商品検索のチュートリアル

このチュートリアルでは、商品の参照イメージが設定された商品のグループが含まれる商品セットを作成する方法を説明します。チュートリアルでは、オンラインで個別にインポートを行い、商品セットを作成する方法について説明します。商品セットにインデックスが作成されると、Vision Product Search を使用して商品セットをクエリできます。

このチュートリアルの学習内容は次のとおりです。

  1. オンラインで個別にインポートを行い、商品セットを作成する
  2. 個別の商品を作成する
  3. 商品セットに商品を追加する
  4. 商品を更新する
  5. 参照画像を作成する
  6. 類似商品を検索する

始める前に

このチュートリアルを始める前に、適切なクライアント ライブラリをインストールし、プロジェクトで課金と API を有効にする必要があります。また、認証の設定を適切に行う必要があります。

ライブラリをインポートする

Cloud Vision Product Search を使用するには、クライアント ライブラリのダウンロードとインストールが完了した後で次のモジュールをインポートします。

C#

using Google.Cloud.Vision.V1;

Go


import (
	"context"
	"fmt"
	"io"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

Java

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.vision.v1.BatchOperationMetadata;
import com.google.cloud.vision.v1.ImportProductSetsGcsSource;
import com.google.cloud.vision.v1.ImportProductSetsGcsSource.Builder;
import com.google.cloud.vision.v1.ImportProductSetsInputConfig;
import com.google.cloud.vision.v1.ImportProductSetsResponse;
import com.google.cloud.vision.v1.ProductSearchClient;
import com.google.cloud.vision.v1.ReferenceImage;

Node.js

const vision = require('@google-cloud/vision');

PHP

use Google\Cloud\Vision\V1\ProductSearchClient;
use Google\Cloud\Vision\V1\ImportProductSetsGcsSource;
use Google\Cloud\Vision\V1\ImportProductSetsInputConfig;

Python

from google.cloud import vision

Ruby

require "google/cloud/vision"

アプリケーションの実行

ステップ 1: 商品カタログを作成する

ユーザーは 2 通りの方法で商品カタログを作成できます。その 1 つは CSV ファイルを使用する一括インポートで、1 回の API 呼び出しで商品カタログ全体をインポートできます。もう 1 つはオンライン インポートで、この方法では商品セットの制御ができ、インポートごとに 1 つのリソースまたは関係を管理できます。これは基本的に商品セット、商品、参照画像の個別作成に相当します。オンライン インポートでは、一括インポートによってすでに作成されている商品カタログの段階的な更新もできます。

このチュートリアルでは、オンライン インポートを使用します。CSV を使用したバッチインポートの例については、クイックスタートをご覧ください。

オンライン（個別）インポート

1. 商品セットを作成する

空の商品セットを作成します。これは商品のグループを格納するためのシンプルなコンテナです。

リクエスト

create_product_set() メソッドを使用して次のリクエストを実行し、空の商品セットを作成して「PS_CLOTH-SHOE_070318」と名前を付けます。商品セット ID と表示名を引数として渡します。

REST とコマンドライン

後述のリクエストのデータを使用する前に、次のように置き換えます。

  • project-id: GCP プロジェクト ID。
  • location-id: 有効なロケーション ID。有効なロケーション識別子は us-west1、us-east1、europe-west1、asia-east1 です。
  • display-name: 選択した文字列の表示名。

HTTP メソッドと URL: 

POST https://vision.googleapis.com/v1/projects/project-id/locations/location-id/productSets

JSON 本文のリクエスト: 

{
  "displayName": "display-name"
}

リクエストを送信するには、次のいずれかのオプションを選択します。

curl

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。 

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://vision.googleapis.com/v1/projects/project-id/locations/location-id/productSets

PowerShell

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。 

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://vision.googleapis.com/v1/projects/project-id/locations/location-id/productSets" | Select-Object -Expand Content

リクエストが成功すると、サーバーは 200 OK HTTP ステータス コードと JSON 形式のレスポンスを返します。

出力は次のようになります。商品セット ID（この場合は b6d809615b6dd675）を使用して、商品セットに対する他の操作を行えます。

{
  "name": "projects/project-id/locations/location-id/productSets/b6d809615b6dd675",
  "displayName": "new-product-set"
}

C#

        private static object CreateProductSet(CreateProductSetsOptions opts)
        {
            var client = ProductSearchClient.Create();

            // Create a product set with the product set specification in the region.
            var request = new CreateProductSetRequest
            {
                // A resource that represents Google Cloud Platform location
                ParentAsLocationName = new LocationName(opts.ProjectID,
                                                        opts.ComputeRegion),
                ProductSetId = opts.ProductSetId,
                ProductSet = new ProductSet
                {
                    DisplayName = opts.ProductSetDisplayName
                }
            };

            // The response is the product set with the `name` populated
            var response = client.CreateProductSet(request);

            Console.WriteLine($"Product set name: {response.DisplayName}");

            return 0;
        }

Go


import (
	"context"
	"fmt"
	"io"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

// createProductSet creates a product set.
func createProductSet(w io.Writer, projectID string, location string, productSetID string, productSetDisplayName string) error {
	ctx := context.Background()
	c, err := vision.NewProductSearchClient(ctx)
	if err != nil {
		return fmt.Errorf("NewProductSearchClient: %v", err)
	}
	defer c.Close()

	req := &visionpb.CreateProductSetRequest{
		Parent:       fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		ProductSetId: productSetID,
		ProductSet: &visionpb.ProductSet{
			DisplayName: productSetDisplayName,
		},
	}

	resp, err := c.CreateProductSet(ctx, req)
	if err != nil {
		return fmt.Errorf("CreateProductSet: %v", err)
	}

	fmt.Fprintf(w, "Product set name: %s\n", resp.Name)

	return nil
}

Java

/**
 * Create a product set
 *
 * @param projectId - Id of the project.
 * @param computeRegion - Region name.
 * @param productSetId - Id of the product set.
 * @param productSetDisplayName - Display name of the product set.
 * @throws IOException - on I/O errors.
 */
public static void createProductSet(
    String projectId, String computeRegion, String productSetId, String productSetDisplayName)
    throws IOException {
  try (ProductSearchClient client = ProductSearchClient.create()) {

    // A resource that represents Google Cloud Platform location.
    String formattedParent = ProductSearchClient.formatLocationName(projectId, computeRegion);

    // Create a product set with the product set specification in the region.
    ProductSet myProductSet =
        ProductSet.newBuilder().setDisplayName(productSetDisplayName).build();
    CreateProductSetRequest request =
        CreateProductSetRequest.newBuilder()
            .setParent(formattedParent)
            .setProductSet(myProductSet)
            .setProductSetId(productSetId)
            .build();
    ProductSet productSet = client.createProductSet(request);
    // Display the product set information
    System.out.println(String.format("Product set name: %s", productSet.getName()));
  }
}

Node.js

async function createProductSet() {
  // Imports the Google Cloud client library
  const vision = require('@google-cloud/vision');

  // Creates a client
  const client = new vision.ProductSearchClient();

  /**
   * TODO(developer): Uncomment the following line before running the sample.
   */
  // const projectId = 'Your Google Cloud project Id';
  // const location = 'A compute region name';
  // const productSetId = 'Id of the product set';
  // const productSetDisplayName = 'Display name of the product set';

  // Resource path that represents Google Cloud Platform location.
  const locationPath = client.locationPath(projectId, location);

  const productSet = {
    displayName: productSetDisplayName,
  };

  const request = {
    parent: locationPath,
    productSet: productSet,
    productSetId: productSetId,
  };

  const [createdProductSet] = await client.createProductSet(request);
  console.log(`Product Set name: ${createdProductSet.name}`);
}

PHP

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Vision\V1\ProductSearchClient;
use Google\Cloud\Vision\V1\ProductSet;

/**
 * Create a product set
 *
 * @param string $projectId Your Google Cloud project ID
 * @param string $location Google Cloud compute region name
 * @param string $productSetId ID of the product set
 * @param string $productSetDisplayName Display name of the product set
 */
function product_set_create($projectId, $location, $productSetId, $productSetDisplayName)
{
    $client = new ProductSearchClient();

