產品搜尋功能目前處於維護模式。如要提高擴充性，並使用與產品搜尋相同的功能，請使用Vision Warehouse。

Vision API Product Search 用戶端程式庫

本頁說明如何開始使用 Vision API Product Search 適用的 Cloud 用戶端程式庫。有了用戶端程式庫，您可以透過支援的語言，更輕鬆地存取Google Cloud API。雖然您可以直接向伺服器發出原始要求來使用Google Cloud API，但用戶端程式庫提供簡化功能，可大幅減少需要編寫的程式碼數量。

如要進一步瞭解 Cloud 用戶端程式庫和舊版 Google API 用戶端程式庫，請參閱「用戶端程式庫說明」。

安裝用戶端程式庫

C++

請參閱「設定 C++ 開發環境」，進一步瞭解這個用戶端程式庫的需求，以及如何安裝依附元件。

C#

如果是使用 Visual Studio 2017 以上版本，請開啟 NuGet 套件管理工具視窗，然後輸入下列內容：

Install-Package Google.Apis

如果是使用 .NET Core 指令列介面工具安裝依附元件，請執行下列指令：

dotnet add package Google.Apis

詳情請參閱「設定 C# 開發環境」。

Go

go get cloud.google.com/go/vision/apiv1

詳情請參閱「設定 Go 開發環境」。

Java

如果您使用 Maven，請將下列指令新增到 pom.xml 檔案中。如要進一步瞭解 BOM，請參閱 Google Cloud Platform 程式庫 BOM。

<dependencyManagement>
  <dependencies>
    <dependency>
      <groupId>com.google.cloud</groupId>
      <artifactId>libraries-bom</artifactId>
      <version>26.79.0</version>
      <type>pom</type>
      <scope>import</scope>
    </dependency>
  </dependencies>
</dependencyManagement>

<dependencies>
  <dependency>
    <groupId>com.google.cloud</groupId>
    <artifactId>google-cloud-vision</artifactId>
  </dependency>
</dependencies>

如果您使用 Gradle，請將下列指令新增到依附元件中：

implementation 'com.google.cloud:google-cloud-vision:3.86.0'

如果您使用 sbt，請在依附元件中加入以下指令：

libraryDependencies += "com.google.cloud" % "google-cloud-vision" % "3.86.0"

如果您使用 Visual Studio Code 或 IntelliJ，可以利用下列 IDE 外掛程式，將用戶端程式庫新增到專案中：

這些外掛程式會提供其他功能，例如服務帳戶的金鑰管理功能。詳情請參閱各外掛程式的說明文件。

詳情請參閱「設定 Java 開發環境」。

Node.js

npm install @google-cloud/vision

詳情請參閱「設定 Node.js 開發環境」。

PHP

composer require google/apiclient

詳情請參閱「在 Google Cloud 上使用 PHP」。

Python

pip install --upgrade google-cloud-vision

詳情請參閱「設定 Python 開發環境」。

Ruby

gem install google-api-client

詳情請參閱「設定 Ruby 開發環境」。

設定驗證方法

為驗證向 Google Cloud API 發出的呼叫，用戶端程式庫支援應用程式預設憑證 (ADC)；程式庫會在定義的一組位置中尋找憑證，並使用這些憑證驗證向 API 發出的要求。有了 ADC，無需修改應用程式程式碼，就能在各種環境 (例如本機開發環境或正式環境)，為應用程式提供憑證。

在正式環境中，設定 ADC 的方式取決於服務和背景。詳情請參閱「設定應用程式預設憑證」。

在本機開發環境中，您可以使用與 Google 帳戶相關聯的憑證設定 ADC：

安裝 Google Cloud CLI。完成後，執行下列指令來初始化 Google Cloud CLI：
```
gcloud init
```
若您採用的是外部識別資訊提供者 (IdP)，請先使用聯合身分登入 gcloud CLI。
如果您使用本機殼層，請為使用者帳戶建立本機驗證憑證：
```
gcloud auth application-default login
```
如果您使用 Cloud Shell，則不需要執行這項操作。

如果系統傳回驗證錯誤，且您使用外部識別資訊提供者 (IdP)，請確認您已使用聯合身分登入 gcloud CLI。

登入畫面會隨即顯示。登入後，您的憑證會儲存在 ADC 使用的本機憑證檔案中。

使用用戶端程式庫

以下範例將說明用戶端程式庫的使用方法。

C++


#include "google/cloud/vision/v1/image_annotator_client.h"
#include <iostream>

int main(int argc, char* argv[]) try {
  auto constexpr kDefaultUri =
      "gs://cloud-samples-data/vision/label/wakeupcat.jpg";
  if (argc > 2) {
    std::cerr << "Usage: " << argv[0] << " [gcs-uri]\n"
              << "  The gcs-uri must be in gs://... format. It defaults to "
              << kDefaultUri << "\n";
    return 1;
  }
  auto uri = std::string{argc == 2 ? argv[1] : kDefaultUri};

  namespace vision = ::google::cloud::vision_v1;
  auto client =
      vision::ImageAnnotatorClient(vision::MakeImageAnnotatorConnection());

