mindee 5.2.1 → 5.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: addb1d4afceb4816df637946d7d0028da0459681ae05ecf5ce9550f5a2329b2c
-  data.tar.gz: f495ddafda38ba5f5cf6c0e00e88a331a32264a297704a941136d61b660700a8
+  metadata.gz: d8eb9e96fa7c4b8a41479c87152f858112a72c52f18c23ad247c220615d4df15
+  data.tar.gz: 44da90b0f6e814f13cd418502998e3e17610e76857199744c8f2e98b217d72c0
 SHA512:
-  metadata.gz: 2e2784c6fb7c8a8cb98eb1bb6d191b451899fbd4c4a4ae985d8f7d0271b4aa2a97edc64a0b084a700d8769def4b0400cdab24393b3eb7b1f14726407d7f2c93b
-  data.tar.gz: 6718cc7f954306771effbc7e96236bd246ed7aaf34f6296278d55cc821e3d850e54ce03608c64d7d81cb05d4b4ed8cf4055e2d0c08ec4ec315c0dfc0d948a188
+  metadata.gz: 543a63c5085472676f044b20721f03844ad3f425f4fef936c147240b0c286da6f81d8ceffb9ebb90b6c70340426e0529350406b0acfb685176cedb85968ddc06
+  data.tar.gz: 591a11727b309a1ac91840ae3dc260f1bcd5186c840b82a71bdc815a8dd3741500191801491ce25edcc44178077d5dd02d437b1c388f9164f1b80c49114a9ea4

data/CHANGELOG.md

@@ -1,5 +1,21 @@
 # Mindee Ruby API Library Changelog
 
+## v5.3.0 - 2026-07-03
+### Changes:
+* :memo: add SKILL file
+* :recycle: use generic array types for images, PDFs
+* :sparkles: allow passing webhooks to the CLI
+* :sparkles: add webhook error response
+### Fixes:
+* :bug: fix for extraction method naming
+
+## v5.2.2 - 2026-06-18
+### Changes
+* :recycle: refactor CLI to conform with other client libraries
+* :recycle: add secondary accessor for search model pagination to match json return
+* :recycle: ensure HEIF images are detected as such and properly handled
+
+
 ## v5.2.1 - 2026-05-27
 ### Changes
 * :recycle: add polling options as a dedicated parameter (#252)

