Overview of Cortex APIs

Cortex’s ability to refresh your Machine Learning Pipelines over time unlocks various automated initiatives for your business. When your predictions are always up-to-date, you can rely on them for dynamic decision-making rather than being limited to a snapshot analysis at one point in time. At Vidora, we’ve seen how powerful these automated ML use cases can be. That’s why we built a robust set of APIs to help deploy your predictions however your business needs.

Together, Cortex’s APIs allow you to create a closed-loop system of intelligent automation which ingests raw behavioral data in real time and returns updated predictions in 10-20ms. This guide provides a brief overview of the available APIs.

Behavioral API

The Behavioral API provides a scalable framework for sending event data to Vidora’s servers in real-time. Events are the required building blocks for any Machine Learning Pipeline in Cortex, and the Behavioral API allows you to stream these events to Cortex as they occur. The more data submitted to the Behavioral API, the wider the set of predictions you can make and the more accurate your predictions will be.

Please visit the Behavioral API documentation for more information on how to use the API.

JavaScript SDK

For organizations that would prefer to send event data from the client side, the JavaScript SDK provides an easy way to do so. Once loaded, the JavaScript SDK can be embedded in your UI in order to send events directly to Cortex without first being routed to your servers. The JavaScript SDK is fully compatible with popular tag managers such as Google Tag Manager and Tealium.

Please visit the JavaScript SDK documentation for more information on how to use the API.

Pipelines API

The Pipelines API provides programmatic access to any Machine Learning Pipeline in your Cortex account. The API allows you to build automated workflows for managing, updating, and deploying your Pipelines, facilitating smoother integrations between Cortex and your business.

Please visit the Pipelines API documentation for more information on how to use the API.

Predictions API

The Predictions API provides low-latency access to predictions made by any pipeline in your Cortex account. The Predictions API returns up-to-date predictions directly to your digital products and business tools, enabling you to build automated mechanisms which act on these predictions in intelligent ways.

A typical use case for the Predictions API requires predictions to be returned on-demand and in real-time. Please visit the Predictions API documentation for more information on how to use the API.

Personalization API

The Personalization API provides a number of ways to personalize each user’s experience, keeping them engaged with the content or items they love most. The Personalization API returns personalized recommendations which update in real-time, and comes equipped with robust systems for filtering results by metadata such as category, type, and others.

Please visit the Personalization API documentation for more information on how to use the API.

Items API

The Items API allows our partners to manage which items are recommended to users through the Personalization API. The Items API can be used to fetch or update properties of a given item, allowing you to disable items from appearing in recommendations with the click of a button in your Content Management System. If an item is updated to ‘disabled’, it will no longer be served by the Personalization API.

Please visit the Item API documentation for more information on how to use the API.

Related Links

Still have questions? Reach out to support@vidora.com for more info!

Table of Contents