    # a resource that represents Google Cloud Platform location.
    $locationPath = $client->locationName($projectId, $location);

    # create a product set with the product set specification in the region.
    $productSet = (new ProductSet())
        ->setDisplayName($productSetDisplayName);

    # the response is the product set with the `name` field populated.
    $response = $client->createProductSet($locationPath, $productSet, ['productSetId' => $productSetId]);

    # display the product information.
    printf('Product set name: %s' . PHP_EOL, $response->getName());

    $client->close();
}

Python

from google.cloud import vision

def create_product_set(
        project_id, location, product_set_id, product_set_display_name):
    """Create a product set.
    Args:
        project_id: Id of the project.
        location: A compute region name.
        product_set_id: Id of the product set.
        product_set_display_name: Display name of the product set.
    """
    client = vision.ProductSearchClient()

    # A resource that represents Google Cloud Platform location.
    location_path = client.location_path(
        project=project_id, location=location)

    # Create a product set with the product set specification in the region.
    product_set = vision.types.ProductSet(
            display_name=product_set_display_name)

    # The response is the product set with `name` populated.
    response = client.create_product_set(
        parent=location_path,
        product_set=product_set,
        product_set_id=product_set_id)

    # Display the product set information.
    print('Product set name: {}'.format(response.name))

Ruby

require "google/cloud/vision"

def product_search_create_product_set project_id = "your-project-id"
  client = Google::Cloud::Vision.product_search

  # A resource that represents Google Cloud Platform location.
  location = "us-west1" # specify a compute region name
  location_path = client.location_path project: project_id, location: location

  # Create a product set with the product set specification in the region.
  product_set = {
    display_name: "display-name"
  }

  # The response is the product set with `name` populated.
  product_set = client.create_product_set parent:      location_path,
                                          product_set: product_set

  # Display the product set information.
  puts "Product set name: #{product_set.name}"
end

レスポンス

Product set name: projects/prj-prod-search-tutorials/locations/us-east1/productSets/PS_CLOTH-SHOE_070318
Product set id: PS_CLOTH-SHOE_070318
Product set display name: CLOTH-SHOE

2. 商品を作成する

商品セットを作成したら、次のステップとして商品を作成します。次のリクエストを実行して商品を作成します。

REST とコマンドライン

後述のリクエストのデータを使用する前に、次のように置き換えます。

  • project-id: GCP プロジェクト ID。
  • location-id: 有効なロケーション ID。有効なロケーション識別子は us-west1、us-east1、europe-west1、asia-east1 です。
  • display-name: 選択した文字列の表示名。
  • product-description: 選択した文字列の説明。
  • product-category: 有効な商品カテゴリ。現在使用可能な商品カテゴリは、homegoods-v2、apparel-v2、toys-v2、packagedgoods-v1、general-v1 です。
  • productLabels: 商品に関連付けられた 1 つ以上の Key-Value ペア。各 key-string には value-string を関連付ける必要があります。

HTTP メソッドと URL: 

POST https://vision.googleapis.com/v1/projects/project-id/locations/location-id/products

JSON 本文のリクエスト: 

{
  "displayName": "display-name",
  "description": "product-description",
  "productCategory": "product-category",
  "productLabels": [
      {
        "key": "key-string",
        "value": "value-string"
      }
  ]
}

リクエストを送信するには、次のいずれかのオプションを選択します。

curl

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。 

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://vision.googleapis.com/v1/projects/project-id/locations/location-id/products

PowerShell

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。 

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://vision.googleapis.com/v1/projects/project-id/locations/location-id/products" | Select-Object -Expand Content

リクエスト本文の例:

{
  "displayName": "sample-product-1234",
  "description": "Athletic shorts",
  "productCategory": "apparel-v2",
  "productLabels": [
      {
        "key": "style",
        "value": "womens"
      },
      {
        "key": "color",
        "value": "blue"
      }
  ]
}

リクエストが成功すると、サーバーは 200 OK HTTP ステータス コードと JSON 形式のレスポンスを返します。

出力は次のようになります。商品 ID（この場合は 37b9811d308c4e42）を使用して、商品に対して他のオペレーションを実行できます。

{
  "name": "projects/project-id/locations/location-id/products/37b9811d308c4e42",
  "displayName": "sample-product-456",
  "description": "Athletic shorts",
  "productCategory": "apparel-v2",
  "productLabels": [
    {
      "key": "style",
      "value": "womens"
    },
    {
      "key": "color",
      "value": "blue"
    }
  ]
}

C#

private static int CreateProduct(CreateProductOptions opts)
{
    var client = ProductSearchClient.Create();
    var request = new CreateProductRequest
    {
        // A resource that represents Google Cloud Platform location.
        ParentAsLocationName = new LocationName(opts.ProjectID,
                                                opts.ComputeRegion),
        // Set product category and product display name
        Product = new Product
        {
            DisplayName = opts.DisplayName,
            ProductCategory = opts.ProductCategory
        },
        ProductId = opts.ProductID
    };

    // The response is the product with the `name` field populated.
    var product = client.CreateProduct(request);

    Console.WriteLine($"Product name: {product.Name}");
    return 0;
}

Go


import (
	"context"
	"fmt"
	"io"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

// createProduct creates a product.
func createProduct(w io.Writer, projectID string, location string, productID string, productDisplayName string, productCategory string) error {
	ctx := context.Background()
	c, err := vision.NewProductSearchClient(ctx)
	if err != nil {
		return fmt.Errorf("NewProductSearchClient: %v", err)
	}
	defer c.Close()

	req := &visionpb.CreateProductRequest{
		Parent:    fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		ProductId: productID,
		Product: &visionpb.Product{
			DisplayName:     productDisplayName,
			ProductCategory: productCategory,
		},
	}

	resp, err := c.CreateProduct(ctx, req)
	if err != nil {
		return fmt.Errorf("CreateProduct: %v", err)
	}

	fmt.Fprintf(w, "Product name: %s\n", resp.Name)

	return nil
}

Java

/**
 * Create one product.
 *
 * @param projectId - Id of the project.
 * @param computeRegion - Region name.
 * @param productId - Id of the product.
 * @param productDisplayName - Display name of the product.
 * @param productCategory - Category of the product.
 * @throws IOException - on I/O errors.
 */
public static void createProduct(
    String projectId,
    String computeRegion,
    String productId,
    String productDisplayName,
    String productCategory)
    throws IOException {
  try (ProductSearchClient client = ProductSearchClient.create()) {

    // A resource that represents Google Cloud Platform location.
    String formattedParent = ProductSearchClient.formatLocationName(projectId, computeRegion);
    // Create a product with the product specification in the region.
    // Multiple labels are also supported.
    Product myProduct =
        Product.newBuilder()
            .setName(productId)
            .setDisplayName(productDisplayName)
            .setProductCategory(productCategory)
            .build();
    Product product = client.createProduct(formattedParent, myProduct, productId);
    // Display the product information
    System.out.println(String.format("Product name: %s", product.getName()));
  }
}

Node.js

async function createProduct() {
  // Imports the Google Cloud client library
  const vision = require('@google-cloud/vision');

  // Creates a client
  const client = new vision.ProductSearchClient();

  /**
   * TODO(developer): Uncomment the following line before running the sample.
   */
  // const projectId = 'Your Google Cloud project Id';
  // const location = 'A compute region name';
  // const productId = 'Id of the product';
  // const productDisplayName = 'Display name of the product';
  // const productCategory = 'Catoegory of the product';

  // Resource path that represents Google Cloud Platform location.
  const locationPath = client.locationPath(projectId, location);

  const product = {
    displayName: productDisplayName,
    productCategory: productCategory,
  };

  const request = {
    parent: locationPath,
    product: product,
    productId: productId,
  };

  const [createdProduct] = await client.createProduct(request);
  console.log(`Product name: ${createdProduct.name}`);
}

PHP

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Vision\V1\ProductSearchClient;
use Google\Cloud\Vision\V1\Product;