data/SKILL.md

@@ -0,0 +1,172 @@
+# Mindee Ruby SDK
+
+Use this skill for Mindee V2 integrations with the official Ruby SDK.
+
+## Scope
+
+- Use the official `mindee` Ruby gem.
+- Focus on SDK-based integration patterns only.
+- Do not suggest direct HTTP calls, cURL, or non-SDK integrations.
+- Do not use undocumented SDK internals.
+
+## Primary documentation
+
+### SDK overview
+- https://docs.mindee.com/integrations/client-libraries-sdk.md
+
+### Client setup
+- https://docs.mindee.com/integrations/client-libraries-sdk/configure-the-client.md
+
+### Model parameters
+- https://docs.mindee.com/integrations/client-libraries-sdk/basic-model-configuration.md
+
+### Load local files
+- https://docs.mindee.com/integrations/client-libraries-sdk/load-and-adjust-a-file.md
+
+### Load remote URLs
+- https://docs.mindee.com/integrations/client-libraries-sdk/load-an-url.md
+
+### Send files and URLs
+- https://docs.mindee.com/integrations/client-libraries-sdk/send-a-file-or-url.md
+
+### Process responses
+- https://docs.mindee.com/integrations/client-libraries-sdk/process-the-response.md
+
+### Handle errors
+- https://docs.mindee.com/integrations/problem-database.md
+
+## Handling responses by model type
+
+### Extraction
+- Use: https://docs.mindee.com/extraction-models/sdk-integration/extraction-result.md
+- Use this page for accessing dynamic fields from `response.inference.result.fields`.
+- Use this page for examples of `SimpleField`, `ObjectField`, `ListField`, confidence, and locations.
+
+### Split
+- Use: https://docs.mindee.com/split-models/sdk-integration/split-result.md
+- Use this page for iterating over `response.inference.result.splits`.
+- Use this page for `document_type`, `page_range`, and optional chained extraction results.
+
+### Crop
+- Use: https://docs.mindee.com/crop-models/sdk-integration/crop-result.md
+- Use this page for iterating over `response.inference.result.crops`.
+- Use this page for `object_type`, crop location, polygon data, and optional chained extraction results.
+
+### Classification
+- Use: https://docs.mindee.com/classification-models/sdk-integration/classification-result.md
+- Use this page for accessing `response.inference.result.classification`.
+- Use this page for `document_type` and optional chained extraction results.
+
+### OCR
+- Use: https://docs.mindee.com/raw-text-ocr-models/sdk-integration/ocr-result.md
+- Use this page for iterating over `response.inference.result.pages`.
+- Use this page for page text (`content`), words, and word polygon data.
+
+## Default workflow
+
+When answering questions, follow this order:
+
+1. Initialize the SDK client.
+2. Configure `model_id` and other inference parameters.
+3. Load the input source.
+4. Optionally adjust the file before upload.
+5. Send with polling or webhooks.
+6. Process the response.
+7. Handle errors and retries.
+
+## Answering rules
+
+- Base answers on the documentation above.
+- Prefer documented SDK methods and patterns.
+- Use environment variables for API keys in production.
+- Reuse a client instance when possible.
+- Prefer polling for simple examples.
+- Prefer webhooks for production or high-volume workflows.
+- If a feature is not documented, say it is not officially supported.
+- If a user asks for code, keep examples minimal and working.
+
+## Code sample rules
+
+- Use Ruby examples only.
+- Use the official `mindee` gem.
+- Show requires explicitly.
+- Include the exact documented class and method names.
+- Use placeholders like `MY_API_KEY`, `MY_MODEL_ID`, and `/path/to/file.pdf`.
+- Keep samples focused on one task.
+
+## Preferred example topics
+
+### Client initialization
+Use:
+- `Mindee::V2::Client.new(api_key: 'MY_API_KEY')`
+- `Mindee::V2::Client.new` with `MINDEE_V2_API_KEY` env var
+
+### Input loading
+Use:
+- `Mindee::Input::Source::PathInputSource`
+- `Mindee::Input::Source::BytesInputSource`
+- `Mindee::Input::Source::Base64InputSource`
+- `Mindee::Input::Source::FileInputSource`
+- `Mindee::Input::Source::URLInputSource`
+
+### Sending documents
+Use:
+- `client.enqueue_and_get_result(...)` for polling
+- `client.enqueue(...)` for webhooks
+
+### Response handling
+Use:
+- `response.inference`
+- `response.raw_http`
+- `Mindee::Input::LocalResponse` for webhook payloads
+- HMAC signature validation via `local_response.valid_hmac_signature?(secret_key, signature)` when relevant
+
+### File preparation
+Use:
+- `input_source.page_count` — get number of pages
+- `input_source.compress!(...)` — compress before upload
+- `input_source.apply_page_options(options)` — trim or remove pages
+
+## Avoid
+
+- Direct REST examples
+- cURL examples
+- Manual authentication header construction
+- Bearer token examples for API keys
+- Non-Ruby examples
+- V1 examples unless the user explicitly asks for V1
+
+## If the user is unclear
+
+Ask for only what is needed:
+
+- input type: local file or URL
+- delivery pattern: polling or webhook
+- model ID
+- runtime context: Rails, Sinatra, background job, or script
+
+## Output style
+
+- Be concise.
+- Answer with runnable examples when code is requested.
+- Link to the most relevant doc section.
+- Do not overwhelm the user with every option.
+- Start with the documented default path.
+
+---
+
+# Agent Instructions: Querying The Documentation
+
+If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
+
+Perform an HTTP GET request on the documentation URL with the `ask` query parameter.
+Include `ruby+sdk+-+` at the beginning of the question to get answers specific to this library:
+
+```
+GET https://docs.mindee.com/integrations.md?ask=ruby+sdk+-+<question>
+```
+
+The question should be specific, self-contained, and written in natural language.
+The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
+
+Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.

