Dell Technologies has worked closely with Kore.ai to deliver Conversational AI through a jointly engineered and validated solution to help enterprises capitalize on the benefits of AI optimized natural language understanding. We have validated Kore.ai on Kubernetes with two of our validated designs:
The Validated Design for AI with VMware incorporates Dell Technologies infrastructure, VMware vSphere with Tanzu. This validated design is a virtualization platform that enables an enterprise to manage clusters of both on-demand Kubernetes containers alongside traditional virtual machines, providing complete life cycle management of those compute and storage resources. This validated design also includes support for NVIDIA GPUs and NVIDIA AI Enterprise. Kore.ai does not use GPUs as of publication of this document.
The Validated Design for Analytics—Data Lakehouse incorporates Symworld Cloud Native Platform for the Kubernetes layer. Symworld Cloud Native Storage provides the Kubernetes Storage Class by discovering disks attached to the PowerEdge servers. Applications that require Persistent Volumes use this Kubernetes Storage Class.
PowerEdge servers provide compute resources for the Kore.ai XO platform. PowerSwitches provide networking. Local storage in the PowerEdge servers, which is made available either through VMware vSAN or Symworld Cloud Native Storage, is sufficient to provide storage for the Kore.ai XO Platform.
In addition, add-on modules to the XO Platform such as Search Assist might require access and use of large quantities of data. In those cases, we recommend that you use Dell ECS for S3 compatibility or Dell PowerScale. While not validated explicitly as part of this solution with the chosen use cases, these and other extensions to the architecture may be considered to support a wider variety of use cases.
Note: Other Dell Validated Designs for container platforms, including Red Hat OpenShift, can be used with similar results. However, Dell Technologies has not validated these container platforms for Conversational AI as of the publication of this white paper.