Orador ConfirmadoRami Krispin
Rami Krispin is a data science and engineering manager who mainly focuses on time series analysis, forecasting, and MLOps applications. He is the author of Hands-On Time Series Analysis with R and is currently working on my next book, Applied Time Series Analysis and Forecasting, which focuses on forecasting at scale.
He is passionate about open source, putting stuff into production, working with data and APIs, machine learning, Bayesian statistics, data visualization, and GIS data.
From Prototype to Production: Deploying AI Agents with Docker
AI applications often work perfectly on a developer’s machine—until differences in dependencies, operating systems, hardware, and infrastructure cause them to fail elsewhere. In this 45-minute workshop, attendees will use a RAG application as a practical example for learning how Docker creates reproducible AI development and deployment workflows. We will trace application requirements through Dockerfiles, images, and running containers before exploring how to divide ingestion, vector storage, and query processing into clearly defined services. Attendees will learn how Docker Compose connects those services, how health checks and integration tests validate the complete workflow, and what separates a working container image from a production-ready artifact. The workshop concludes with a practical readiness checklist covering image size, security, portability, distribution, resource limits, and operability. Designed for AI developers familiar with Python and common AI components. Prior Docker experience is not required.