Building MLOps POCs and Sandbox Environments Using k3s and Argo

This talk discusses the challenges corporations face when implementing MLOps workflows and how open source technologies like k3s and Argo can help reduce implementation time and infrastructure costs. The speaker presents a demo showing a basic MLOps workflow implementation using k3s and Argo.

• POCs and sandbox environments are used to evaluate and test different technologies and solutions
• k3s is a lightweight Kubernetes that can be used for POCs
• Apache Spark and Scikit Learn are commonly used for ETL processes and ML model generation
• Argo can replace or complement pipelines designed with Apache Airflow
• Edge computing allows for processing data closer to the source
• Envelopes refer to the automation of model generation and management
• The demo shows a basic MLOps workflow implementation using k3s and Argo

The speaker mentions the importance of POCs and sandbox environments for testing different technologies and solutions. He also highlights the advantages of using k3s as a lightweight Kubernetes for POCs and how Argo can replace or complement pipelines designed with Apache Airflow. The demo shows how k3s and Argo interact with each other to deploy ML models ready to be used.

This talk presents the challenges that corporations have when they evaluate technologies for data pipelines automation or for MLOps workflows, this includes processes like ETL, ML model generation and ML model deployments. At the same time, this talk shows how open source technologies can help to reduce implementation time and infrastructure costs for MLOps systems. The talk also presents the advantages of using k3s as a lightweight Kubernetes for POCs, the lessons learned at work when trying to implement MLOps using Scikit Learn for ML Models and Apache Spark for ETL processes. As a complement for k3s the talk describes how Argo can replace or complement pipelines designed with Apache Airflow and how these types of technologies prepare companies for Edge Computing. At the end of the session the speaker presents a short demo showing a basic MLOps workflow implementation using k3s and Argo and showing how k3s and Argo interact with each other to deploy ML models ready to be used.