_generation = true
+a.user("Draw a picture of a kitten")
+a.generate! # => "Here is your picture of a kitten:"
+```
+
+By default, images are saved to `./images`. You can configure a different location:
+
+```ruby
+a = AI::Chat.new
+a.image_generation = true
+a.image_folder = "./my_images"
+a.user("Draw a picture of a kitten")
+a.generate! # => "Here is your picture of a kitten:"
+```
+
+Images are saved in timestamped subfolders using ISO 8601 basic format. For example:
+- `./images/20250804T11303912_resp_abc123/001.png`
+- `./images/20250804T11303912_resp_abc123/002.png` (if multiple images)
+
+The folder structure ensures images are organized chronologically and by response.
+
+The messages array will now look like this:
+
+```ruby
+pp a.messages
+# => [
+#   {:role=>"user", :content=>"Draw a picture of a kitten"},
+#   {:role=>"assistant", :content=>"Here is your picture of a kitten:", :images => ["./images/20250804T11303912_resp_abc123/001.png"], :response => #<Response ...>}
+# ]
+```
+
+You can access the image filenames in several ways:
+
+```ruby
+# From the last message
+images = a.messages.last[:images]
+# => ["./images/20250804T11303912_resp_abc123/001.png"]
+
+# From the response object
+images = a.messages.last[:response].images
+# => ["./images/20250804T11303912_resp_abc123/001.png"]
+```
+
+Note: Unlike with user-provided input images, OpenAI _does_ store AI-generated output images. So, if you make another API request using the same chat, previous images generated by the model in the conversation history will automatically be used — you don't have to re-send them. This allows you to easily refine an image with user input over multi-turn chats.
+
+```ruby
+a = AI::Chat.new
+a.image_generation = true
+a.image_folder = "./images"
+a.user("Draw a picture of a kitten")
+a.generate! # => "Here is a picture of a kitten:"
+a.user("Make it even cuter")
+a.generate! # => "Here is the kitten, but even cuter:"
+```
 
 ## Building Conversations Without API Calls
 

data/ai-chat.gemspec

@@ -2,7 +2,7 @@
 
 Gem::Specification.new do |spec|
   spec.name = "ai-chat"
-  spec.version = "0.2.0"
+  spec.version = "0.2.1"
   spec.authors = ["Raghu Betina"]
   spec.email = ["raghu@firstdraft.com"]
   spec.homepage = "https://github.com/firstdraft/ai-chat"

data/lib/ai/chat.rb

@@ -6,6 +6,7 @@ require "marcel"
 require "openai"
 require "pathname"
 require "stringio"
+require "fileutils"
 
 require_relative "response"
 
@@ -17,7 +18,7 @@ module AI
   # :reek:IrresponsibleModule
   class Chat
     # :reek:Attribute
-    attr_accessor :messages, :model, :web_search, :previous_response_id
+    attr_accessor :messages, :model, :web_search, :previous_response_id, :image_generation, :image_folder
     attr_reader :reasoning_effort, :client, :schema
 
     VALID_REASONING_EFFORTS = [:low, :medium, :high].freeze
@@ -29,6 +30,8 @@ module AI
       @model = "gpt-4.1-nano"
       @client = OpenAI::Client.new(api_key: api_key)
       @previous_response_id = nil
+      @image_generation = false
+      @image_folder = "./images"
     end
 
     # :reek:TooManyStatements
@@ -102,6 +105,10 @@ module AI
 
       text_response = extract_text_from_response(response)
 
+      image_filenames = extract_and_save_images(response)
+
+      chat_response.images = image_filenames
+
       message = if schema
         if text_response.nil? || text_response.empty?
           raise ArgumentError, "No text content in response to parse as JSON for schema: #{schema.inspect}"
@@ -111,7 +118,18 @@ module AI
         text_response
       end
 
-      assistant(message, response: chat_response)
+      if image_filenames.empty?
+        assistant(message, response: chat_response)
+      else
+        messages.push(
+          {
+            role: "assistant",
+            content: message,
+            images: image_filenames,
+            response: chat_response
+          }.compact
+        )
+      end
 
       self.previous_response_id = response.id
 
@@ -333,9 +351,83 @@ module AI
       if web_search
         tools_list << {type: "web_search_preview"}
       end
+      if image_generation
+        tools_list << {type: "image_generation"}
+      end
+      tools_list
+    end
+
+    def extract_text_from_response(response)
+      response.output.flat_map { |output|
+        output.respond_to?(:content) ? output.content : []
+      }.compact.find { |content|
+        content.is_a?(OpenAI::Models::Responses::ResponseOutputText)
+      }&.text
+    end
+
+    # :reek:FeatureEnvy
+    def wrap_schema_if_needed(schema)
+      if schema.key?(:format) || schema.key?("format")
+        schema
+      elsif (schema.key?(:name) || schema.key?("name")) &&
+          (schema.key?(:schema) || schema.key?("schema")) &&
+          (schema.key?(:strict) || schema.key?("strict"))
+        {
+          format: schema.merge(type: :json_schema)
+        }
+      else
+        {
+          format: {
+            type: :json_schema,
+            name: "response",
+            schema: schema,
+            strict: true
+          }
+        }
+      end
       tools_list
     end
 
+    # :reek:DuplicateMethodCall
+    # :reek:FeatureEnvy
+    # :reek:ManualDispatch
+    # :reek:TooManyStatements
+    def extract_and_save_images(response)
+      image_filenames = []
+
+      image_outputs = response.output.select { |output|
+        output.respond_to?(:type) && output.type == :image_generation_call
+      }
+
+      return image_filenames if image_outputs.empty?
+
+      # ISO 8601 basic format with centisecond precision
+      timestamp = Time.now.strftime("%Y%m%dT%H%M%S%2N")
+
+      subfolder_name = "#{timestamp}_#{response.id}"
+      subfolder_path = File.join(image_folder || "./images", subfolder_name)
+      FileUtils.mkdir_p(subfolder_path)
+
+      image_outputs.each_with_index do |output, index|
+        next unless output.respond_to?(:result) && output.result
+
+        begin
+          image_data = Base64.strict_decode64(output.result)
+
+          filename = "#{(index + 1).to_s.rjust(3, "0")}.png"
+          filepath = File.join(subfolder_path, filename)
+
+          File.binwrite(filepath, image_data)
+
+          image_filenames << filepath
+        rescue => error
+          warn "Failed to save image: #{error.message}"
+        end
+      end
+
+      image_filenames
+    end
+
     # :reek:UtilityFunction
     # :reek:ManualDispatch
     def extract_text_from_response(response)

data/lib/ai/response.rb

@@ -1,13 +1,17 @@
 module AI
   # :reek:IrresponsibleModule
+  # :reek:TooManyInstanceVariables
   class Response
     attr_reader :id, :model, :usage, :total_tokens
+    # :reek:Attribute
+    attr_accessor :images
 
     def initialize(response)
       @id = response.id
       @model = response.model
       @usage = response.usage.to_h.slice(:input_tokens, :output_tokens, :total_tokens)
       @total_tokens = @usage[:total_tokens]
+      @images = []
     end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ai-chat
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Raghu Betina