  // Define the image we want to annotate
  google::cloud::vision::v1::Image image;
  image.mutable_source()->set_image_uri(uri);
  // Create a request to annotate this image with Request text annotations for a
  // file stored in GCS.
  google::cloud::vision::v1::AnnotateImageRequest request;
  *request.mutable_image() = std::move(image);
  request.add_features()->set_type(
      google::cloud::vision::v1::Feature::TEXT_DETECTION);

  google::cloud::vision::v1::BatchAnnotateImagesRequest batch_request;
  *batch_request.add_requests() = std::move(request);
  auto batch = client.BatchAnnotateImages(batch_request);
  if (!batch) throw std::move(batch).status();

  // Find the longest annotation and print it
  auto result = std::string{};
  for (auto const& response : batch->responses()) {
    for (auto const& annotation : response.text_annotations()) {
      if (result.size() < annotation.description().size()) {
        result = annotation.description();
      }
    }
  }
  std::cout << "The image contains this text: " << result << "\n";

  return 0;
} catch (google::cloud::Status const& status) {
  std::cerr << "google::cloud::Status thrown: " << status << "\n";
  return 1;
}

Go


import (
	"context"
	"fmt"
	"io"

	vision "cloud.google.com/go/vision/apiv1"
	"cloud.google.com/go/vision/v2/apiv1/visionpb"
)

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

	image := vision.NewImageFromURI(imageURI)

	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: %w", 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 = ProductSetName.format(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

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

async function getSimilarProductsGcs(
  projectId,
  location,
  productSetId,
  productCategory,
  filePath,
  filter
) {
  /**
   * 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 productCategory = 'Category of the product';
  // const filePath = 'Local file path of the image to be searched';
  // const filter = 'Condition to be applied on the labels';
  const productSetPath = productSearchClient.productSetPath(
    projectId,
    location,
    productSetId
  );

  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: {source: {gcsImageUri: filePath}},
    features: [{type: 'PRODUCT_SEARCH'}],
    imageContext: {
      productSearchParams: {
        productSet: productSetPath,
        productCategories: [productCategory],
        filter: filter,
      },
    },
  };
  console.log(request.image);

  const [response] = await imageAnnotatorClient.batchAnnotateImages({
    requests: [request],
  });
  console.log('Search Image:', filePath);
  console.log('\nSimilar product information:');

  const results = response['responses'][0]['productSearchResults']['results'];
  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);
  });
}
getSimilarProductsGcs();

Python

from google.cloud import vision

def get_similar_products_uri(
    project_id, location, product_set_id, product_category, image_uri, 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.
        image_uri: Cloud Storage location of 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()

    # Create annotate image request along with product search feature.
    image_source = vision.ImageSource(image_uri=image_uri)
    image = vision.Image(source=image_source)

    # 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.ProductSearchParams(
        product_set=product_set_path,
        product_categories=[product_category],
        filter=filter,
    )
    image_context = vision.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(index_time)

    results = response.product_search_results.results

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

        print(f"Score(Confidence): {result.score}")
        print(f"Image name: {result.image}")

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

其他資源

C++

下方列出與 C++ 用戶端程式庫相關的其他資源連結：

C#

下方列出與 C# 用戶端程式庫相關的其他資源連結：

Go

下方列出與 Go 用戶端程式庫相關的其他資源連結：

Java

下方列出與 Java 用戶端程式庫相關的其他資源連結：

Node.js

下方列出與 Node.js 用戶端程式庫相關的其他資源連結：

PHP

下方列出與 PHP 用戶端程式庫相關的其他資源連結：

Python

下方列出與 Python 用戶端程式庫相關的其他資源連結：

Ruby

下方列出與 Ruby 用戶端程式庫相關的其他資源連結：

歡迎試用

如果您未曾使用過 Google Cloud，歡迎建立帳戶，親自體驗實際使用 Cloud Vision API 的成效。新客戶還能獲得價值 $300 美元的免費抵免額，用於執行、測試及部署工作負載。

免費試用 Cloud Vision API

Vision API Product Search 用戶端程式庫 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

安裝用戶端程式庫

C++

C#

Go

Java

Node.js

PHP

Python

Ruby

設定驗證方法

使用用戶端程式庫

C++

Go

Java

Node.js

Python

其他資源

C++

C#

Go

Java

Node.js

PHP

Python

Ruby

歡迎試用

Vision API Product Search 用戶端程式庫