OmniAI VPC 🔐

Private Cloud & On-Prem deployment available on Enterprise Tier

OmniAI Dedicated is a fully isolated, single-tenant SaaS solution that is:

• Hosted and managed by OmniAI.

• Deployed on AWS in a cloud region of your choice. See available AWS regions.

OmniAI Dedicated removes the overhead of platform management while allowing for fully isolated deployments. Each OmniAI Dedicated instance is highly available with disaster recovery and deployed into the cloud region of your choice.

The OmniAI team fully manages the maintenance and operations of each isolated instance, so customers can access our latest product improvements while meeting the most complex compliance standards. Administers from your organization are granted IAM roles to monitor the application while OmniAI manages the underlying infrastructure.

Available Features

Isolation

As a single-tenant solution, OmniAI Dedicated provides infrastructure-level isolation of your Omni environment. Your environment is managed within into a separate AWS account from other tenants. This AWS account contains all of the underlying infrastructure necessary to host the OmniAI application and your data stays within the account boundary.

Access controls

OmniAI maintains strict access controls to AWS accounts, limiting access solely to designated OmniAI team members and the customer's appointed administrators. This approach ensures that only authorized personnel can manage and interact with the account, safeguarding against unauthorized access. All other access is firmly restricted, upholding the highest standards of security and privacy for our customers.

Audit and observability

OmniAI Dedicated provides access to audit and system logs generated by the application.

Continuous Upgrades

OmniAI performs monthly upgrades to your instance with the latest features or security releases during your preferred maintenance window tracking one release behind the latest OmniAI release.

For example, if the latest version of OmniAI available is 1.8.4, OmniAI Dedicated runs on 1.8.5.

Available AWS regions

The following is a list of AWS regions verified for use in OmniAI Dedicated. Regions must support io2 volumes and meet other requirements. If there is a region you are interested in that is not on this list, reach out through to inquire about its availability.

This list will be updated from time to time as additional regions are verified.

• Asia Pacific (Singapore)

• Asia Pacific (Sydney)

• Europe (Frankfurt)

• Europe (Ireland)

• Europe (London)

• US East (Ohio)

• US East (N. Virginia)

• US West (N. California)

• US West (Oregon)

---

Private Cloud Deployment

Building and deploying containers

This documentation outlines the steps for deploying OmniAI within a private cloud environment, ensuring secure and efficient operation.

Packages

The Omni Platform is composed of the following packages:

• Server: Serves as the API layer, connecting the client, models, and the PostgreSQL database.

• App: The front-end interface for OmniAI

• Postgres: Omni relies on a PostgreSQL database for model configuration.

Prerequisites

• Access to a private Docker registry (e.g. AWS ECR).

• Docker and Docker Compose installed on the deployment environment.

• Credentials for accessing the private Docker registry.