Overview
Kumo Relational is a relational foundation model for predictive AI on structured, multi-table data. It generates predictions from relational context without requiring you to train a task-specific model first.
Kumo Relational learns from your data at query time. Describe a prediction task with Predictive Query Language (PQL), a lightweight SQL-like interface, and receive results as a pandas DataFrame through the Python SDK.
You access Kumo Relational through the NVIDIA Kumo Relational Client Python package (kumo-relational-client), which connects to a Kumo Relational instance running as an NVIDIA NIM.
What you can predict
Predict categories, Boolean outcomes, and numeric values.
Predict numeric values over a future time horizon.
Rank or recommend related entities.
Get Started
Install kumo-relational-client[relational] and connect to a Kumo Relational NIM.
Build a graph and run a prediction through the graph-bound client.
Explore end-to-end predictive workflows and datasets.
Look up the Python SDK, PQL, result schema, and NIM REST API.
