Quick Start

Beginner

This guide will help you set up and start using the Datamint Python API for your medical imaging projects.

Installation

Datamint requires Python 3.10+ and a Datamint account with an API key.

pip install -U datamint

We recommend a dedicated virtualenv to avoid conflicting with your system packages:

python3 -m venv datamint-env
source datamint-env/bin/activate  # Windows: datamint-env\Scripts\activate.bat
pip install -U datamint

Verify your installation

python -c "import datamint; print(datamint.__version__)"

Setup API Key

Obtaining an API key

Before using the Datamint API, you need to configure your API key. If you have the necessary permissions, you can obtain one from the Datamint platform:

In the left sidebar, select Teams.
Click Edit on your user profile.

Click Generate API key to create a new API key.

Note

If you don’t have the necessary permissions, ask your administrator.

Configuring your API key

Once you have your API key, choose one of the following options:

Option 1: Using the CLI tool (recommended)

datamint config --api-key YOUR_API_KEY

Option 2: Setting an environment variable

export DATAMINT_API_KEY="your_api_key"

Option 3: Programmatically in Python

from datamint import Api

api = Api(api_key="your_api_key")

Scaffold your first project

datamint init generates a ready-to-run set of numbered scripts tailored to your task (detection, segmentation, or classification):

datamint init

It asks for a project name and task type, then writes six scripts into a new directory (upload data, explore, build a dataset, train, evaluate, and deploy), so you can follow them in order without writing boilerplate.

Don’t have your own data yet? datamint init can populate the project with a small public example dataset instead — see Command-line tools for details, or run datamint example --help directly.

Your first API call

Once installed and configured, verify everything works end-to-end:

from datamint import Api

api = Api()
for project in api.projects.get_all():
    print(project.name)

Tip

Want to see full end-to-end examples? Browse our tutorial notebooks — they cover real datasets, training workflows, and deployment from scratch.

Next Steps

Master the command-line interface: Command-line tools
Check out our Python API documentation: Client Python API
Our PyTorch, Lightning and MLflow integration: PyTorch & Lightning Integration
Use the built-in trainers and custom model integration patterns: Training your Model