How Do I Set up Appian AI?

Both Appian AI and non-Appian AI customers are able to use the out-of-the-box AI services as long as they have a valid Google Cloud set up and meet the minimum system requirements. To use certain AI functionality, you will need to download and deploy additional plug-ins before you can use the Appian design objects in your application.

Review the sections below to ensure you are ready to begin building AI into your application.

System requirements

  • To use the Google Cloud AI connected systems and connected system plug-ins, Appian must be running version 19.2 or higher.
  • To use IDP, Appian must be running version 20.1 or higher.
  • A supported web browser.
  • If your Appian installation is on a dedicated VPN, the VPN must allow Google's APIs to be accessible from the application server.

Google Cloud setup

Since Appian AI leverages the power of Google Cloud AI, you must have a Google Cloud account, service account, and service account key to connect to Google Cloud AI services.

Appian AI Customers

If you have opted in to being an Appian AI customer, your Google Cloud setup is already handled for you.

Appian will configure a Google Cloud Platform project on your behalf. Since the project uses automatic provisioning, your service account credentials are generated automatically and no other users see or have access to the credentials during the process. For more details on Google's data security and privacy practices, see Google Cloud Security.

Once the project is set up, the service account credentials, bucket names, and region information will be sent to your Appian technical contact through the License Management site on Appian Community. To get started, contact your Appian technical contact administrator to obtain your credentials.

Your technical contact administrator is listed on the Accounts page in Community, under Administrators. Note that you must be registered with your company on Community to access this site.

Non-Appian AI Customers

If you've purchased Google Cloud separately and already have an existing account, you don't need to create a new one to use Appian AI. You will, however, need to take a few additional configuration steps.

To use the Appian AI offering, you must do the following:

  1. As the Project Owner, log into the Google Cloud console and select an existing project or create a new project.
  2. Ensure that billing is enabled for your project.
  3. Enable the following APIs:
    • Cloud AutoML API
    • Google Cloud Storage JSON API
    • Cloud Document AI API
  4. Create Cloud Storage buckets that follow the bucket requirements to store the AutoML Natural Language files:
    • For us-central1:
    • Location type: Region
    • Location: us-central1
    • Storage class: Standard (sometimes displayed in the Cloud Storage browser as Regional) - For eu:
    • Location type: Multi-region
    • Location: eu
    • Storage class: Standard (sometimes displayed in the Cloud Storage browser as Multi-Regional)
  5. You may choose to have two buckets: one for the training documents and one for the prediction documents. Or, you can use the same storage bucket for both. If you use two buckets, then they must be in the same regional location.
  6. Create a Google Service Account in the Google Cloud Console with AutoML Admin and Storage Admin permissions.
  7. Create the service account key and save the file as a JSON document.

Deploy plug-ins

To use custom machine learning models or access a Google Cloud Storage bucket in your application, you'll need to deploy the associated connected system plug-ins:

To deploy the plug-ins for Appian Cloud installations:

  1. In your Appian environment, log in as a system administrator.
  2. Go to > Admin Console.
  3. On the left side of the console, click Plug-ins.
  4. Click DEPLOY NEW PLUG-INS.
  5. Search for and click the desired plug-in. Note that only cloud-approved plug-ins that are supported for your site's version of Appian will appear.
  6. Click DEPLOY.

To deploy plug-ins for self-managed installations, see Appian Suite Plug-Ins.

Open in Github

On This Page

FEEDBACK