Jump to content

Amazon Personalize increases limits for all customers, simplifying large scale deployments


Recommended Posts

We are excited to announce that Amazon Personalize is increasing service limits and quotas for existing and new customers, making it easier to deploy Personalize at scale. Amazon Personalize enables developers to improve customer engagement through personalized product and content recommendations – no ML expertise required. Prior to this launch, limits on the use of certain Personalize resources and the rate of data import API calls were set at the AWS account level. For example, customers could use a maximum of 10 filters at a given time in their AWS account. Similarly, customers were limited to 1,000 PutEvent requests per second for their AWS account. With this launch, Personalize transitioned these limits and others from an account level to a dataset group (DSG) level. Customers can now have up to 10 filters and 1,000 PutEvents per second, per DSG. You can create up to 5 dataset groups per account, meaning you can create a total of 50 filters and 5,000 PutEvents per second for each AWS account. This means higher capacity from Amazon Personalize for customers with multiple use-cases or multiple tenants using Amazon Personalize in their applications. These improvements also make it easier to request limit increases. By simply requesting an increase for DSGs via the AWS quotas console, customers will also benefit from increased limits on other resources and API rates, when aggregated at the account level.

View the full article

Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...