AzureAI (coming soon)

The foundational models for time series by Nixtla can be deployed on
your Azure subscription. This page explains how to easily get started
with TimeGEN deployed as an Azure AI endpoint. If you use the
nixtlats library, it should be a drop-in replacement where you only
need to change the client parameters (endpoint URL, API key, model
name).

Deploying TimeGEN (coming soon)

Using the model

Once your model is deployed and provided that you have the relevant permissions, consuming it will basically be the same process as for a Nixtla endpoint. To run the examples below, you will need to define the following environment variables:

  • AZURE_AI_NIXTLA_BASE_URL is your api URL, should be of the form
    https://your-endpoint.inference.ai.azure.com/.
  • AZURE_AI_NIXTLA_API_KEY is your authentication key.

How to use

Just import the library, set your credentials, and start forecasting in two lines of code!


pip install nixtlats


import os
from nixtlats import NixtlaClient

base_url = os.environ["AZURE_AI_NIXTLA_BASE_URL"]
api_key = os.environ["AZURE_AI_NIXTLA_API_KEY"]
model = "azureai"

nixtla_client = NixtlaClient(api_key=api_key, base_url=base_url)
nixtla_client.forecast(
    ...,
    model=model,
)