Set Up Appian AI for Appian on Kubernetes

Overview

Appian AI features are available for self-managed environments using Appian on Kubernetes. In order to use these features, system administrators need to set up and configure these services to work with Appian on Kubernetes.

During setup, we guide you through the process of creating and configuring Appian on Kubernetes to be able to use AI features. To do this, customers must use Amazon Web Services (AWS) infrastructure.

Features included

After you successfully complete setup, your environment has access to the following AI features:

• AI Copilot for data fabric
• AI Copilot for reports
• AI skills, including:
  • Advanced IDP Tools
  • Document classification
  • Document extraction
  • Email classification
  • Generative AI skills
• Composer
• Create sample data for record types
• Data fabric chatbot component
• Documents Chat
• Enterprise Copilot
• Generate interface from PDF
• Generate test cases for expression rules
• Records chat component
• Suggested insight summaries
• Suggested KPIs
• Suggested views

Software and experience requirements

• Appian: Customers must be using Appian on Kubernetes to gain access to AI features in a self-managed Appian environment. Further, the Appian platform version must be 25.3 or higher.
• Appian Operator: Most recently released version.
• Kubernetes: v1.29 or higher.
• AWS infrastructure, including Amazon EKS cluster
• Experience with KEDA
• Experience with Knative infrastructure
• Experience with Helm

Get started

To get started using Appian AI services on Kubernetes, install Appian on Kubernetes if you haven't already.

Visit Appian Forum to access key installation resources, including documentation on how to set up AI services for Appian on Kubernetes using AWS infrastructure. The guide includes:

• comprehensive software, infrastructure, and tool prerequisites.
• important disclaimers and best practices. The sample Terraform files are for demonstration and customers are responsible for their environments, including data backups.
• definitions of core concepts, such as IAM Roles for Service Accounts (IRSA) and chained role assumption.
• guidance for configuring kubectl, setting up resources with example Terraform files, configuring IAM permissions for pods, and deploying Helm charts.
• a section for testing the connections to ensure users will have access to multiple AI features.

Feedback