Create a product set and search for products

This quickstart demonstrates how to create and use the three types of Vision API Product Search resources: a product set which contains a group of products, and reference images associated with those products.

In this quickstart you will create a product set, products, and their reference images in a single step by batch import.

After the product set has been indexed, you can query the product set using Vision API Product Search.

This quickstart steps you through the process of:

  • Using a CSV and bulk import to create a product set, products, and reference images.
  • Making a request to the Vision API Product Search with an image stored in a Cloud Storage bucket.

Before you begin

If you haven't done so already, set up your project as explained below.

Set up your project

  1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.
  2. Install the Google Cloud CLI.
  3. To initialize the gcloud CLI, run the following command:

    gcloud init
  4. Create or select a Google Cloud project.

    • Create a Google Cloud project:

      gcloud projects create PROJECT_ID

      Replace PROJECT_ID with a name for the Google Cloud project you are creating.

    • Select the Google Cloud project that you created:

      gcloud config set project PROJECT_ID

      Replace PROJECT_ID with your Google Cloud project name.

  5. Make sure that billing is enabled for your Google Cloud project.

  6. Enable the Vision API:

    gcloud services enable vision.googleapis.com
  7. Grant roles to your Google Account. Run the following command once for each of the following IAM roles: roles/storage.objectViewer

    gcloud projects add-iam-policy-binding PROJECT_ID --member="user:EMAIL_ADDRESS" --role=ROLE
    • Replace PROJECT_ID with your project ID.
    • Replace EMAIL_ADDRESS with your email address.
    • Replace ROLE with each individual role.
  8. Install the Google Cloud CLI.
  9. To initialize the gcloud CLI, run the following command:

    gcloud init
  10. Create or select a Google Cloud project.

    • Create a Google Cloud project:

      gcloud projects create PROJECT_ID

      Replace PROJECT_ID with a name for the Google Cloud project you are creating.

    • Select the Google Cloud project that you created:

      gcloud config set project PROJECT_ID

      Replace PROJECT_ID with your Google Cloud project name.

  11. Make sure that billing is enabled for your Google Cloud project.

  12. Enable the Vision API:

    gcloud services enable vision.googleapis.com
  13. Grant roles to your Google Account. Run the following command once for each of the following IAM roles: roles/storage.objectViewer

    gcloud projects add-iam-policy-binding PROJECT_ID --member="user:EMAIL_ADDRESS" --role=ROLE
    • Replace PROJECT_ID with your project ID.
    • Replace EMAIL_ADDRESS with your email address.
    • Replace ROLE with each individual role.

Set environment variables

To make it more convenient to run the curl samples in this quickstart, set the following environment variables where:

  • PROJECT_ID is the ID of your Google Cloud project.
  • LOCATION_ID is the Google Cloud location that will run your tutorial, for example, us-east1. Valid location identifiers are: us-west1, us-east1, europe-west1, and asia-east1 .

Using a dataset

In this quickstart you use a dataset of ~100 apparel-v2 product category entries. This publicly available dataset is located in a public Cloud Storage bucket at:

The CSV format is as follows:

gs://cloud-ai-vision-data/product-search-tutorial/images/filename1.jpg,image0,product_set0,product_id0,apparel-v2,,"style=women,category=shoe",
gs://cloud-ai-vision-data/product-search-tutorial/images/filename2.jpg,image1,product_set0,product_id1,apparel-v2,,"style=men,category=shoe",
gs://cloud-ai-vision-data/product-search-tutorial/images/filename3.jpg,image2,product_set0,product_id2,apparel-v2,,"style=women,category=dress",

Use bulk import to create a product set, products, and reference images

Use the following curl command to create a new product set with products and reference images. This set is named product_set0, a value declared in the import CSV.

First create a request JSON file called import_request.json and save it in your current working directory:

import_request.json

{
  "inputConfig": {
    "gcsSource": {
      "csvFileUri": "gs://cloud-samples-data/vision/product_search/product_catalog.csv"
    }
  }
}

After creating the request JSON file, send the request:

curl -X POST \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "x-goog-user-project: PROJECT_ID" \
    -H "Content-Type: application/json; charset=utf-8" \
    -d @import_request.json \
    https://vision.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/productSets:import

A successful response contains a long-running operation object:

{
  "name": "locations/LOCATION_ID/operations/0a0aec86192599fa"
}

The response also contains a relative operation ID (for example, 0a0aec86192599fa) that can be used to get the status of the operation.

Get import operation status

You can use the operation-id returned from the import operation to check the status of the bulk import operation:

curl -X GET \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "x-goog-user-project: PROJECT_ID" \
    -H "Content-Type: application/json" \
    https://vision.googleapis.com/v1/locations/LOCATION_ID/operations/OPERATION_ID

A successful response looks like:

