Quickstart

This quickstart guide will help you get up and running with AutoGluon Assistant (MLZero) in just a few minutes.

Installation and Prerequisites

First, install AutoGluon Assistant:

pip install uv && uv pip install autogluon.assistant>=1.0

If you don't have conda installed, follow conda's official installation guide to install it.

MLZero uses AWS Bedrock by default. Configure your AWS credentials:

export AWS_DEFAULT_REGION="<your-region>"
export AWS_ACCESS_KEY_ID="<your-access-key>"
export AWS_SECRET_ACCESS_KEY="<your-secret-key>"

We also support Anthropic, OpenAI, and SageMaker. See our LLM Providers guide for details on configuring these providers.

Here's a simple example to get you started with our command line interface:

mlzero -i <input_data_folder> [-t <optional_user_instructions>] [--provider <bedrock|openai|anthropic|sagemaker>]

For more detailed options and interfaces, see our Interfaces guide.

Now that you've got the basics down, explore more advanced features:

LLM Providers: Learn how to use different AI providers (Bedrock, OpenAI, Anthropic, SageMaker)
Interfaces: Understand the different ways to interact with AutoGluon Assistant (CLI, Python API, WebUI, MCP)
Configuration: Master customizing AutoGluon Assistant for your specific needs

If you run into any issues: