✨ add support for V2 products

.github/workflows/_test-code-samples.yml

@@ -4,6 +4,18 @@ on:
   workflow_call:
   workflow_dispatch:
 
+env:
+  MINDEE_ENDPOINT_SE_TESTS: ${{ secrets.MINDEE_ENDPOINT_SE_TESTS }}
+  MINDEE_ACCOUNT_SE_TESTS: ${{ secrets.MINDEE_ACCOUNT_SE_TESTS }}
+  MINDEE_API_KEY_SE_TESTS: ${{ secrets.MINDEE_API_KEY_SE_TESTS }}
+  MINDEE_V2_API_KEY: ${{ secrets.MINDEE_V2_SE_TESTS_API_KEY }}
+  MINDEE_V2_SE_TESTS_FINDOC_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_FINDOC_MODEL_ID }}
+  MINDEE_V2_SE_TESTS_FAILURE_WEBHOOK_ID: ${{ secrets.MINDEE_V2_SE_TESTS_FAILURE_WEBHOOK_ID }}
+  MINDEE_V2_SE_TESTS_CLASSIFICATION_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_CLASSIFICATION_MODEL_ID }}
+  MINDEE_V2_SE_TESTS_CROP_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_CROP_MODEL_ID }}
+  MINDEE_V2_SE_TESTS_OCR_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_OCR_MODEL_ID }}
+  MINDEE_V2_SE_TESTS_SPLIT_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_SPLIT_MODEL_ID }}
+
 jobs:
   test:
     name: Run Tests
@@ -28,8 +40,14 @@ jobs:
           ruby-version: ${{ matrix.ruby }}
           bundler-cache: true
 
-      - name: Tests code samples
+      - name: Tests V1 code samples
+        env:
+          MINDEE_LOG_LEVEL: DEBUG
+        run: |
+          ./spec/test_code_samples_v1.sh
+
+      - name: Tests V2 code samples
         env:
           MINDEE_LOG_LEVEL: DEBUG
         run: |
-            ./spec/test_code_samples.sh ${{ secrets.MINDEE_ACCOUNT_SE_TESTS }} ${{ secrets.MINDEE_ENDPOINT_SE_TESTS }} ${{ secrets.MINDEE_API_KEY_SE_TESTS }} ${{ secrets.MINDEE_V2_SE_TESTS_API_KEY }} ${{ secrets.MINDEE_V2_SE_TESTS_FINDOC_MODEL_ID }}
+          ./spec/test_code_samples_v2.sh

.github/workflows/_test-integrations.yml

@@ -20,7 +20,7 @@ jobs:
           - "macos-latest"
         ruby:
           - "3.0"
-          - "3.4"
+          - "4.0"
     steps:
       - uses: actions/checkout@v4
         with:
@@ -56,6 +56,10 @@ jobs:
           MINDEE_V2_API_KEY: ${{ secrets.MINDEE_V2_SE_TESTS_API_KEY }}
           MINDEE_V2_FINDOC_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_FINDOC_MODEL_ID }}
           MINDEE_V2_SE_TESTS_BLANK_PDF_URL: ${{ secrets.MINDEE_V2_SE_TESTS_BLANK_PDF_URL }}
+          MINDEE_V2_SE_TESTS_CLASSIFICATION_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_CLASSIFICATION_MODEL_ID }}
+          MINDEE_V2_SE_TESTS_CROP_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_CROP_MODEL_ID }}
+          MINDEE_V2_SE_TESTS_OCR_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_OCR_MODEL_ID }}
+          MINDEE_V2_SE_TESTS_SPLIT_MODEL_ID: ${{ secrets.MINDEE_V2_SE_TESTS_SPLIT_MODEL_ID }}
           MINDEE_LOG_LEVEL: DEBUG
         run: |
           bundle exec rake integration

.github/workflows/_test-units.yml

@@ -23,6 +23,7 @@ jobs:
           - "3.2"
           - "3.3"
           - "3.4"
+          - "4.0"
     steps:
     - uses: actions/checkout@v4
       with:

.gitignore

@@ -16,6 +16,8 @@
 /test/version_tmp/
 /tmp/
 _test.rb
+_test_v1.rb
+_test_v2.rb
 /vendor
 /mindee-*/
 local-test

.rubocop.yml

@@ -6,7 +6,7 @@ AllCops:
     - 'tmp/**/*'
     - '.git/**/*'
     - 'bin/*'
-    - _test.rb
+    - _test*.rb
     - local_test/*
     - Steepfile
 

docs/code_samples/v2_classification.txt

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+require 'mindee'
+require 'mindee/v2/product'
+
+input_path = '/path/to/the/file.ext'
+api_key = 'MY_API_KEY'
+model_id = 'MY_MODEL_ID'
+
+# Init a new client
+mindee_client = Mindee::ClientV2.new(api_key: api_key)
+
+# Set inference parameters
+classification_params = {
+    # ID of the model, required.
+    model_id: model_id,
+}
+
+# Load a file from disk
+input_source = Mindee::Input::Source::PathInputSource.new(input_path)
+
+# Send for processing
+response = mindee_client.enqueue_and_get_result(
+    Mindee::V2::Product::Classification::Classification,
+    input_source,
+    classification_params
+)
+
+# Access the classification result
+puts response.inference.result.classification

