Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Deploying an Amazon Personalize solution version with a campaign

For real-time recommendations with custom resources, after you complete Manually creating a solution version, you are ready to deploy your solution version with a campaign.

A campaign deploys a solution version (trained model) with a provisioned transaction capacity for generating real-time recommendations. After you create a campaign, you use the GetRecommendations or GetPersonalizedRanking API operations to get recommendations. If you are getting batch item recommendations or user segments, you don't need to create a campaign. For more information, see Getting batch item recommendations or Getting batch user segments.

When you create a campaign, you can configure the following:

You can create a campaign with the Amazon Personalize console, Amazon Command Line Interface (Amazon CLI), or Amazon SDKs. If you want to change an existing campaign's settings, such as enabling metadata in recommendations, you must update your campaign. For more information, see Updating an Amazon Personalize campaign's configuration.

You incur campaign costs while the campaign is active. To avoid unnecessary costs, make sure to delete the campaign when you are finished. For information about campaign costs, see Amazon Personalize pricing.

Automatic campaign updates

When you create a campaign, you can enable automatic campaign updates. With automatic updates, the campaign automatically updates to deploy the latest automatically or manually trained solution version of your solution. This makes it easier for you to keep your campaign current.

For example, if your solution uses automatic training to create a new solution version every seven days, your campaign would automatically update to use the latest solution version for every weekly training. If you don't use automatic campaign updates, you must manually update the campaign to deploy the latest trained model.

Minimum provisioned transactions per second and auto-scaling

When you create an Amazon Personalize campaign, you can specify the minimum provisioned transactions per second (minProvisionedTPS) for the campaign. This is the baseline transaction throughput for the campaign provisioned by Amazon Personalize. It sets the minimum billing charge for the campaign while it is active. A transaction is a single GetRecommendations or GetPersonalizedRanking request. The default minProvisionedTPS is 1.

If your TPS increases beyond the minProvisionedTPS, Amazon Personalize auto-scales the provisioned capacity up and down, but never below minProvisionedTPS. There's a short time delay while the capacity is increased that might cause loss of transactions. When your traffic reduces, capacity returns to the minProvisionedTPS.

You are charged for the minimum provisioned TPS or, if your requests exceed the minProvisionedTPS, the actual TPS. The actual TPS is the total number of recommendation requests you make. We recommend starting with a low minProvisionedTPS, track your usage using Amazon CloudWatch metrics, and then increase the minProvisionedTPS as necessary.

For more information about campaign costs, see Amazon Personalize pricing.

Item metadata in recommendations

When you get recommendations, you can have Amazon Personalize include item metadata in recommendation results. In your request, you can choose the columns from your Items dataset to include. Amazon Personalize returns this data for each item in the recommendation response.

You might use metadata to enrich recommendations in your user interface, such as adding the genres for movies to carousels. Or you might use it to visually assess recommendation quality. If you use generative AI in your app, you can plug the metadata into AI prompts to generate more relevant content. For more information about using Amazon Personalize with generative AI, see Amazon Personalize and generative AI.

Enabling metadata

To add metadata to recommendations, you must have an Items dataset with a column of metadata. You don't have to use the metadata in training. For information about creating a dataset, see Creating a schema and a dataset. For information updating data, see Updating data in datasets after training.

If you use the User-Personalization-v2 or Personalized-Ranking-v2 recipe, new campaigns automatically have the option to include item metadata with recommendation results. You don't have manually enable metadata for your campaign. For all other recipes and domain use cases, you must enable the metadata option:

Creating a campaign (console)

After your solution version status is Active, you are ready to deploy it with an Amazon Personalize campaign.

Creating a campaign (Amazon CLI)

After your solution version is Active, you are ready to deploy it with an Amazon Personalize campaign. To create a campaign with the Amazon CLI, you use the create-campaign command.

The following code sample shows you how to create a campaign. It deploys the latest solution version of a solution that uses the User-Personalization recipe. The campaign it creates automatically updates to use future solution versions. The code uses the following configuration:

For a complete list of all parameters, see CreateCampaign.

aws personalize create-campaign \
--name campaign-name \
--solution-version-arn solution-arn/\$LATEST \
--min-provisioned-tps 1 \
--campaign-config "{"\"syncWithLatestSolutionVersion"\": "true", "\"enableMetadataWithRecommendations"\": "true"}"

The campaign is ready when its status is ACTIVE. To get the current status, call DescribeCampaign and check that the status field is ACTIVE.

If you retrain your solution version and your campaign doesn't automatically update to use the latest solution version, or if your want to change your campaign settings, you must update your campaign. For more information, see Updating an Amazon Personalize campaign's configuration.

Amazon Personalize provides you with operations for managing campaigns such as ListCampaigns to list the campaigns that you have created. You can delete a campaign by calling DeleteCampaign. If you delete a campaign, the solution versions that are part of the campaign are not deleted.

After you have created your campaign, you can use it to make recommendations. For more information, see Getting recommendations from Amazon Personalize.

Creating a campaign (Amazon SDKs)

After your solution version is Active, you are ready to deploy it with an Amazon Personalize campaign. To create a campaign with Amazon SDKs, you use the CreateCampaign API operation.

The following code sample shows you how to create a campaign. The code deploys the latest solution version of a solution that uses the User-Personalization recipe. The campaign it creates automatically updates to use future solution versions. The code uses the following configuration:

For a complete list of all parameters, see CreateCampaign.

SDK for Python (Boto3)

import boto3

personalize = boto3.client('personalize')

response = personalize.create_campaign(
    name = 'campaign name',
    solutionVersionArn = 'solution ARN/$LATEST',
    minProvisionedTPS = 1,
    campaignConfig = {"syncWithLatestSolutionVersion": True, "enableMetadataWithRecommendations": True}
)

arn = response['campaignArn']

description = personalize.describe_campaign(campaignArn = arn)['campaign']
print('Name: ' + description['name'])
print('ARN: ' + description['campaignArn'])
print('Status: ' + description['status'])

SDK for JavaScript v3

// Get service clients module and commands using ES6 syntax.
import { CreateCampaignCommand, PersonalizeClient } from
  "@aws-sdk/client-personalize";

// create personalizeClient
const personalizeClient = new PersonalizeClient({ region: "REGION" });

// set the campaign parameters
export const createCampaignParam = {
  solutionVersionArn: "SOLUTION_ARN/$LATEST" /* required */,
  name: "NAME" /* required */,
  minProvisionedTPS: 1 /* optional */,
  campaignConfig: {   /* optional */
    syncWithLatestSolutionVersion: true,
    enableMetadataWithRecommendations: true,
  },
};

export const run = async () => {
  try {
    const response = await personalizeClient.send(
      new CreateCampaignCommand(createCampaignParam)
    );
    console.log("Success", response);
    return response; // For unit tests.
  } catch (err) {
    console.log("Error", err);
  }
};
run();

The campaign is ready when its status is ACTIVE. To get the current status, call DescribeCampaign, and check that the status field is ACTIVE.

If you manually retrain your solution version, or if you want to change your campaign settings, you must update your campaign. For more information, see Updating an Amazon Personalize campaign's configuration.

Amazon Personalize provides you with operations for managing campaigns such as ListCampaigns to list the campaigns that you have created. You can delete a campaign by calling DeleteCampaign. If you delete a campaign, the solution versions that are part of the campaign are not deleted.

After you have created your campaign, use it to make recommendations. For more information, see Getting recommendations from Amazon Personalize.