/**
 * Create one product
 *
 * @param string $projectId Your Google Cloud project ID
 * @param string $location Google Cloud compute region name
 * @param string $productId ID of the product
 * @param string $productDisplayName Display name of the product
 * @param string $productCategory Category of the product
 */
function product_create($projectId, $location, $productId, $productDisplayName, $productCategory)
{
    $client = new ProductSearchClient();

    # a resource that represents Google Cloud Platform location.
    $locationPath = $client->locationName($projectId, $location);

    # create a product with the product specification in the region.
    # set product name and product display name.
    $product = (new Product())
        ->setDisplayName($productDisplayName)
        ->setProductCategory($productCategory);

    # the response is the product with the `name` field populated.
    $response = $client->createProduct($locationPath, $product, ['productId' => $productId]);

    # display the product information.
    printf('Product name: %s' . PHP_EOL, $response->getName());

    $client->close();
}

Python

from google.cloud import vision

def create_product(
        project_id, location, product_id, product_display_name,
        product_category):
    """Create one product.
    Args:
        project_id: Id of the project.
        location: A compute region name.
        product_id: Id of the product.
        product_display_name: Display name of the product.
        product_category: Category of the product.
    """
    client = vision.ProductSearchClient()

    # A resource that represents Google Cloud Platform location.
    location_path = client.location_path(project=project_id, location=location)

    # Create a product with the product specification in the region.
    # Set product display name and product category.
    product = vision.types.Product(
        display_name=product_display_name,
        product_category=product_category)

    # The response is the product with the `name` field populated.
    response = client.create_product(
        parent=location_path,
        product=product,
        product_id=product_id)

    # Display the product information.
    print('Product name: {}'.format(response.name))

Ruby

require "google/cloud/vision"

def product_search_create_product project_id = "your-project-id"
  client = Google::Cloud::Vision.product_search

  # A resource that represents Google Cloud Platform location.
  location      = "us-west1" # specify a compute region name
  location_path = client.location_path project: project_id, location: location

  # Create a product with the product specification in the region.
  # Set product display name and product category.
  product = {
    display_name:     "sample-product-1234",
    description:      "Athletic shorts",
    product_category: "apparel",
    product_labels:   [{ key: "color", value: "blue" }]
  }

  # The response is the product with the `name` field populated.
  product = client.create_product parent: location_path, product: product

  # Display the product information.
  puts "Product name: #{product.name}"
end

レスポンス

Product name: projects/prj-prod-search-tutorials/locations/us-east1/products/P_CLOTH-SHOE_46903668_070318
Product id: P_CLOTH-SHOE_46903668_070318
Product display name: Blue Dress
Product category: apparel
Product description: Short sleeved and 1950s style satin dress
Product labels:
  Product label 1:
        key: style
        value: women
  Product label 2:
        key: category
        value: dress
  Product label 3:
        key: color
        value: dark-blue

3. 商品セットに商品を追加する

商品セットと商品が作成されたら、商品セットに商品を追加できます。

REST とコマンドライン

後述のリクエストのデータを使用する前に、次のように置き換えます。

  • project-id: GCP プロジェクト ID
  • location-id: 有効なロケーション ID。有効なロケーション識別子は us-west1、us-east1、europe-west1、asia-east1 です。
  • product-set-id: 操作を実行する商品セットの ID。
  • product-name: 商品の完全なリソース名。形式:
    • projects/project-id/locations/location-id/products/product-id

HTTP メソッドと URL:

POST https://vision.googleapis.com/v1/projects/project-id/locations/location-id/productSets/product-set-id:addProduct

JSON 本文のリクエスト: 

{
  "product": "product-name"
}

リクエストを送信するには、次のいずれかのオプションを選択します。

curl

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://vision.googleapis.com/v1/projects/project-id/locations/location-id/productSets/product-set-id:addProduct

PowerShell

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://vision.googleapis.com/v1/projects/project-id/locations/location-id/productSets/product-set-id:addProduct" | Select-Object -Expand Content

次のような JSON レスポンスが返されます。

{}

C#

private static int AddProductToProductSet(AddProductToProductSetOptions opts)
{
    var client = ProductSearchClient.Create();
    var request = new AddProductToProductSetRequest
    {
        // Get the full path of the products
        ProductAsProductName = new ProductName(opts.ProjectID,
                                              opts.ComputeRegion,
                                              opts.ProductID),
        // Get the full path of the product set.
        ProductSetName = new ProductSetName(opts.ProjectID,
                                           opts.ComputeRegion,
                                           opts.ProductSetId),
    };

    client.AddProductToProductSet(request);

    Console.WriteLine("Product added to product set.");

    return 0;
}

Go


import (
	"context"
	"fmt"
	"io"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

// addProductToProductSet adds a product to a product set.
func addProductToProductSet(w io.Writer, projectID string, location string, productID string, productSetID string) error {
	ctx := context.Background()
	c, err := vision.NewProductSearchClient(ctx)
	if err != nil {
		return fmt.Errorf("NewProductSearchClient: %v", err)
	}
	defer c.Close()

	req := &visionpb.AddProductToProductSetRequest{
		Name:    fmt.Sprintf("projects/%s/locations/%s/productSets/%s", projectID, location, productSetID),
		Product: fmt.Sprintf("projects/%s/locations/%s/products/%s", projectID, location, productID),
	}

	if err = c.AddProductToProductSet(ctx, req); err != nil {
		return fmt.Errorf("NewProductSearchClient: %v", err)
	}

	fmt.Fprintf(w, "Product added to product set.\n")

	return nil
}

Java

/**
 * Add a product to a product set.
 *
 * @param projectId - Id of the project.
 * @param computeRegion - Region name.
 * @param productId - Id of the product.
 * @param productSetId - Id of the product set.
 * @throws IOException - on I/O errors.
 */
public static void addProductToProductSet(
    String projectId, String computeRegion, String productId, String productSetId)
    throws IOException {
  try (ProductSearchClient client = ProductSearchClient.create()) {

    // Get the full path of the product set.
    String formattedName =
        ProductSearchClient.formatProductSetName(projectId, computeRegion, productSetId);

    // Get the full path of the product.
    String productPath = ProductName.of(projectId, computeRegion, productId).toString();

    // Add the product to the product set.
    client.addProductToProductSet(formattedName, productPath);

    System.out.println(String.format("Product added to product set."));
  }
}

Node.js

async function addProductToProductSet() {
  const vision = require('@google-cloud/vision');

  const client = new vision.ProductSearchClient();

  /**
   * TODO(developer): Uncomment the following line before running the sample.
   */
  // const projectId = 'Your Google Cloud project Id';
  // const location = 'A compute region name';
  // const productId = 'Id of the product';
  // const productSetId = 'Id of the product set';

  const productPath = client.productPath(projectId, location, productId);
  const productSetPath = client.productSetPath(
    projectId,
    location,
    productSetId
  );

  const request = {
    name: productSetPath,
    product: productPath,
  };

  await client.addProductToProductSet(request);
  console.log('Product added to product set.');
}

PHP

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Vision\V1\ProductSearchClient;

/**
 * Create a product set
 *
 * @param string $projectId Your Google Cloud project ID
 * @param string $location Google Cloud compute region name
 * @param string $productId ID of the product
 * @param string $productSetId ID of the product set
 */
function product_set_add_product($projectId, $location, $productId, $productSetId)
{
    $client = new ProductSearchClient();

    # get the name of the product set
    $productSetPath = $client->productSetName($projectId, $location, $productSetId);

    # get the name of the product.
    $productPath = $client->productName($projectId, $location, $productId);

    # add product to product set
    $client->addProductToProductSet($productSetPath, $productPath);
    print('Product added to product set.' . PHP_EOL);

    $client->close();
}

Python

from google.cloud import vision

def add_product_to_product_set(
        project_id, location, product_id, product_set_id):
    """Add a product to a product set.
    Args:
        project_id: Id of the project.
        location: A compute region name.
        product_id: Id of the product.
        product_set_id: Id of the product set.
    """
    client = vision.ProductSearchClient()

    # Get the full path of the product set.
    product_set_path = client.product_set_path(
        project=project_id, location=location,
        product_set=product_set_id)

    # Get the full path of the product.
    product_path = client.product_path(
        project=project_id, location=location, product=product_id)

    # Add the product to the product set.
    client.add_product_to_product_set(
        name=product_set_path, product=product_path)
    print('Product added to product set.')