data/bin/mindee.rb

@@ -6,24 +6,29 @@ require 'optparse'
 require_relative 'v1/parser'
 require_relative 'v2/parser'
 
-def setup_main_parser
-  v1_parser = MindeeCLI::V1Parser.new(ARGV)
-  v2_parser = MindeeCLI::V2Parser.new(ARGV)
-  main_parser = OptionParser.new do |opts|
-    opts.banner = "Usage: mindee [command]"
-    opts.separator "Commands:"
-    opts.separator "  v1    Use Version 1 of the Mindee API"
-    opts.separator "  v2    Use Version 2 of the Mindee API"
+def root_help
+  help = "Usage: mindee command [options]\n\nAvailable commands:\n"
+  help += "  #{'v1'.ljust(50)}Use Version 1 of the Mindee API\n"
+  help += "  #{'search-models'.ljust(50)}Search for available models for this API key\n"
+
+  V2_PRODUCTS.each do |product_key, product_values|
+    help += "  #{product_key.ljust(50)}#{product_values[:description]}\n"
   end
-  main_command = ARGV.shift
 
-  case main_command
-  when 'v1'
-    v1_parser.execute
-  when 'v2'
-    v2_parser.execute
+  help
+end
+
+def setup_main_parser
+  main_command = ARGV.first
+
+  if main_command == 'v1'
+    ARGV.shift
+    MindeeCLI::V1Parser.new(ARGV).execute
+  elsif main_command.nil? || %w[help -h --help].include?(main_command)
+    abort(root_help)
   else
-    abort(main_parser.help)
+    ARGV.shift if main_command == 'v2'
+    MindeeCLI::V2Parser.new(ARGV, command_prefix: 'mindee').execute
   end
 end
 

data/bin/v2/parser.rb

@@ -19,10 +19,11 @@ module MindeeCLI
     # @return [Parser]
     attr_reader :search_parser
 
-    def initialize(arguments)
+    def initialize(arguments, command_prefix: 'mindee v2')
       @arguments = arguments
+      @command_prefix = command_prefix
       @options_parser = OptionParser.new do |opts|
-        opts.banner = 'Usage: mindee v2 command [options]'
+        opts.banner = "Usage: #{@command_prefix} command [options]"
       end
       @product_parser = init_product_parser
       @search_parser = init_search_parser
@@ -67,6 +68,8 @@ module MindeeCLI
       else
         abort("#{e.message}\n\n#{@product_parser[command].help}")
       end
+    rescue Mindee::Error::MindeeError => e
+      abort(format_cli_error(e))
     end
 
