VMind Cloud Documentation
VMind Cloud
VMind Cloud is a Python programmatic interface to the VMind Cloud VPU Training Platform. This client library allows you to train AI models on VMind Cloud virtual processing units (VPUs) at groundbreaking speeds from your own infrastructure, with a few lines of code.
import vmind as vm
vm.train(model, training_data)
VMind Cloud is in private beta and requires registration. To get started, follow the steps below.
Getting started
To use VMind Cloud, you first need to have a VMind Account associated to your company email address. This allows you to access VMind support resources and obtain your client credentials.

To request a VMind Account, reach out to your account manager at support@vmindai.com.
Installing
VMind Cloud Stable (0.2.9) is compatible with Python 3.7 or above and Linux or macOS 10.15 (Catalina) or above operating systems. VMind Cloud is currently not supported on Python 2.7 or below, or on Windows.

To install VMind Cloud, we recommend using the Anaconda package manager, to ensure all dependencies are installed.
Anaconda
To install VMind Cloud via Anaconda, use the following conda command:
conda install vmind
Pip
To install VMind Cloud via Pip for Python 3.7 or above, use the following command:
pip3 install vmind
Setting up VPC peering
To access VMind Cloud securely from your infrastructure, you need to set up a VPC peering connection between your network and your dedicated VMind Cloud VPU managed service.

To ensure an optimal developer experience, only Google Cloud networks colocated in us-central1 (Iowa) are supported.
Google Cloud
To set up a VPC peering connection between your Google Cloud VPC network and your dedicated VMind Cloud VPU endpoint (10.8.0.100), use the following gcloud command:
gcloud aurora-
vm.train(model, training_data)
To complete the VPC peering, you also need to provide VMind with your Google Cloud project identifier, and the name of your VPC network. Fill out the form at .
To verify VMind Cloud installed successfully, run the following Python code:
import vmind as vm

vm.train(
Authentication
To use VMind Cloud you need to obtain OAuth 2,0 client credentials.


Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License.

This means you are free to use the content of this page, and in addition you are free to use the computer source code that appears in the content of this page (such as in examples) in the code of your own projects, as long as you provide proper attribution to VMind to the best of the ability of the medium in which you are producing the work under the terms of the Creative Commons Attribution license. The complete requirements for attribution can be found in section 3 of the Creative Commons legal code.

This license does not include VMind's trademarks and other brand features, nor any images, audio, slide decks or video material, or links to content on a different webpage, unless specifically noted.

Portions of this page and notice are modifications based on work created and shared by Google and used according to the terms described in the Creative Commons Attribution 4.0 License.

Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2022-08-03 UTC.
To install VMind Cloud via Pip for Python 3.7 or above, use the following command:
Installing VMind Cloud
pip3 install vmind
pip3 install vmind
Pip
Providing your client credentials

VMind API Docs