Ruby

require "google/cloud/vision"

def product_search_add_product_to_product_set \
    project_id     = "your-project-id",
    location       = "us-west1",
    product_id     = "your-product-id",
    product_set_id = "your-product-set-id"

  client = Google::Cloud::Vision.product_search

  # Get the full path of the product set.
  product_set_path = client.product_set_path project:     project_id,
                                             location:    location,
                                             product_set: product_set_id

  # Get the full path of the product.
  product_path = client.product_path project:  project_id,
                                     location: location,
                                     product:  product_id

  # Add the product to the product set.
  client.add_product_to_product_set name:    product_set_path,
                                    product: product_path

  puts "Product #{product_id} added to product set #{product_set_id}."
end

レスポンス

Product added to product set.

4.商品を更新する

作成した商品や商品セットを更新する必要がある場合は、更新用のメソッドを使用できます。次の例では、ラベルを変更して商品の更新を行います。

コマンドライン

商品を更新するには、次の URI に PATCH リクエストを送信します。
  • project-id は、Google Cloud Platform（GCP）プロジェクトの ID に置き換えます。
  • location-id は、有効なロケーション識別子に置き換えます。有効なロケーション識別子は us-west1、us-east1、europe-west1、asia-east1 です。
  • product-id は、更新対象の商品の ID に置き換えます。
curl -X PATCH \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
-H "Content-Type: application/json" \
https://vision.googleapis.com/v1/projects/project-id/locations/location-id/products/product-id -d "{
   'updateMask': { 'paths': ['display_name'] },
   'product': { 'display_name': 'new-display-name' }
}"

C#

private static int UpdateProductLabels(UpdateProductLabelsOptions opts)
{
    var client = ProductSearchClient.Create();
    var request = new UpdateProductRequest
    {
        Product = new Product
        {
            // Get the name of the product
            ProductName = new ProductName(opts.ProjectID,
                                         opts.ComputeRegion,
                                         opts.ProductID),
            // Set the product name, product label, and product display
            // name. Multiple labels are also supported.
            ProductLabels =
            {
                new Product.Types.KeyValue
                {
                    Key = opts.Labels.Split(",").First(),
                    Value = opts.Labels.Split(",").Last()
                }
            }
        },
        // Updating only the product_labels field here.
        UpdateMask = new FieldMask
        {
            Paths = { "product_labels" }
        }
    };

    // This overwrites the product_labels.
    var product = client.UpdateProduct(request);

    var productId = product.Name.Split("/").Last();
    Console.WriteLine($"\nProduct name: {product.Name}");
    Console.WriteLine($"Product id: {productId}");
    Console.WriteLine($"Product display name: {product.DisplayName}");
    Console.WriteLine($"Product category: {product.ProductCategory}");
    Console.WriteLine($"Product labels:");
    foreach (var label in product.ProductLabels)
    {
        Console.WriteLine($"\tLabel: {label.ToString()}");
    }
    return 0;
}

Go


import (
	"context"
	"fmt"
	"io"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
	field_mask "google.golang.org/genproto/protobuf/field_mask"
)

// updateProductLabels updates product labels of a product.
func updateProductLabels(w io.Writer, projectID string, location string, productID string, key string, value string) error {
	ctx := context.Background()
	c, err := vision.NewProductSearchClient(ctx)
	if err != nil {
		return fmt.Errorf("NewProductSearchClient: %v", err)
	}
	defer c.Close()

	req := &visionpb.UpdateProductRequest{
		UpdateMask: &field_mask.FieldMask{
			Paths: []string{
				"product_labels",
			},
		},
		Product: &visionpb.Product{
			Name: fmt.Sprintf("projects/%s/locations/%s/products/%s", projectID, location, productID),
			ProductLabels: []*visionpb.Product_KeyValue{
				{
					Key:   key,
					Value: value,
				},
			},
		},
	}

	resp, err := c.UpdateProduct(ctx, req)
	if err != nil {
		return fmt.Errorf("UpdateProduct: %v", err)
	}

	fmt.Fprintf(w, "Product name: %s\n", resp.Name)
	fmt.Fprintf(w, "Updated product labels: %s\n", resp.ProductLabels)

	return nil
}

Java

/**
 * Update the product labels.
 *
 * @param projectId - Id of the project.
 * @param computeRegion - Region name.
 * @param productId -Id of the product.
 * @param productLabels - Labels of the product.
 * @throws IOException - on I/O errors.
 */
public static void updateProductLabels(
    String projectId, String computeRegion, String productId, String productLabels)
    throws IOException {
  try (ProductSearchClient client = ProductSearchClient.create()) {

    // Get the full path of the product.
    String formattedName =
        ProductSearchClient.formatProductName(projectId, computeRegion, productId);

    // Set product name, product labels and product display name.
    // Multiple labels are also supported.
    Product product =
        Product.newBuilder()
            .setName(formattedName)
            .addProductLabels(
                KeyValue.newBuilder()
                    .setKey(productLabels.split(",")[0].split("=")[0])
                    .setValue(productLabels.split(",")[0].split("=")[1])
                    .build())
            .build();

    // Set product update field name.
    FieldMask updateMask = FieldMask.newBuilder().addPaths("product_labels").build();

    // Update the product.
    Product updatedProduct = client.updateProduct(product, updateMask);
    // Display the product information
    System.out.println(String.format("Product name: %s", updatedProduct.getName()));
    System.out.println(String.format("Updated product labels: "));
    for (Product.KeyValue element : updatedProduct.getProductLabelsList()) {
      System.out.println(String.format("%s: %s", element.getKey(), element.getValue()));
    }
  }
}

Node.js

async function updateProductLabels() {
  // Imports the Google Cloud client library
  const vision = require('@google-cloud/vision');

  // Creates a client
  const client = new vision.ProductSearchClient();

  /**
   * TODO(developer): Uncomment the following line before running the sample.
   */
  // const projectId = 'Your Google Cloud project Id';
  // const location = 'A compute region name';
  // const productId = 'Id of the product';
  // const key = 'The key of the label';
  // const value = 'The value of the label';

  // Resource path that represents full path to the product.
  const productPath = client.productPath(projectId, location, productId);

  const product = {
    name: productPath,
    productLabels: [
      {
        key: key,
        value: value,
      },
    ],
  };

  const updateMask = {
    paths: ['product_labels'],
  };

  const request = {
    product: product,
    updateMask: updateMask,
  };

  const [updatedProduct] = await client.updateProduct(request);
  console.log(`Product name: ${updatedProduct.name}`);
  console.log(`Product display name: ${updatedProduct.displayName}`);
  console.log(`Product description: ${updatedProduct.description}`);
  console.log(`Product category: ${updatedProduct.productCategory}`);
  console.log(
    `Product Labels: ${updatedProduct.productLabels[0].key}: ${updatedProduct.productLabels[0].value}`
  );
}

PHP

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Vision\V1\ProductSearchClient;
use Google\Cloud\Vision\V1\Product\KeyValue;
use Google\Cloud\Vision\V1\Product;
use Google\Protobuf\FieldMask;

/**
 * Update product labels
 *
 * @param string $projectId Your Google Cloud project ID
 * @param string $location Google Cloud compute region name
 * @param string $productId ID of the product
 * @param string $key Key of the label to update
 * @param string $value Value of label to update
 */
function product_update($projectId, $location, $productId, $key, $value)
{
    $client = new ProductSearchClient();

    # get the name of the product.
    $productPath = $client->productName($projectId, $location, $productId);

    # set product name, product label and product display name.
    # multiple labels are also supported.
    $keyValue = (new KeyValue())
        ->setKey($key)
        ->setValue($value);
    $product = (new Product())
        ->setName($productPath)
        ->setProductLabels([$keyValue]);

    # updating only the product labels field here.
    $updateMask = (new FieldMask())
        ->setPaths(['product_labels']);