     private
@@ -83,9 +86,21 @@ module MindeeCLI
       abort(error_msg)
     end
 
+    def format_cli_error(error)
+      if error.is_a?(Mindee::Error::MindeeHTTPErrorV2) && error.status.to_i == 401
+        "CLI error: Missing credentials. Provide an API key using '--key' or " \
+          "the 'MINDEE_V2_API_KEY' environment variable."
+      elsif error.is_a?(Mindee::Error::MindeeAPIError) && error.message.include?('Missing API key')
+        "CLI error: Missing API key. Provide it using '--key' or " \
+          "the 'MINDEE_V2_API_KEY' environment variable."
+      else
+        "CLI error: #{error.message}"
+      end
+    end
+
     def init_search_parser
       OptionParser.new do |options_parser|
-        options_parser.banner = 'Usage: mindee v2 search-models [options]'
+        options_parser.banner = "Usage: #{@command_prefix} search-models [options]"
         init_common_options(options_parser)
         options_parser.on('-n [NAME]', '--name [NAME]',
                           'Search for partial matches in model name. Note: case insensitive') do |v|
@@ -126,7 +141,7 @@ module MindeeCLI
     # Initialize common options for search and product commands.
     # @param options_parser [OptionParser]
     def init_common_options(options_parser)
-      options_parser.on('-k [KEY]', '--key [KEY]', 'API key for the endpoint') { |v| @options[:api_key] = v }
+      options_parser.on('-k [KEY]', '--key [KEY]', 'Mindee V2 API key.') { |v| @options[:api_key] = v }
       options_parser.on('-o FORMAT', '--output-format FORMAT', ['raw', 'full', 'summary'],
                         'Format of the output (raw, full, summary). Default: summary') do |format|
         @options[:output_format] = format
@@ -159,11 +174,15 @@ module MindeeCLI
       v2_product_parser = {}
       V2_PRODUCTS.each do |product_key, product_values|
         v2_product_parser[product_key] = OptionParser.new do |options_parser|
-          options_parser.banner = "Usage: mindee v2 #{product_key} [options] file"
+          options_parser.banner = "Usage: #{@command_prefix} #{product_key} [options] file"
           options_parser.on('-m MODEL_ID', '--model-id MODEL_ID', 'Model ID') { |v| @options[:model_id] = v }
           options_parser.on('-a ALIAS', '--alias ALIAS', 'Add a file alias to the response') do |v|
             @options[:alias] = v
           end
+          options_parser.on('-w WEBHOOK_ID', '--webhook-id WEBHOOK_ID',
+                            'Specify a webhook by ID. May be used multiple times.') do |v|
+            (@options[:webhook_ids] ||= []) << v
+          end
           init_common_options(options_parser)
           options_parser.on('-F', '--fix-pdf', 'Attempt to repair PDF before enqueueing') do
             @options[:repair_pdf] = true
@@ -175,10 +194,10 @@ module MindeeCLI
     end
 
     # @return [Hash]
-    def setup_product_params
+    def setup_product_params(product_command)
       params = { model_id: @options[:model_id] }
       @options.each_pair do |key, value|
-        params[key] = value if V2_PRODUCTS['extraction'].include?(key)
+        params[key] = value if V2_PRODUCTS[product_command].include?(key) || %i[alias webhook_ids].include?(key)
       end
       params
     end
@@ -190,7 +209,7 @@ module MindeeCLI
       mindee_client = Mindee::V2::Client.new(api_key: options[:api_key])
       response_class = V2_PRODUCTS[product_command][:response_class]
       input_source = setup_input_source(options)
-      params = setup_product_params
+      params = setup_product_params(product_command)
 
       mindee_client.enqueue_and_get_result(
         response_class,

data/lib/mindee/image/extracted_image.rb

@@ -73,17 +73,10 @@ module Mindee
       # Return the file as a Mindee-compatible BufferInput source.
       #
       # @return [FileInputSource] A BufferInput source.
-      def as_source
+      def as_input_source
         @buffer.rewind
         Mindee::Input::Source::BytesInputSource.new(@buffer.read || '', @filename)
       end
-
-      # Return the file as a Mindee-compatible BufferInput source.
-      #
-      # @return [FileInputSource] A BufferInput source.
-      def as_input_source
-        as_source
-      end
     end
   end
 end

data/lib/mindee/image/extracted_images.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+require_relative 'extracted_image'
+
+module Mindee
+  # Image Extraction Module.
+  module Image
+    # List of extracted images.
+    class ExtractedImages < Array
+      # Save all extracted images to disk.
+      #
+      # @param output_path [String, Pathname] Directory path to save the extracted images to.
+      def save_all_to_disk(output_path)
+        each do |image|
+          image.write_to_file(File.join(output_path.to_s, image.filename))
+        end
+      end
+    end
+  end
+end