docs/code_samples/v2_crop.txt

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+require 'mindee'
+require 'mindee/v2/product'
+
+input_path = '/path/to/the/file.ext'
+api_key = 'MY_API_KEY'
+model_id = 'MY_MODEL_ID'
+
+# Init a new client
+mindee_client = Mindee::ClientV2.new(api_key: api_key)
+
+# Set inference parameters
+crop_params = {
+    # ID of the model, required.
+    model_id: model_id,
+}
+
+# Load a file from disk
+input_source = Mindee::Input::Source::PathInputSource.new(input_path)
+
+# Send for processing
+response = mindee_client.enqueue_and_get_result(
+    Mindee::V2::Product::Crop::Crop,
+    input_source,
+    crop_params
+)
+
+# Access the result crops
+puts response.inference.result.crops

docs/code_samples/default_v2.txt → docs/code_samples/v2_extraction.txt

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require 'mindee'
+require 'mindee/v2/product'
 
 input_path = '/path/to/the/file.ext'
 api_key = 'MY_API_KEY'
@@ -10,9 +11,9 @@ model_id = 'MY_MODEL_ID'
 mindee_client = Mindee::ClientV2.new(api_key: api_key)
 
 # Set inference parameters
-inference_params = Mindee::Input::InferenceParameters.new(
+inference_params = {
     # ID of the model, required.
-    model_id,
+    model_id: model_id,
 
     # Options: set to `true` or `false` to override defaults
 
@@ -25,15 +26,16 @@ inference_params = Mindee::Input::InferenceParameters.new(
     # Boost the precision and accuracy of all extractions.
     # Calculate confidence scores for all fields.
     confidence: nil
-)
+}
 
 # Load a file from disk
 input_source = Mindee::Input::Source::PathInputSource.new(input_path)
 
 # Send for processing
-response = mindee_client.enqueue_and_get_inference(
+response = mindee_client.enqueue_and_get_result(
+    Mindee::V2::Product::Extraction::Extraction,
     input_source,
-    inference_params # This parameter can also be provided as a Hash.
+    inference_params
 )
 
 # Print a brief summary of the parsed data

docs/code_samples/v2_extraction_webhook.txt

@@ -0,0 +1,45 @@
+# frozen_string_literal: true
+
+require 'mindee'
+require 'mindee/v2/product'
+
+input_path = '/path/to/the/file.ext'
+api_key = 'MY_API_KEY'
+model_id = 'MY_MODEL_ID'
+
+# Init a new client
+mindee_client = Mindee::ClientV2.new(api_key: api_key)
+
+inference_params = {
+    # ID of the model, required.
+    model_id: model_id,
+    # Add any number of webhook IDs here.
+    webhook_ids: ['MY_WEBHOOK_ID'],
+
+    # Options: set to `true` or `false` to override defaults
+
+    # Enhance extraction accuracy with Retrieval-Augmented Generation.
+    rag: nil,
+    # Extract the full text content from the document as strings.
+    raw_text: nil,
+    # Calculate bounding box polygons for all fields.
+    polygon: nil,
+    # Boost the precision and accuracy of all extractions.
+    # Calculate confidence scores for all fields.
+    confidence: nil
+}
+
+# Load a file from disk
+input_source = Mindee::Input::Source::PathInputSource.new(input_path)
+
+# Send for processing
+response = mindee_client.enqueue(
+    Mindee::V2::Product::Extraction::Extraction,
+    input_source,
+    inference_params
+)
+
+# Print the job ID
+job_id = response.job.id
+
+puts job_id

docs/code_samples/v2_ocr.txt

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+require 'mindee'
+require 'mindee/v2/product'
+
+input_path = '/path/to/the/file.ext'
+api_key = 'MY_API_KEY'
+model_id = 'MY_MODEL_ID'
+
+# Init a new client
+mindee_client = Mindee::ClientV2.new(api_key: api_key)
+
+# Set inference parameters
+ocr_params = {
+    # ID of the model, required.
+    model_id: model_id,
+}
+
+# Load a file from disk
+input_source = Mindee::Input::Source::PathInputSource.new(input_path)
+
+# Send for processing
+response = mindee_client.enqueue_and_get_result(
+    Mindee::V2::Product::Ocr::Ocr,
+    input_source,
+    ocr_params
+)
+
+# Access the result OCR pages
+puts response.inference.result.pages

docs/code_samples/v2_split.txt

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+require 'mindee'
+require 'mindee/v2/product'
+
+input_path = '/path/to/the/file.ext'
+api_key = 'MY_API_KEY'
+model_id = 'MY_MODEL_ID'
+
+# Init a new client
+mindee_client = Mindee::ClientV2.new(api_key: api_key)
+
+# Set inference parameters
+split_params = {
+    # ID of the model, required.
+    model_id: model_id,
+}
+
+# Load a file from disk
+input_source = Mindee::Input::Source::PathInputSource.new(input_path)
+
+# Send for processing
+response = mindee_client.enqueue_and_get_result(
+    Mindee::V2::Product::Split::Split,
+    input_source,
+    split_params
+)
+
+# Access the result splits
+puts response.inference.result.splits

lib/mindee.rb

@@ -84,6 +84,13 @@ module IND
     module US
     end
   end
+
+  # V2-specific module.
+  module V2
+    # Product-specific module.
+    module Product
+    end
+  end
 end
 
 # Shorthand to call the logger from anywhere.