reference deployment

Amazon SageMaker Autopilot for Snowflake on AWS

Connects Snowflake with SageMaker Autopilot ML models to power analytics

This Quick Start sets up an Amazon Web Services (AWS) architecture that automatically configures the integration between Amazon SageMaker Autopilot and Snowflake. You can use this Quick Start to add machine learning (ML) capabilities to your Snowflake account with Amazon SageMaker using familiar SQL syntax. SageMaker Autopilot automatically builds, trains, and tunes ML models based on the data in your data lake.

This Quick Start was developed by Snowflake in collaboration with AWS. Snowflake is an AWS Partner.

  •  What you'll build
  • This Quick Start sets up the following:

    • An AWS Lambda function to configure API integration, external functions, and custom serializers in your Snowflake account.
    • An Amazon API Gateway endpoint to integrate your AWS account with your Snowflake account.
    • Amazon SageMaker to apply ML models to your Snowflake data.
    • An Amazon Simple Storage Service (Amazon S3) bucket to store assets.
  •  How to deploy
  • To deploy this Quick Start, follow the steps in the deployment guide, which includes these steps. The stack takes about 10 minutes to launch.

    1. Sign in to your Snowflake account. If you don't have an account, sign up for one.
    2. Load a tabular dataset, such as a comma-separated-values (CSV) file, into Snowflake.
    3. Generate and upload the layer and Lambda code to an existing S3 bucket.
    4. Sign in to your AWS account. If you don't have an account, sign up at
    5. Deploy the Quick Start into your AWS account. Before you create the stack, choose the AWS Region from the top toolbar.

    Amazon may share user-deployment information with the AWS Partner that collaborated with AWS on this solution.  

  •  Cost and licenses
  • To deploy this Quick Start, you must have a Snowflake account. No licenses are required.

    You are responsible for the cost of the AWS services and any third-party licenses used while running this Quick Start reference deployment. There is no additional cost for using the Quick Start.

    The AWS CloudFormation templates for this Quick Start include configuration parameters that you can customize. Some of these settings, such as instance type, affect the cost of deployment. For cost estimates, refer to the pricing pages for each AWS service you use. Prices are subject to change.

    Tip: After you deploy the Quick Start, create AWS Cost and Usage Reports to track costs associated with the Quick Start. These reports deliver billing metrics to an Amazon Simple Storage Service (Amazon S3) bucket in your account. They provide cost estimates based on usage throughout each month and aggregate the data at the end of the month. For more information about the report, refer to  What are AWS Cost and Usage Reports?