This document provides an overview of Vertex AI on
Google Distributed Cloud (GDC) air-gapped, including its available features and key
benefits. It helps you understand how Vertex AI machine learning
capabilities can enhance your air-gapped applications.

This document is for application developers within the application operator
group who are looking to incorporate AI features into their air-gapped
applications and workflows. For more information, see
[Audiences for GDC air-gapped
documentation](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/resources/audiences).

## Vertex AI for on-premises environments

Vertex AI on GDC brings a machine
learning platform and generative AI models to your air-gapped on-premises
environments. Vertex AI on GDC supports
organizations with strict data sovereignty, security, and privacy requirements.
Vertex AI services let you innovate with AI features while
maintaining control in the same air-gapped infrastructure.

## Key features

Vertex AI on GDC offers the following
features:

- **Air-gapped deployment**: run Vertex AI services within your data center to help meet your data sovereignty and compliance requirements.
- **Familiar Vertex AI experience**: use familiar tools, APIs, and models from Vertex AI on Google Cloud to simplify development and management.
- **Prebuilt models and algorithms**: use a range of pretrained models for common machine learning and AI tasks.
- **Custom model training**: develop and train custom AI and machine learning models using your own data in Vertex AI Workbench notebooks.
- **Machine learning operations (MLOps) capabilities**: manage your machine learning workflows with tools for model deployment and monitoring.

## Available services

Vertex AI on GDC offers the following
services:

- [**Generative AI**](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/genai/genai-overview): build applications that use foundational generative AI models to generate content and text embeddings.
- [**Online Prediction**](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-online-predictions) (*Preview*): deploy and make requests to your prediction models.
- [**Optical Character Recognition (OCR)**](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-ocr): extract text from images and documents.
- [**Speech-to-Text**](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-stt): convert spoken language into written text.
- [**Vertex AI Translation**](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-translation): translate text between multiple languages.
- [**Vertex AI Workbench**](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-workbench-intro): create a managed JupyterLab notebook environment for machine learning development.

## Benefits

Vertex AI on GDC provides the following
benefits:

- **Consistent development experience**: use familiar APIs, models, and workflows from Vertex AI on Google Cloud for application development and management.
- **Data privacy and residency**: maintain control over your data within your air-gapped environment to help meet your regulatory requirements.
- **Operational agility**: develop and deploy AI and machine learning models directly in your air-gapped infrastructure.
- **Faster time to value**: use pretrained models for common machine learning tasks, or train custom models using your own datasets.
- **Integrated MLOps**: deploy, monitor, and manage models within your air-gapped environment.

## Get started

To get started with Vertex AI on GDC, do
the following:

1. Learn about [essential roles and permissions for available services](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-ao-permissions).
2. [Set up a project](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-set-up-project) for your AI and machine learning workflows.
3. Enable the [Vertex AI pretrained APIs](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-enable-pre-trained-apis).
4. View [service status and endpoints](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-api-status).
5. Install the [Vertex AI client libraries](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-install-libraries).
6. [Authenticate API requests](https://docs.cloud.google.com/distributed-cloud/hosted/docs/1.16/gdcag/application/ao-user/vertex-ai-api-auth).

After you complete these steps, you can start building and deploying your AI and
machine learning models.