{
  "name": "locations/LOCATION_ID/operations/0a0aec86192599fb",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.vision.v1.BatchOperationMetadata",
    "state": "SUCCESSFUL",
    "submitTime": "2018-11-30T03:11:04.808114024Z",
    "endTime": "2018-11-30T03:11:38.624444324Z"
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.vision.v1.ImportProductSetsResponse",
    "referenceImages": [
      {
        "name": "projects/PROJECT_ID/locations/LOCATION_ID/products/product_id0/referenceImages/image0",
        "uri": "gs://cloud-ai-vision-data/product-search-tutorial/images/46a0cbcf70ba11e89399d20059124800.jpg"
      },
      {
        "name": "projects/PROJECT_ID/locations/LOCATION_ID/products/product_id1/referenceImages/image1",
        "uri": "gs://cloud-ai-vision-data/product-search-tutorial/images/46a1aea370ba11e888d4d20059124800.jpg"
      },
      ...
      {
        "name": "projects/PROJECT_ID/locations/LOCATION_ID/products/product_id93/referenceImages/image93",
        "uri": "gs://cloud-ai-vision-data/product-search-tutorial/images/4697319970ba11e8a7bfd20059124800.jpg"
      },
      {
        "name": "projects/PROJECT_ID/locations/LOCATION_ID/products/product_id94/referenceImages/image94",
        "uri": "gs://cloud-ai-vision-data/product-search-tutorial/images/4698596370ba11e8bf6ad20059124800.jpg"
      }
    ],
    "statuses": [
      {},
      {},
      [...]
      {},
      {}
    ]
  }
}

Indexing

The Product Search index of products is updated approximately every 30 minutes. When images are added or deleted, the change won't be reflected in your Product Search responses until the index is next updated.

To make sure that indexing has completed successfully, check the indexTime field of a product set.

List product sets and check indexing

You can list all your product sets and use the indexTime field to verify that indexing has completed successfully:

curl -X GET \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "x-goog-user-project: PROJECT_ID" \
    -H "Content-Type: application/json" \
    https://vision.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/productSets

A successful response lists all your product sets, including a product set ID (for example, product_set0) as well as the indexTime field indicating when indexing completed:

{
  "productSets": [
    {
      "name": "projects/PROJECT_ID/locations/LOCATION_ID/productSets/product_set0",
      "displayName": " ",
      "indexTime": "2019-11-30T18:33:40.093508652Z",
      "indexError": {}
    }
  ]
}

List products

You can use the PRODUCT_SET_ID returned from the list of product sets to list all products in your product set:

curl -X GET \
    -H "Authorization: Bearer $(gcloud auth print-access-token)" \
    -H "x-goog-user-project: PROJECT_ID" \
    -H "Content-Type: application/json" \
    https://vision.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION_ID/productSets/PRODUCT_SET_ID/products?pageSize=15

A successful response lists product details.

In this request you use the optional query parameter pageSize to set the result list to 15 products. The nextPageToken in the response also indicates there are more products to list. You can use the token listed to retrieve further results. For more information on using a pageToken, see Getting and listing resources.

{
  "products": [
    {
      "name": "projects/PROJECT_ID/locations/LOCATION_ID/products/product_id0",
      "displayName": " ",
      "productCategory": "apparel",
      "productLabels": [
        {
          "key": "style",
          "value": "women"
        },
        {
          "key": "category",
          "value": "shoe"
        }
      ]
    },
    {
      "name": "projects/PROJECT_ID/locations/LOCATION_ID/products/product_id1",
      "displayName": " ",
      "productCategory": "apparel",
      "productLabels": [
        {
          "key": "style",
          "value": "men"
        },
        {
          "key": "category",
          "value": "shoe"
        }
      ]
    },
    ...
    {
      "name": "projects/PROJECT_ID/locations/LOCATION_ID/products/product_id21",
      "displayName": " ",
      "productCategory": "apparel",
      "productLabels": [
        {
          "key": "style",
          "value": "women"
        },
        {
          "key": "category",
          "value": "dress"
        }
      ]
    }
  ],
  "nextPageToken": "1LqhSgZfM_uWKOxvog"
}

Search for matching products with Vision API Product Search

After indexing is complete, you can search for products that match a sample image. In this quickstart you use an image stored in a Google Cloud Storage bucket such as the following image.

A dress image in a Cloud Storage bucket.
gs://cloud-ai-vision-data/product-search-tutorial/images/468f782e70ba11e8941fd20059124800.jpg

Search using a remote image

Use the following request to search using the image stored in a public Cloud Storage bucket.

First create a request JSON file called search_request.json and save it in your current working directory. Change the following values in the request JSON to match your project's information:

  • PROJECT_ID
  • LOCATION_ID
  • PRODUCT_SET_ID

search_request.json

{
  "requests": [
    {
      "image": {
        "source": {
          "gcsImageUri": "gs://cloud-ai-vision-data/product-search-tutorial/images/468f782e70ba11e8941fd20059124800.jpg"
        }
      },
      "features": [
        {
          "type": "PRODUCT_SEARCH"
        }
      ],
      "imageContext": {
        "productSearchParams": {
          "productSet": "projects/PROJECT_ID/locations/LOCATION_ID/productSets/PRODUCT_SET_ID",
          "productCategories": [
            "apparel-v2"
          ],
          "filter": "style=womens OR style=women"
        }
      }
    }
  ]
}

After creating the request JSON file, send the request:

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

A successful request returns a list of matching products, indicated by their product ID. These results are further broken down by individual products identified by bounding boxes if there are multiple products in a single image.

For an example of single-product detection and multi-detection of products in an image, see Understanding search responses & multi-detection.

A field score is returned as well. This field indicates the confidence at which the service feels the product matches the supplied image, on a scale of 0 (no confidence) to 1 (full confidence).

The indexTime field shows which version of the index is being searched. Image changes made after this time are not reflected in the results.

Congratulations! You've made your first images.annotate request to the Vision API Product Search service.

Clean up

  1. Optional: Revoke credentials from the gcloud CLI.

    gcloud auth revoke
  2. Delete a Google Cloud project:

    gcloud projects delete PROJECT_ID

What's next