    # this overwrites the product_labels.
    $updatedProduct = $client->updateProduct($product, ['updateMask' => $updateMask]);

    # display the product information.
    printf('Product name: %s' . PHP_EOL, $updatedProduct->getName());
    print('Product labels: ' . PHP_EOL);
    foreach ($product->getProductLabels() as $label) {
        printf('%s : %s' . PHP_EOL, $label->getKey(), $label->getValue());
    }

    $client->close();
}

Python

from google.cloud import vision

def update_product_labels(
        project_id, location, product_id, key, value):
    """Update the product labels.
    Args:
        project_id: Id of the project.
        location: A compute region name.
        product_id: Id of the product.
        key: The key of the label.
        value: The value of the label.
    """
    client = vision.ProductSearchClient()

    # Get the name of the product.
    product_path = client.product_path(
        project=project_id, location=location, product=product_id)

    # Set product name, product label and product display name.
    # Multiple labels are also supported.
    key_value = vision.types.Product.KeyValue(key=key, value=value)
    product = vision.types.Product(
        name=product_path,
        product_labels=[key_value])

    # Updating only the product_labels field here.
    update_mask = vision.types.FieldMask(paths=['product_labels'])

    # This overwrites the product_labels.
    updated_product = client.update_product(
        product=product, update_mask=update_mask)

    # Display the updated product information.
    print('Product name: {}'.format(updated_product.name))
    print('Updated product labels: {}'.format(product.product_labels))

Ruby

require "google/cloud/vision"

def product_search_update_product_labels project_id = "your-project-id",
                                         location   = "us-west1",
                                         product_id = "your-product-id"

  client = Google::Cloud::Vision.product_search

  product_path = client.product_path project:  project_id,
                                     location: location,
                                     product:  product_id
  product = {
    name:           product_path,
    product_labels: [{ key: "color", value: "green" }]
  }

  client.update_product product:     product,
                        update_mask: { "paths": ["product_labels"] }
end

レスポンス

Product name: projects/prj-prod-search-tutorials/locations/us-east1/products/P_CLOTH-SHOE_46903668_070318
Product id: P_CLOTH-SHOE_46903668_070318
Product display name: Blue Dress
Updated product labels:
  Product label 1:
        key: style
        value: women
  Product label 2:
        key: category
        value: dress
  Product label 3:
        key: color
        value: blue
Product description: Short sleeved and 1950s style satin dress

5. 商品の参照画像を作成する

個別の商品の参照画像を作成すると、画像にインデックスが作成された後に Vision Product Search でその画像を使用して商品を検索できます。特に一致の品質の向上が必要な場合は、1 つの商品に複数の参照画像を設定できます。

商品にはいつでも新しい参照画像を追加できます。

参照画像を作成する際は、必要に応じて境界ポリゴン座標を指定できます。境界ポリゴン座標は、参照画像の対象領域を特定します。たとえば、ジャケットの商品の参照画像を作成した場合に、境界ポリゴン引数でジャケットの座標を指定すると、システムで商品の一致を検索するときにジャケットのみが考慮されます。注: クエリ時に API でサポートされる境界ポリゴンは 1 つのみですが、インデックス作成時には複数の境界ポリゴンを指定できます。

画像の境界ポリゴン座標の取得には、Vision API のオブジェクト ローカライズを使用すると便利です。オブジェクト ローカライズの詳細については、複数のオブジェクトを検出するをご覧ください。

REST とコマンドライン

後述のリクエストのデータを使用する前に、次のように置き換えます。

  • project-id: GCP プロジェクト ID。
  • location-id: 有効なロケーション ID。有効なロケーション識別子は us-west1、us-east1、europe-west1、asia-east1 です。
  • product-id: 参照画像に関連付けられている商品の ID。この ID は、商品の作成時にユーザーによってランダムに設定または指定されます。
  • cloud-storage-image-uri: Cloud Storage バケット内の有効な画像ファイルへのパス。少なくとも、ファイルに対する読み取り権限が必要です。例: 
    • gs://storage-bucket/filename.jpg

HTTP メソッドと URL: 

POST https://vision.googleapis.com/v1/projects/project-id/locations/location-id/products/product-id/referenceImages

JSON 本文のリクエスト: 

{
  "uri": "cloud-storage-image-uri",
  "boundingPolys": [
    {
      "vertices": [
        {
          "x": X_MIN,
          "y": Y_MIN
        },
        {
          "x": X_MAX,
          "y": Y_MIN
        },
        {
          "x": X_MAX,
          "y": Y_MAX
        },
        {
          "x": X_MIN,
          "y": Y_MAX
        }
      ]
    }
  ]
}

リクエストを送信するには、次のいずれかのオプションを選択します。

curl

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://vision.googleapis.com/v1/projects/project-id/locations/location-id/products/product-id/referenceImages

PowerShell

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://vision.googleapis.com/v1/projects/project-id/locations/location-id/products/product-id/referenceImages" | Select-Object -Expand Content

リクエストが成功すると、サーバーは 200 OK HTTP ステータス コードと JSON 形式のレスポンスを返します。

出力は次のようになります。このリクエストの例では、画像内の 1 つの boundingPoly が指定されています。境界ボックスの頂点は正規化されません。頂点の値は実際のピクセル値になります。オリジナル画像に合わせて 0 から 1 の範囲でスケーリングされません。これらの頂点の値は [(33,22),(282,22),(282,278),(33,278)] になります。


{
  "name": "projects/project-id/locations/location-id/products/product-id/referenceImages/image-id",
  "uri": "gs://storage-bucket/filename.jpg",
  "boundingPolys": [
    {
      "vertices": [
        {
          "x": 33,
          "y": 22
        },
        {
          "x": 282,
          "y": 22
        },
        {
          "x": 282,
          "y": 278
        },
        {
          "x": 33,
          "y": 278
        }
      ]
    }
  ]
}

C#

private static int CreateReferenceImage(CreateReferenceImageOptions opts)
{
    var client = ProductSearchClient.Create();
    var request = new CreateReferenceImageRequest
    {
        // Get the full path of the product.
        ParentAsProductName = new ProductName(opts.ProjectID,
                                              opts.ComputeRegion,
                                              opts.ProductID),
        ReferenceImageId = opts.ReferenceImageID,
        // Create a reference image.
        ReferenceImage = new ReferenceImage
        {
            Uri = opts.ReferenceImageURI
        }
    };

    var referenceImage = client.CreateReferenceImage(request);

    Console.WriteLine($"Reference image name: {referenceImage.Name}");
    Console.WriteLine($"Reference image URI: {referenceImage.Uri}");

    return 0;
}

Go


import (
	"context"
	"fmt"
	"io"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

// createReferenceImage creates a reference image for a product.
func createReferenceImage(w io.Writer, projectID string, location string, productID string, referenceImageID string, gcsURI string) error {
	ctx := context.Background()
	c, err := vision.NewProductSearchClient(ctx)
	if err != nil {
		return fmt.Errorf("NewProductSearchClient: %v", err)
	}
	defer c.Close()

	req := &visionpb.CreateReferenceImageRequest{
		Parent: fmt.Sprintf("projects/%s/locations/%s/products/%s", projectID, location, productID),
		ReferenceImage: &visionpb.ReferenceImage{
			Uri: gcsURI,
		},
		ReferenceImageId: referenceImageID,
	}

	resp, err := c.CreateReferenceImage(ctx, req)
	if err != nil {
		return fmt.Errorf("CreateReferenceImage: %v", err)
	}

	fmt.Fprintf(w, "Reference image name: %s\n", resp.Name)
	fmt.Fprintf(w, "Reference image uri: %s\n", resp.Uri)

	return nil
}

Java

/**
 * Create a reference image.
 *
 * @param projectId - Id of the project.
 * @param computeRegion - Region name.
 * @param productId - Id of the product.
 * @param referenceImageId - Id of the image.
 * @param gcsUri - Google Cloud Storage path of the input image.
 * @throws IOException - on I/O errors.
 */
public static void createReferenceImage(
    String projectId,
    String computeRegion,
    String productId,
    String referenceImageId,
    String gcsUri)
    throws IOException {
  try (ProductSearchClient client = ProductSearchClient.create()) {

