News: First Ever Pay-As-You-Go AI Management Platform Launches on Google Cloud.


Are you a passionate Python Data Scientist looking for the RIGHT way to build production-ready and fully monitored AI models using your real-world business data?

Grab your drink and Enjoy this blog post series dedicated to showcasing’s AI management platform and its Python SDK.  For this exercise we will focus on forecasting electricity consumption 🥳!

At the end of this journey A project of electricity forecast powered by deployed and fully monitored models will be added to your realized projects list!

Note: If you are a data scientist more comfortable with R, no worries we’ve got you covered in another blog post series available on our website😇! For Python data scientists, because of iterative development of the product, Python functions used in this series are designed to work with ’s versions going from 11.3.1 to 11.3.4. Solution: Experiment, Deploy, Monitor is a complete AI management platform meant to help you build, deploy and monitor efficient AI models without any hassle.

The whole goal of the offering is to provide you with an efficient and well-prepared framework that takes away all the storage, analysis, modeling, deployment and monitoring complexity. is user-friendly and offers an online web version with an intuitive UI which makes it easy to start taking advantage of all the features and the power of the platform. Moreover, most tasks done within the UI can be achieved by coding within our SDKs which may be convenient for the most advanced users.

What Are We Doing Today?

For today’s first blog post, we’ll start by setting up the Python SDK in order to enjoy interacting with APIs directly from a python environment.

First things first, start by heading over to this link and create a free account. You’ll need it later!

Step1. Pre-requisites:

The Python SDK has some dependencies that need to be installed prior to installing the SDK.

Before Starting: Free Trial Account Creation

As of today, these requirements can be found here [Up to date dependencies]. They can be installed with a simple pip install within your Python environment.

Step2. Get the package:

This step can be achieved by three methods:

  1. Using’s notebooks: It is actually the easiest way to use the package without worrying about the package installation. The only action to take is to go into your instance and launch a python notebook.

Account Created: Launch & Start Using Python Notebooks 🚀

  1. Using in your own environment:

    1. You can get the latest version from’s repository, available on this [Link] and follow simply the instructions mentioned in the readme or simply type in your favourite console:
git clone
cd prevision-python
python install


      Please note that:

  • Git should be installed on your computer / server
  • A working internet connection is needed to retrieve sources
  • The current version number is 11.3.1, but that will change over time


    1. You can simply type pip install previsionio and run the command.


Once the notebook is run (for method1) or the package is installed(for both choices of method 2), you can import the library and print the version number to confirm it was installed successfully. By default, the latest version (11.3.1):

In [1]: import previsionio as pio
In [2]: pio.__version__
Out[2]: 'v11.3.1'

Step 3.  Set Up your client’s SDK client uses a specific master token to authenticate with the instance’s server and allows you to perform various requests. To get your master token, log in the online interface of your instance, navigate to the admin page and copy the token.

Access Your Admin Page

Once done, don’t forget to either set the token and the instance name as environment variables by specifying PREVISION_URL and PREVISION_MASTER_TOKEN ,or at the beginning of your script:

import previsionio as pio

# The client is initialized with your master token and the url of the server
# (or local installation, if applicable)
url = "https://<your instance>"
token = "<your token>"
pio.client.init_client(url, token)

What’s coming next?

Now that everything is installed and connected, let the fun begin by sending some data from your Python environment to the’ platform  🧐.

Zina Rezgui

About the author

Zina Rezgui

Data Scientist