Developing and Deploying RAG Systems in Python

You will learn how to design, implement, evaluate and deploy a production-ready RAG (Retrieval-Augmented Generation) system, including ingestion pipelines, embeddings and vector databases, retrieval strategies, LLM orchestration, evaluation, observability, security, deployment and scaling. The course is practical in focus: each day includes hands-on workshops and the step-by-step development of a single production project.