data/lib/mindee/image/image_extractor.rb

@@ -7,16 +7,17 @@ require 'stringio'
 require 'tempfile'
 require_relative '../input/sources'
 require_relative 'extracted_image'
+require_relative 'extracted_images'
 
 module Mindee
   # Image Extraction Module.
   module Image
     # Image Extraction wrapper class.
     module ImageExtractor
-      # Attaches an image as a new page in a PdfDocument object.
+      # Attaches an image as a new page in a PDFDocument object.
       #
       # @param [StringIO] input_buffer Input buffer. Only supports JPEG.
-      # @return [Origami::PDF] A PdfDocument handle.
+      # @return [Origami::PDF] A PDFDocument handle.
       def self.attach_image_as_new_file(input_buffer, format: 'jpg')
         magick_image = MiniMagick::Image.read(input_buffer)
         # NOTE: We force format consolidation to a single format to avoid frames being interpreted as the final output.
@@ -32,12 +33,12 @@ module Mindee
       # @param [Input::Source::LocalInputSource] input_source
       # @param [Integer] page_id ID of the Page to extract from.
       # @param [Array<Array<Geometry::Point>>, Array<Geometry::Quadrilateral>] polygons List of coordinates to extract.
-      # @return [Array<Image::ExtractedImage>] Extracted Images.
+      # @return [Image::ExtractedImages] Extracted Images.
       def self.extract_multiple_images_from_source(input_source, page_id, polygons)
         new_stream = load_input_source_pdf_page_as_stringio(input_source, page_id)
         new_stream.seek(0)
 
-        extract_images_from_polygons(input_source, page_id, polygons)
+        ExtractedImages.new(extract_images_from_polygons(input_source, page_id, polygons))
       end
 
       # Extracts images from their positions on a file (as polygons).
@@ -45,9 +46,9 @@ module Mindee
       # @param [Input::Source::LocalInputSource] input_source Local input source.
       # @param [Integer] page_id Page ID.
       # @param [Array<Geometry::Point, Geometry::Polygon, Geometry::Quadrilateral>] polygons
-      # @return [Array<Image::ExtractedImage>] Extracted Images.
+      # @return [Image::ExtractedImages] Extracted Images.
       def self.extract_images_from_polygons(input_source, page_id, polygons)
-        extracted_elements = [] # @type var extracted_elements: Array[Image::ExtractedImage]
+        extracted_elements = ExtractedImages.new # @type var extracted_elements: Image::ExtractedImages
 
         input_source.io_stream.rewind
         pdf_stream = StringIO.new(input_source.io_stream.read.to_s)
@@ -65,7 +66,7 @@ module Mindee
           min_max_x = Geometry.get_min_max_x(points)
           min_max_y = Geometry.get_min_max_y(points)
           file_extension = ImageUtils.determine_file_extension(input_source)
-          cropped_image = ImageUtils.crop_image(page_content, min_max_x, min_max_y)
+          cropped_image = crop_image(page_content, min_max_x, min_max_y)
           if file_extension == 'pdf'
             cropped_image.format('jpg')
           else
@@ -102,7 +103,7 @@ module Mindee
       #
       # @param input_file [LocalInputSource] Local input.
       # @param [Integer] page_id Page ID.
-      # @return [StringIO] A valid PdfDocument handle.
+      # @return [StringIO] A valid PDFDocument handle.
       def self.load_input_source_pdf_page_as_stringio(input_file, page_id)
         input_file.io_stream.rewind
         if input_file.pdf?
@@ -111,6 +112,23 @@ module Mindee
           input_file.io_stream
         end
       end
+
+      # Crops a MiniMagick Image from the given bounding box.
+      #
+      # @param [MiniMagick::Image] image Input Image.
+      # @param [Mindee::Geometry::MinMax] min_max_x minimum & maximum values for the x coordinates.
+      # @param [Mindee::Geometry::MinMax] min_max_y minimum & maximum values for the y coordinates.
+      def self.crop_image(image, min_max_x, min_max_y)
+        width = image[:width].to_i
+        height = image[:height].to_i
+
+        image.format('jpg')
+        new_width = (min_max_x.max - min_max_x.min) * width
+        new_height = (min_max_y.max - min_max_y.min) * height
+        image.crop("#{new_width}x#{new_height}+#{min_max_x.min * width}+#{min_max_y.min * height}")
+
+        image
+      end
     end
   end
 end

