Model Deployment in a MLOps Workflow: The Various Ways

In MLOps pipelines, deployment is the pivotal phase where machine learning models transform from development artifacts into production-ready assets. The MLOps Zoomcamp Module 4: Deployment outlines three primary deployment strategies:

1. Web-services: Flask + Docker 🐍

  • Flask app loads model artifacts from local disk or cloud storage

  • Containerization ensures identical environments across dev/prod

  • Key Course Tool: Docker for dependency isolation


2. Web-services: MLflow Model Registry 📦

  • Fetch models using mlflow.pyfunc.load_model() with registry URIs (e.g., models:/churn-model/Production)

  • No hardcoded paths – models update without redeploying app

  • Note: MLflow's built-in REST server (mlflow models serve) is an alternative to Flask


3. Streaming: AWS Kinesis + Lambda ⚡

  • Lambda downloads model from S3 (not directly from MLflow registry)

  • Max execution time: 15 minutes (critical for large models)

  • Course Pattern: Kinesis → Lambda → S3/DynamoDB


4. Batch Scoring with Prefect ⏱️

When real-time isn't required: Batch scoring shines for periodic, high-volume predictions. Prefect orchestrates these workflows like a conductor – managing execution timing, failure recovery, and progress tracking while your Python code handles the heavy lifting:

  1. Model Loading
    Retrieve production-ready models directly from cloud storage (S3 in course examples)

  2. Data Chunk Processing
    Efficiently score large datasets in parallelizable batches

  3. Result Export
    Save predictions to databases, data lakes, or BI systems

The Prefect Advantage:

  • 🔄 Zero redeploys: Update scoring logic without infrastructure changes

  • ⚡ Elastic scaling: Handles terabyte-scale datasets on your infrastructure

  • 📅 Intelligent scheduling: Daily/weekly runs with built-in retries

Comments

Post a Comment

Popular posts from this blog

My midterm project at MLZoomcamp led by Alexey Grigorov for DataTalksClub

 Predicting Patient No-Shows: A Data-Driven Approach Hospital no-shows significantly disrupt healthcare systems, wasting resources and delaying care for those in need. My midterm project for the MLZoomcamp , led by Alexey Grigorev and hosted by DataTalksClub, tackles this challenge using machine learning to predict no-show probabilities for appointments in Brazilian hospitals. Here's how I approached the problem: The Challenge The dataset, sourced from Kaggle, includes over 110,000 appointments and diverse features such as patient demographics, appointment details, and medical history. However, achieving reliable predictions is complex due to: Imbalanced Data : About 80% of appointments were attended, while 20% were no-shows. Dependence on Feature Engineering : Key predictors like patient history (previous/missed appointments) were engineered from the raw data. Bias Mitigation : Socioeconomic factors, such as neighborhood, required careful handling to ensure fairness. The Solution ...
Read more

Starting my Data Engineering journey with a foundational insight on Docker, Terraform and Google Cloud Platform

 The Data Engineering Zoomcamp 2025, led by Alexey Grigorev at DataTalksClub, offers an in-depth exploration of modern data engineering practices. The first module, "Containerization and Infrastructure as Code," serves as a foundational entry point into the course, equipping participants with essential skills for building and managing scalable data systems. Module 1: Containerization and Infrastructure as Code This module introduces participants to two pivotal concepts in data engineering: containerization and infrastructure as code (IaC). By leveraging these technologies, data engineers can create consistent, reproducible environments and automate the provisioning of infrastructure, leading to more efficient and reliable data pipelines. Key Topics Covered: Introduction to Google Cloud Platform (GCP): Participants are introduced to GCP, a leading cloud service provider offering a suite of tools and services for building and managing data systems. The course provides guidance ...
Read more

Logistic Regression: A walkthrough by Alexey Grigorev

Logistic Regression is one of the foundational algorithms for classification tasks, and Alexey Grigorev at DataTalks.Club provides an insightful approach to understanding it in his courses, such as the Machine Learning Zoomcamp. Alexey Grigorev provides a clear and practical explanation of Logistic Regression, helping learners understand its application and limitations in real-world scenarios. In his teaching, Alexey emphasizes the simplicity and interpretability of Logistic Regression. The model predicts the probability that a given input belongs to a particular class, which makes it especially useful in binary classification problems. For example, it’s widely applied in fields like customer churn prediction, fraud detection, and medical diagnoses. Logistic Regression works by modeling the relationship between input features and the probability of a binary outcome using a sigmoid function. This makes the predictions constrained between 0 and 1. Alexey often stresses the importance of ...
Read more