teradatamodelops

What it is and what it does

Teradata ModelOps Client is a command-line tool and Python SDK for managing the full lifecycle of machine learning models on Teradata's Vantage platform. It bridges local development and remote model management by allowing data scientists to initialize projects, train and evaluate models locally before committing to version control, manage feature engineering tasks, and deploy model versions to production. The package integrates with git for repository management and provides OAuth-based authentication to Teradata ModelOps instances.

The CLI supports interactive and non-interactive workflows for common tasks: listing projects, models, and datasets; cloning project repositories; running model training and evaluation; managing connections and feature statistics; and diagnosing configuration issues. The SDK layer exposes the same capabilities programmatically, enabling automation and integration into larger data pipelines. It depends on standard libraries (requests, pyyaml, gitpython, cryptography) plus Teradata's own teradataml for database connectivity.

Use it for:

• Train and validate ML models locally before committing to a shared ModelOps project repository.
• Automate feature engineering workflows and compute feature statistics across datasets.
• Deploy trained model versions to Teradata Vantage for production inference.
• Clone and link local development repositories to remote ModelOps projects for team collaboration.
• Diagnose and troubleshoot ModelOps configuration and authentication issues via the doctor command.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Teradata ModelOps Client provides a CLI and SDK for managing machine learning model lifecycle—training, evaluation, deployment, and versioning—within Teradata's data platform.

Yes, if you are a Teradata Vantage user developing ML models within that ecosystem. The package is actively maintained, has no known vulnerabilities, and low install friction. However, the proprietary license restricts use to internal purposes tied to a Teradata database license, and Windows users must manually install OpenSSL. Not suitable for open-source or non-Teradata workflows.

Install

teradatamodelops on PyPI

pip install teradatamodelops

uv add teradatamodelops

poetry add teradatamodelops

Installing teradatamodelops

Before you install

Low install friction; pure Python wheel with no compiled dependencies. Actively maintained as of 56 days ago. Requires Python 3.10 or later.

License in practice

Proprietary license with export control restrictions. Use is limited to internal purposes facilitating Teradata Relational Database licensing. Redistribution, modification, and reverse engineering are prohibited without written consent.

Quickstart

pip install teradatamodelops

from teradatamodelops import Client

client = Client()
projects = client.list_projects()

On Windows, OpenSSL must be installed manually to authenticate with ModelOps instance. Requires Teradata Relational Database license and valid ModelOps credentials in ~/.tmo/config.yaml.

Verify before relying

• Whether SDK methods beyond list_projects are documented in the fact sheet or require external documentation review.
• Specific authentication flow and credential management details beyond config.yaml location.
• Performance characteristics and scalability limits for large model repositories or datasets.

Package facts

Evidence: teradatamodelops-7.3.4-py3-none-any.whl

Keywords: teradata, vantage, data science, devops, vantagecloud

Tags

More Utilities packages