Kumo lets data scientists and engineers build AI models for predictions and embeddings directly from relational data, without the time-consuming pain of feature engineering. Kumo offers flexibility in how you interact with its advanced machine learning platform, providing both an intuitive web console for seamless, user-friendly access and a fully composable Python SDK for integration in your production workflows.

​
Workflow

1

Connect your data

Set up a connection with your cloud data platform to grant Kumo access to your data. Or, upload files directly.
2

Create tables and graph schema

Select training tables and connect them to create a graphical schema.
3

Train a model

Define your predictive task using Kumo’s simple and intuitive Predictive Query Language, and let Kumo automatically train and optimize the model for your data.
4

Run models

Run batch jobs to get embeddings or predictions on the latest data.

​
Resources

Quick Start

SDK Reference

Predictive Query Reference

Snowflake Native App

​