    // Get the full path of the product.
    String formattedParent =
        ProductSearchClient.formatProductName(projectId, computeRegion, productId);
    // Create a reference image.
    ReferenceImage referenceImage = ReferenceImage.newBuilder().setUri(gcsUri).build();

    ReferenceImage image =
        client.createReferenceImage(formattedParent, referenceImage, referenceImageId);
    // Display the reference image information.
    System.out.println(String.format("Reference image name: %s", image.getName()));
    System.out.println(String.format("Reference image uri: %s", image.getUri()));
  }
}

Node.js

async function createReferenceImage() {
  const vision = require('@google-cloud/vision');

  const client = new vision.ProductSearchClient();

  /**
   * TODO(developer): Uncomment the following line before running the sample.
   */
  // const projectId = 'Your Google Cloud project Id';
  // const location = 'A compute region name';
  // const productId = 'Id of the product';
  // const referenceImageId = 'Id of the reference image';
  // const gcsUri = 'Google Cloud Storage path of the input image';

  const formattedParent = client.productPath(projectId, location, productId);

  const referenceImage = {
    uri: gcsUri,
  };

  const request = {
    parent: formattedParent,
    referenceImage: referenceImage,
    referenceImageId: referenceImageId,
  };

  const [response] = await client.createReferenceImage(request);
  console.log(`response.name: ${response.name}`);
  console.log(`response.uri: ${response.uri}`);
}

PHP

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Vision\V1\ProductSearchClient;
use Google\Cloud\Vision\V1\ReferenceImage;

/**
 * Create a reference image
 *
 * @param string $projectId Your Google Cloud project ID
 * @param string $location Google Cloud compute region name
 * @param string $productId ID of the product
 * @param string $referenceImageId ID of the reference image
 * @param string $gcsUri Google Cloud Storage path of the input image
 */
function product_image_create($projectId, $location, $productId, $referenceImageId, $gcsUri)
{
    $client = new ProductSearchClient();

    # get the name of the product.
    $productPath = $client->productName($projectId, $location, $productId);

    # create a reference image.
    $referenceImage = (new ReferenceImage())
        ->setUri($gcsUri);

    # the response is the reference image with `name` populated.
    $image = $client->createReferenceImage($productPath, $referenceImage, ['referenceImageId' => $referenceImageId]);

    # display the reference image information
    printf('Reference image name: %s' . PHP_EOL, $image->getName());
    printf('Reference image uri: %s' . PHP_EOL, $image->getUri());

    $client->close();
}

Python

from google.cloud import vision

def create_reference_image(
        project_id, location, product_id, reference_image_id, gcs_uri):
    """Create a reference image.
    Args:
        project_id: Id of the project.
        location: A compute region name.
        product_id: Id of the product.
        reference_image_id: Id of the reference image.
        gcs_uri: Google Cloud Storage path of the input image.
    """
    client = vision.ProductSearchClient()

    # Get the full path of the product.
    product_path = client.product_path(
        project=project_id, location=location, product=product_id)

    # Create a reference image.
    reference_image = vision.types.ReferenceImage(uri=gcs_uri)

    # The response is the reference image with `name` populated.
    image = client.create_reference_image(
        parent=product_path,
        reference_image=reference_image,
        reference_image_id=reference_image_id)

    # Display the reference image information.
    print('Reference image name: {}'.format(image.name))
    print('Reference image uri: {}'.format(image.uri))

Ruby

require "google/cloud/vision"

def product_search_create_reference_image project_id = "your-project-id",
                                          location   = "us-west1",
                                          product_id = "your-product-id"

  client = Google::Cloud::Vision.product_search

  product_path = client.product_path project:  project_id,
                                     location: location,
                                     product:  product_id
  reference_image = {
    uri: "gs://cloud-samples-data/vision/product_search/shoes_1.jpg"
  }

  reference_image = client.create_reference_image parent:          product_path,
                                                  reference_image: reference_image

  puts "Added reference image to #{product_id}."
  puts "Reference image name: #{reference_image.name}"
  puts "Reference image uri: #{reference_image.uri}"
end

レスポンス

Reference image name: projects/prj-prod-search-tutorials/locations/us-east1/products/P_CLOTH-SHOE_46903668_070318/referenceImages/I_469a896b70ba11e8be97d20059124800_070418
Reference image id: I_469a896b70ba11e8be97d20059124800_070418
Reference image uri: gs://product-search-tutorial/dress-shoe-dataset/469a896b70ba11e8be97d20059124800.jpg
Reference image bounding polygons:
vertices {
  x: 80
  y: 50
}
vertices {
  x: 80
  y: 660
}
vertices {
  x: 300
  y: 50
}
vertices {
  x: 430
  y: 660
}

ステップ 2: 一致する商品を検索する

このインターフェースでは、新しい画像を入力として受け取り、最も一致する商品を検索することで、作成した商品カタログをクエリできます。

参照画像の作成と同様、一致画像の検索時は必要に応じて境界ポリゴン座標を指定できます。境界ポリゴンは、一致を検索するソース画像の対象領域を特定します。たとえば、ドレスと財布の両方が含まれるソース画像でドレスの一致のみを検索する必要があるとします。このような場合にドレスのみが含まれる画像の領域の境界ポリゴン座標を特定できます。境界ポリゴンが指定されていない場合、デフォルトでは、API によって最大の境界ポリゴンが判定され、それに対するクエリが自動的に行われます。

画像の境界ポリゴン座標の取得には、Vision API のオブジェクト ローカライズを使用すると便利です。オブジェクト ローカライズの詳細については、複数のオブジェクトを検出するをご覧ください。たとえば、画像ボックス全体の境界ポリゴン [(0, 0), (0, 1), (1, 1), (1, 0)] を指定すると、明示的に画像全体に対するクエリを行うことができます。

リクエストは、画像と最も一致する商品、スコア、一致画像を含む API レスポンスを返します。この画像は、最高信頼値を使用して返されます。

REST とコマンドライン

後述のリクエストのデータを使用する前に、次のように置き換えます。

  • base64-encoded-image: バイナリ画像データの base64 表現（ASCII 文字列）。これは次のような文字列になります。
    • /9j/4QAYRXhpZgAA...9tAVx/zDQDlGxn//2Q==
    詳細については、base64 エンコードをご覧ください。
  • project-id: GCP プロジェクト ID
  • location-id: 有効なロケーション ID。有効なロケーション識別子は us-west1、us-east1、europe-west1、asia-east1 です。
  • product-set-id: 操作を実行する商品セットの ID。

フィールド固有の考慮事項:

  • features.maxResults - 返される結果の最大件数です。
  • imageContext.productCategories - 検索を実行する商品カテゴリです。現在、商品カテゴリは、ホームグッズ、アパレル、玩具、グッズ、総合から 1 つのみ指定できます。
  • imageContext.filter - 商品ラベルに対する Key-Value の単一または複数のフィルタリング式です。フォーマット: 「key = value」。フィルタリングする Key-Value ペアは、次のように AND 式または OR 式を使ってリンクできます。「color = blue AND style = mens」、または「color = blue OR color = black」。OR 式を使用する場合、式の鍵がすべて同じである必要があります。

HTTP メソッドと URL:

POST https://vision.googleapis.com/v1/images:annotate

JSON 本文のリクエスト: 

{
  "requests": [
    {
      "image": {
        "content": base64-encoded-image
      },
      "features": [
        {
          "type": "PRODUCT_SEARCH",
          "maxResults": 5
        }
      ],
      "imageContext": {
        "productSearchParams": {
          "productSet": "projects/project-id/locations/location-id/productSets/product-set-id",
          "productCategories": [
               "apparel"
          ],
          "filter": "style = womens"
        }
      }
    }
  ]
}

リクエストを送信するには、次のいずれかのオプションを選択します。

curl

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://vision.googleapis.com/v1/images:annotate

PowerShell

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://vision.googleapis.com/v1/images:annotate" | Select-Object -Expand Content

