Summary  
This chapter covers the programming concept of a lifecycle management tool that tracks experiments, packages reproducible code, standardizes model storage, and versions models.

General domain of usage  
Machine learning operations (MLOps)

MLflow is one of the most popular **open-source tools for managing the machine learning lifecycle**.
It helps track experiments, manage models, and streamline workflows from training to deployment.
MLflow provides a unified interface for **experiment tracking**, **model packaging**, and **model registry**, making it an essential tool in modern MLOps.

## **Key Components of MLflow**

1. **MLflow Tracking** — records parameters, metrics, and artifacts (like models or plots) for each run;
2. **MLflow Projects** — allows you to package code in a reproducible format;
3. **MLflow Models** — standardizes model storage and deployment across different frameworks;
4. **MLflow Registry** — serves as a central repository to version and manage models.

**MLflow** — an open-source platform for managing the end-to-end machine learning lifecycle, including tracking, packaging, and deploying models.

Definition

You can use MLflow locally or with cloud-based backends.
It integrates easily with frameworks like **scikit-learn**, **TensorFlow**, **PyTorch**, and **XGBoost** — all without modifying existing training code.


Note

Which of the following is *not* a core MLflow component?

Learn how to deploy machine learning models using Docker, FastAPI, and MLflow. This focused course covers creating API endpoints for inference, containerizing models, and managing the model lifecycle for production-ready solutions.

Introduction to MLflow

Key Components of MLflow