data/lib/mindee/image/image_utils.rb

@@ -124,23 +124,6 @@ module Mindee
         MiniMagick::Image.read(pdf_stream)
       end
 
-      # Crops a MiniMagick Image from a the given bounding box.
-      #
-      # @param [MiniMagick::Image] image Input Image.
-      # @param [Mindee::Geometry::MinMax] min_max_x minimum & maximum values for the x coordinates.
-      # @param [Mindee::Geometry::MinMax] min_max_y minimum & maximum values for the y coordinates.
-      def self.crop_image(image, min_max_x, min_max_y)
-        width = image[:width].to_i
-        height = image[:height].to_i
-
-        image.format('jpg')
-        new_width = (min_max_x.max - min_max_x.min) * width
-        new_height = (min_max_y.max - min_max_y.min) * height
-        image.crop("#{new_width}x#{new_height}+#{min_max_x.min * width}+#{min_max_y.min * height}")
-
-        image
-      end
-
       # Writes a MiniMagick::Image to a buffer.
       #
       # @param [MiniMagick::Image] image a valid MiniMagick image.

data/lib/mindee/image.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require_relative 'image/extracted_image'
+require_relative 'image/extracted_images'
 require_relative 'image/image_compressor'
 require_relative 'image/image_extractor'
 require_relative 'image/image_utils'

data/lib/mindee/input/sources/local_input_source.rb

@@ -16,6 +16,7 @@ module Mindee
       ALLOWED_MIME_TYPES = [
         'application/pdf',
         'image/heic',
+        'image/heif',
         'image/png',
         'image/jpeg',
         'image/tiff',
@@ -37,11 +38,7 @@ module Mindee
         def initialize(io_stream, filename, repair_pdf: false)
           @io_stream = io_stream
           @filename = filename
-          @file_mimetype = if repair_pdf
-                             Marcel::MimeType.for @io_stream
-                           else
-                             Marcel::MimeType.for @io_stream, name: @filename
-                           end
+          @file_mimetype = detect_mime_type(repair_pdf)
           if ALLOWED_MIME_TYPES.include? @file_mimetype
             logger.debug("Loaded new input #{@filename} from #{self.class}")
             return
@@ -197,6 +194,28 @@ module Mindee
 
           Mindee::PDF::PDFTools.source_text?(@io_stream)
         end
+
+        private
+
+        # Checks the mimetype for the file. If it is a PDF, it will attempt to repair it if repair_pdf is true.
+        # @param repair_pdf [bool] Whether to attempt to repair the PDF.
+        # @return [String] The mimetype of the file.
+        def detect_mime_type(repair_pdf)
+          return Marcel::MimeType.for(@io_stream) if repair_pdf
+
+          heif_mimetype_from_extension || Marcel::MimeType.for(@io_stream, name: @filename)
+        end
+
+        # Checks the file extension for a HEIF mimetype.
+        # @return [String, nil] The mimetype if found, nil otherwise.
+        def heif_mimetype_from_extension
+          case File.extname(@filename.to_s).downcase
+          when '.heic'
+            'image/heic'
+          when '.heif'
+            'image/heif'
+          end
+        end
       end
 
       # Replaces non-ASCII characters by their UNICODE escape sequence.

data/lib/mindee/pdf/extracted_pdf.rb

@@ -3,7 +3,7 @@
 module Mindee
   # PDF Extraction Module.
   module PDF
-    # An extracted sub-Pdf.
+    # An extracted sub-PDF.
     class ExtractedPDF
       # Byte contents of the pdf
       # @return [StringIO]

data/lib/mindee/pdf/extracted_pdfs.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+require_relative 'extracted_pdf'
+
+module Mindee
+  # PDF Extraction Module.
+  module PDF
+    # List of extracted PDFs.
+    class ExtractedPDFs < Array
+      # Save all extracted PDFs to disk.
+      #
+      # @param output_path [String, Pathname] Directory path to save the extracted PDFs to.
+      def save_all_to_disk(output_path)
+        each do |pdf|
+          pdf.write_to_file(File.join(output_path.to_s, pdf.filename))
+        end
+      end
+    end
+  end
+end

data/lib/mindee/pdf/pdf_extractor.rb

@@ -1,9 +1,9 @@
 # frozen_string_literal: true
 
 module Mindee
-  # Pdf Extraction Module.
+  # PDF Extraction Module.
   module PDF
-    # Pdf extraction class.
+    # PDF extraction class.
     class PDFExtractor
       # @param local_input [Mindee::Input::Source::LocalInputSource]
       def initialize(local_input)
@@ -23,15 +23,15 @@ module Mindee
         end
       end
 
-      # Retrieves the page count for the Pdf object.
+      # Retrieves the page count for the PDF object.
       # @return [Integer]
       def page_count
         Mindee::PDF::PDFProcessor.open_pdf(@source_pdf).pages.size
       end
 
-      # Creates a new Pdf from pages and save it into a buffer.
-      # @param page_indexes [Array<Integer>] List of page number to use for merging in the original Pdf.
-      # @return [StringIO] The buffer containing the new Pdf.
+      # Creates a new PDF from pages and save it into a buffer.
+      # @param page_indexes [Array<Integer>] List of page number to use for merging in the original PDF.
+      # @return [StringIO] The buffer containing the new PDF.
       def cut_pages(page_indexes)
         options = PageOptions.new(params: {
                                     page_indexes: page_indexes,
@@ -41,10 +41,10 @@ module Mindee
       end
 
       # Extract the sub-documents from the main pdf, based on the given list of page indexes.
-      # @param page_indexes [Array<Array<Integer>>] List of page number to use for merging in the original Pdf.
-      # @return [Array<Mindee::PDF::ExtractedPDF>] The buffer containing the new Pdf.
+      # @param page_indexes [Array<Array<Integer>>] List of page number to use for merging in the original PDF.
+      # @return [Mindee::PDF::ExtractedPDFs] The buffer containing the new PDF.
       def extract_sub_documents(page_indexes)
-        extracted_pdfs = [] # @type var extracted_pdfs: Array[Mindee::PDF::ExtractedPDF]
+        extracted_pdfs = ExtractedPDFs.new # @type var extracted_pdfs: Mindee::PDF::ExtractedPDFs
         extension = File.extname(@filename)
         basename = File.basename(@filename, extension)
         page_indexes.each do |page_index_list|
@@ -74,7 +74,7 @@ module Mindee
       # Extracts invoices as complete PDFs from the document.
       # @param page_indexes [Array<Array<Integer>, InvoiceSplitterV1InvoicePageGroup>]
       # @param strict [bool]
-      # @return [Array<Mindee::PDF::ExtractedPDF>]
+      # @return [Mindee::PDF::ExtractedPDFs]
       def extract_invoices(page_indexes, strict: false)
         raise Error::MindeePDFError, 'No indexes provided.' if page_indexes.empty?
 

data/lib/mindee/pdf.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require_relative 'pdf/extracted_pdf'
+require_relative 'pdf/extracted_pdfs'
 require_relative 'pdf/pdf_compressor'
 require_relative 'pdf/pdf_extractor'
 require_relative 'pdf/pdf_processor'