リクエストが成功すると、サーバーは 200 OK HTTP ステータス コードと JSON 形式のレスポンスを返します。

レスポンスの JSON は次のようになります。

  • productSearchResults - 画像全体に一致する商品のリストが含まれます。サンプルのレスポンスで、一致する商品は product_id65、product_id35、product_id34、product_id62、product_id32 です。
  • productGroupedResults - 境界ボックスの座標と、画像で識別されたそれぞれの商品に一致するアイテムが含まれます。次のレスポンスでは、識別された商品は 1 つのみで、続いてサンプルの商品セットと一致する商品（product_id65、product_id35、product_id34、product_id93、product_id62）が表示されます。

2 つの結果のデータの種類には重複がありますが、レスポンスが異なる（たとえば product_id32 や product_id93 など）場合もあります。

C#

private static int GetSimilarProductsFile(GetSimilarProductsOptions opts)
{
    // Create annotate image request along with product search feature.
    Image image = Image.FromFile(opts.FilePath);
    var imageAnnotatorClient = ImageAnnotatorClient.Create();

    // Product Search specific parameters
    var productSearchParams = new ProductSearchParams
    {
        ProductSetAsProductSetName = new ProductSetName(opts.ProjectID,
                                                        opts.ComputeRegion,
                                                        opts.ProductSetId),
        ProductCategories = { opts.ProductCategory },
        Filter = opts.Filter
    };

    // Search products similar to the image.
    var results = imageAnnotatorClient.DetectSimilarProducts(image, productSearchParams);

    Console.WriteLine("Similar products:");
    foreach (var result in results.Results)
    {
        var product = result.Product;
        Console.WriteLine($"Score (Confidence): {result.Score}");
        Console.WriteLine($"Image name: {result.Image}");
        Console.WriteLine($"Product name: {product.Name}");
        Console.WriteLine($"Product display name: {product.DisplayName}");
        Console.WriteLine($"Product description: {product.Description}");
        Console.WriteLine($"Product labels: {product.ProductLabels}");
    }
    return 0;
}

Go


import (
	"context"
	"fmt"
	"io"
	"os"

	vision "cloud.google.com/go/vision/apiv1"
	visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

// getSimilarProducts searches for products from a product set similar to products in an image file.
func getSimilarProducts(w io.Writer, projectID string, location string, productSetID string, productCategory string, file string, filter string) error {
	ctx := context.Background()
	c, err := vision.NewImageAnnotatorClient(ctx)
	if err != nil {
		return fmt.Errorf("NewImageAnnotatorClient: %v", err)
	}
	defer c.Close()

	f, err := os.Open(file)
	if err != nil {
		return fmt.Errorf("Open: %v", err)
	}
	defer f.Close()

	image, err := vision.NewImageFromReader(f)
	if err != nil {
		return fmt.Errorf("NewImageFromReader: %v", err)
	}

	ictx := &visionpb.ImageContext{
		ProductSearchParams: &visionpb.ProductSearchParams{
			ProductSet:        fmt.Sprintf("projects/%s/locations/%s/productSets/%s", projectID, location, productSetID),
			ProductCategories: []string{productCategory},
			Filter:            filter,
		},
	}

	response, err := c.ProductSearch(ctx, image, ictx)
	if err != nil {
		return fmt.Errorf("ProductSearch: %v", err)
	}

	fmt.Fprintf(w, "Product set index time:\n")
	fmt.Fprintf(w, "seconds: %d\n", response.IndexTime.Seconds)
	fmt.Fprintf(w, "nanos: %d\n", response.IndexTime.Nanos)

	fmt.Fprintf(w, "Search results:\n")
	for _, result := range response.Results {
		fmt.Fprintf(w, "Score(Confidence): %f\n", result.Score)
		fmt.Fprintf(w, "Image name: %s\n", result.Image)

		fmt.Fprintf(w, "Prodcut name: %s\n", result.Product.Name)
		fmt.Fprintf(w, "Product display name: %s\n", result.Product.DisplayName)
		fmt.Fprintf(w, "Product labels: %s\n", result.Product.ProductLabels)
	}

	return nil
}

Java

/**
 * Search similar products to image in local file.
 *
 * @param projectId - Id of the project.
 * @param computeRegion - Region name.
 * @param productSetId - Id of the product set.
 * @param productCategory - Category of the product.
 * @param filePath - Local file path of the image to be searched
 * @param filter - Condition to be applied on the labels. Example for filter: (color = red OR
 *     color = blue) AND style = kids It will search on all products with the following labels:
 *     color:red AND style:kids color:blue AND style:kids
 * @throws IOException - on I/O errors.
 */
public static void getSimilarProductsFile(
    String projectId,
    String computeRegion,
    String productSetId,
    String productCategory,
    String filePath,
    String filter)
    throws IOException {
  try (ImageAnnotatorClient queryImageClient = ImageAnnotatorClient.create()) {

    // Get the full path of the product set.
    String productSetPath =
        ProductSearchClient.formatProductSetName(projectId, computeRegion, productSetId);

    // Read the image as a stream of bytes.
    File imgPath = new File(filePath);
    byte[] content = Files.readAllBytes(imgPath.toPath());

    // Create annotate image request along with product search feature.
    Feature featuresElement = Feature.newBuilder().setType(Type.PRODUCT_SEARCH).build();
    // The input image can be a HTTPS link or Raw image bytes.
    // Example:
    // To use HTTP link replace with below code
    //  ImageSource source = ImageSource.newBuilder().setImageUri(imageUri).build();
    //  Image image = Image.newBuilder().setSource(source).build();
    Image image = Image.newBuilder().setContent(ByteString.copyFrom(content)).build();
    ImageContext imageContext =
        ImageContext.newBuilder()
            .setProductSearchParams(
                ProductSearchParams.newBuilder()
                    .setProductSet(productSetPath)
                    .addProductCategories(productCategory)
                    .setFilter(filter))
            .build();

    AnnotateImageRequest annotateImageRequest =
        AnnotateImageRequest.newBuilder()
            .addFeatures(featuresElement)
            .setImage(image)
            .setImageContext(imageContext)
            .build();
    List<AnnotateImageRequest> requests = Arrays.asList(annotateImageRequest);

    // Search products similar to the image.
    BatchAnnotateImagesResponse response = queryImageClient.batchAnnotateImages(requests);

    List<Result> similarProducts =
        response.getResponses(0).getProductSearchResults().getResultsList();
    System.out.println("Similar Products: ");
    for (Result product : similarProducts) {
      System.out.println(String.format("\nProduct name: %s", product.getProduct().getName()));
      System.out.println(
          String.format("Product display name: %s", product.getProduct().getDisplayName()));
      System.out.println(
          String.format("Product description: %s", product.getProduct().getDescription()));
      System.out.println(String.format("Score(Confidence): %s", product.getScore()));
      System.out.println(String.format("Image name: %s", product.getImage()));
    }
  }
}

Node.js

async function getSimilarProductsFile() {
  // Imports the Google Cloud client library
  const vision = require('@google-cloud/vision');
  const fs = require('fs');
  // Creates a client
  const productSearchClient = new vision.ProductSearchClient();
  const imageAnnotatorClient = new vision.ImageAnnotatorClient();

  /**
   * TODO(developer): Uncomment the following line before running the sample.
   */
  // const projectId = 'nodejs-docs-samples';
  // const location = 'us-west1';
  // const productSetId = 'indexed_product_set_id_for_testing';
  // const productCategory = 'apparel';
  // const filePath = './resources/shoes_1.jpg';
  // const filter = '';
  const productSetPath = productSearchClient.productSetPath(
    projectId,
    location,
    productSetId
  );
  const content = fs.readFileSync(filePath, 'base64');
  const request = {
    // The input image can be a GCS link or HTTPS link or Raw image bytes.
    // Example:
    // To use GCS link replace with below code
    // image: {source: {gcsImageUri: filePath}}    // To use HTTP link replace with below code
    // image: {source: {imageUri: filePath}}    image: {content: content},
    features: [{type: 'PRODUCT_SEARCH'}],
    imageContext: {
      productSearchParams: {
        productSet: productSetPath,
        productCategories: [productCategory],
        filter: filter,
      },
    },
  };
  const [response] = await imageAnnotatorClient.batchAnnotateImages({
    requests: [request],
  });
  console.log('Search Image:', filePath);
  const results = response['responses'][0]['productSearchResults']['results'];
  console.log('\nSimilar product information:');
  results.forEach(result => {
    console.log('Product id:', result['product'].name.split('/').pop(-1));
    console.log('Product display name:', result['product'].displayName);
    console.log('Product description:', result['product'].description);
    console.log('Product category:', result['product'].productCategory);
  });
}

