Step 1: Launch the Deployment dashboard stack - Generative AI Application Builder on AWS

Step 1: Launch the Deployment dashboard stack

Follow the step-by-step instructions in this section to configure and deploy the solution into your account.

Time to deploy: Approximately 10 minutes

  1. Sign in to the AWS Management Console and select the button to launch the generative-ai-application-builder-on-aws.template CloudFormation template.

    Blue oval button with white text reading "Launch solution".

  2. The template launches in the US East (N. Virginia) Region by default. To launch the solution in a different AWS Region, use the Region selector in the console navigation bar.

    Note

    This solution uses Amazon Kendra and Amazon Bedrock, which are not currently available in all AWS Regions. If using these features, you must launch this solution in an AWS Region where these services are available. For the most current availability by Region, see the AWS Regional Services List.

  3. On the Create stack page, verify that the correct template URL is in the Amazon S3 URL text box and choose Next.

  4. On the Specify stack details page, assign a name to your solution stack. For information about naming character limitations, see IAM and STS Limits in the AWS Identity and Access Management User Guide.

  5. Under Parameters, review the parameters for this solution template and modify them as necessary. This solution uses the following default values.

    Parameter Default Description
    Admin User Email <Requires input> The email address of the admin user who will have access to the Deployment dashboard. An Amazon Cognito user will be created with permissions to deploy and manage use cases.

    VpcEnabled

    No

    Should the Deployment dashboard be deployed within a VPC

    CreateNewVpc

    No

    Only available, if VpcEnabled is Yes. If the value is Yes, the stack will create the VPC and deploy the solution within the created VPC.

    If VpcEnabled is Yes and CreateNewVpc is No, then you must provide an existing VPC configuration (ExistingVpcId, ExistingPrivateSubnetIds, ExistingSecurityGroupIds, VpcAzs).

    Note

    If you're using your own VPC, see Managing your own Amazon VPC.

    IPAMPoolId

    <Optional input>

    You can configure IPAM and provide the created id as input to assign the IP address range that the deployment of this stack should use. For details regarding IPAM, see How IPAM works.

    DeployUI

    Yes

    You have the option to deploy the Deployment dashboard without the web user interface (and the AWS resources required for the web deployment). In which case, the solution will deploy all infrastructure including REST API endpoints. This option is useful to integrate your own web interface with the Deployment dashboard APIs.

    ExistingVpcId

    <Optional input>

    Required only if you want to deploy the solution in an existing VPC that you have created.

    ExistingPrivateSubnetIds

    <Optional input>

    Required only if you want to deploy the solution in an existing VPC that you have created. The Lambda functions will be deployed in this subnet.

    ExistingSecurityGroupIds

    <Optional input>

    Required only if you want to deploy the solution in an existing VPC that you have created. Ensure that security groups have the permissions for an outbound TCP connection.

    VpcAzs

    <Optional input>

    Required only if you want to deploy the solution in an existing VPC that you have created.

  6. Choose Next.

  7. On the Configure stack options page, choose Next.

  8. On the Review and create page, review and confirm the settings. Select the box acknowledging that the template will create AWS Identity and Access Management (IAM) resources.

  9. Choose Submit to deploy the stack.

You can view the status of the stack in the AWS CloudFormation console in the Status column. You should receive a CREATE_COMPLETE status in approximately 10 minutes.