> This page is for Structured Data Models Client.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/sdgm/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/sdgm/_mcp/server.

# Notebooks

> Follow an example Kumo Relational workflow in a notebook

Download this quickstart notebook to learn how Kumo Relational turns connected business tables into predictions without training a task-specific model.
The example uses four tables from Microsoft's AdventureWorks sample database.

In the notebook, you will:

* Install and configure `structured-data-models-client`.
* Connect to a deployed Kumo Relational NVIDIA NIM inference service.
* Load and prepare the sample data as pandas DataFrames.
* Build and inspect a schema, which maps the tables and their key-based relationships.
* Submit prediction requests for several use cases.

Before you begin, you need a deployed Kumo Relational NIM endpoint and the AdventureWorks data files identified in the notebook.

Download the Kumo Relational quickstart notebook

Before running the Snowflake notebook, follow the
[Kumo Relational NIM Snowflake deployment guide](/sdgm/kumo-relational/deployment/snowflake)
to deploy the inference service in Snowflake.

Kumo Relational quickstart snowflake notebook