PHP

namespace Google\Cloud\Samples\Vision;

use Google\Cloud\Vision\V1\ImageAnnotatorClient;
use Google\Cloud\Vision\V1\ProductSearchClient;
use Google\Cloud\Vision\V1\ProductSearchParams;

/**
 * Search similar products to image
 *
 * @param string $projectId Your Google Cloud project ID
 * @param string $location Google Cloud compute region name
 * @param string $productSetId ID of the product set
 * @param string $productCategory Category of the product
 * @param string $filePath Local file path of the image to be searched
 * @param string $filter Condition to be applied on the labels
 */
function product_search_similar($projectId, $location, $productSetId, $productCategory, $filePath, $filter)
{
    $imageAnnotatorClient = new ImageAnnotatorClient();
    $productSearchClient = new ProductSearchClient();

    # read the image
    $image = file_get_contents($filePath);

    # get the name of the product set
    $productSetPath = $productSearchClient->productSetName($projectId, $location, $productSetId);

    # product search specific parameters
    $productSearchParams = (new ProductSearchParams())
        ->setProductSet($productSetPath)
        ->setProductCategories([$productCategory])
        ->setFilter($filter);

    # search products similar to the image
    $response = $imageAnnotatorClient->productSearch($image, $productSearchParams);

    if ($productSearchResults = $response->getProductSearchResults()) {
        $indexTime = $productSearchResults->getIndexTime();
        printf('Product set index time: %d seconds %d nanos' . PHP_EOL, $indexTime->getSeconds(), $indexTime->getNanos());

        $results = $productSearchResults->getResults();
        print('Search results: ' . PHP_EOL);
        foreach ($results as $result) {
            printf('Score (confidence): %d' . PHP_EOL, $result->getScore());

            # display the product information.
            $product = $result->getProduct();
            $productName = $product->getName();
            $productNameArray = explode('/', $productName);

            printf('Product name: %s' . PHP_EOL, $productName);
            printf('Product id: %s' . PHP_EOL, end($productNameArray));
            printf('Product display name: %s' . PHP_EOL, $product->getDisplayName());
            printf('Product description: %s' . PHP_EOL, $product->getDescription());
            printf('Product category: %s' . PHP_EOL, $product->getProductCategory());
            print('Product labels: ' . PHP_EOL);
            foreach ($product->getProductLabels() as $label) {
                printf('%s : %s' . PHP_EOL, $label->getKey(), $label->getValue());
            }
        }
    } else {
        print($response->getError()->getMessage());
    }

    $imageAnnotatorClient->close();
    $productSearchClient->close();
}

Python

from google.cloud import vision

def get_similar_products_file(
        project_id, location, product_set_id, product_category,
        file_path, filter):
    """Search similar products to image.
    Args:
        project_id: Id of the project.
        location: A compute region name.
        product_set_id: Id of the product set.
        product_category: Category of the product.
        file_path: Local file path of the image to be searched.
        filter: Condition to be applied on the labels.
        Example for filter: (color = red OR color = blue) AND style = kids
        It will search on all products with the following labels:
        color:red AND style:kids
        color:blue AND style:kids
    """
    # product_search_client is needed only for its helper methods.
    product_search_client = vision.ProductSearchClient()
    image_annotator_client = vision.ImageAnnotatorClient()

    # Read the image as a stream of bytes.
    with open(file_path, 'rb') as image_file:
        content = image_file.read()

    # Create annotate image request along with product search feature.
    image = vision.types.Image(content=content)

    # product search specific parameters
    product_set_path = product_search_client.product_set_path(
        project=project_id, location=location,
        product_set=product_set_id)
    product_search_params = vision.types.ProductSearchParams(
        product_set=product_set_path,
        product_categories=[product_category],
        filter=filter)
    image_context = vision.types.ImageContext(
        product_search_params=product_search_params)

    # Search products similar to the image.
    response = image_annotator_client.product_search(
        image, image_context=image_context)

    index_time = response.product_search_results.index_time
    print('Product set index time:')
    print('  seconds: {}'.format(index_time.seconds))
    print('  nanos: {}\n'.format(index_time.nanos))

    results = response.product_search_results.results

    print('Search results:')
    for result in results:
        product = result.product

        print('Score(Confidence): {}'.format(result.score))
        print('Image name: {}'.format(result.image))

        print('Product name: {}'.format(product.name))
        print('Product display name: {}'.format(
            product.display_name))
        print('Product description: {}\n'.format(product.description))
        print('Product labels: {}\n'.format(product.product_labels))

Ruby

require "google/cloud/vision"

def product_search_get_similar_products \
    project_id       = "your-project-id",
    location         = "us-west1",
    product_set_id   = "your-product-set-id",
    product_category = "apparel",
    file_path        = "path/to/product_image.jpg",
    filter           = "(color = red OR color = blue) AND style = kids"

  product_search_client  = Google::Cloud::Vision.product_search
  image_annotator_client = Google::Cloud::Vision.image_annotator

  product_set_path = product_search_client.product_set_path(
    project:     project_id,
    location:    location,
    product_set: product_set_id
  )

  product_set = product_search_client.get_product_set name: product_set_path

  if product_set.index_time.seconds.zero?
    puts "Product set has not been indexed. Please wait and try again."
    return
  end

  product_search_params = {
    product_set:        product_set_path,
    product_categories: [product_category],
    filter:             filter
  }
  image_context = { product_search_params: product_search_params }

  response = image_annotator_client.product_search_detection(
    image:         file_path,
    image_context: image_context
  )

  display_similar_products response.responses.first.product_search_results
end

def display_similar_products search_results
  index_time = search_results.index_time
  puts "Product set index time:"
  puts "\tseconds: #{index_time.seconds}"
  puts "\tnanos: #{index_time.nanos}\n"

  puts "Search results:"
  search_results.results.each_with_index do |result, index|
    puts "Result #{index + 1}:"
    product = result.product

    puts "\tScore(Confidence): #{result.score}"
    puts "\tImage name: #{result.image}"

    puts "\tProduct name: #{product.name}"
    puts "\tProduct display name: #{product.display_name}"
    puts "\tProduct description: #{product.description}"
    puts "\tProduct labels: #{product.product_labels}"
  end
end

アパレルのレスポンス例

Search Image:
  D:/product/final/images-20180618T073733Z-01/images/469355b570ba11e88ff2d20059124800.jpg

画像の検索結果

Similar product information:
 Product id: 46930b6b
 Product display name: Evening gown
 Product description: Blue evening gown in 1940s style
 Product category: apparel
 style: women
 category: dress
 color: blue

ラベルを使用して検索する

次の検索例では、色を基準とするフィルタが含まれています。

リクエスト

検索をリクエストするには、get_similar_products_file() または get_similar_products_uri() メソッドを使用して次のリクエストを実行します。商品セット ID、ローカルの画像ファイルのパス、フィルタが引数として渡されます。この入力画像は resources/input/ にも格納されています。

Python

python product_search.py get_similar_products_file "12000002" "D:/product/final/images-20180618T073733Z-001/images/469355b570ba11e88ff2d20059124800.jpg" "color=white"

レスポンス

Search Image:
  D:/product/final/images-20180618T073733Z-001/images/469355b570ba11e88ff2d20059124800.jpg

画像の検索結果 2

Similar product information:
 Product id: p569d4e7a1
 Product display name: Wedding Dress
 Product description: Elegant Wedding Dress for women
 Product category: apparel
 style: women
 category: dress
 color: white