Building Retrieval Augmented Generation (RAG)

This hands-on course introduces students to the design and development of Retrieval-Augmented Generation (RAG) systems — powerful architectures that combine large language models (LLMs) with external knowledge sources to improve accuracy, reduce hallucinations, and enhance domain-specific reasoning. Students progress from foundational understanding to real-world implementation, gaining experience with the latest tools and frameworks in the RAG ecosystem. Through guided labs and projects, learners will build complete, production-ready RAG pipelines — from data ingestion and embedding optimization to retrieval tuning, evaluation, and deployment on cloud platforms. The course emphasizes both engineering depth and practical evaluation, ensuring students understand the trade-offs between model quality, latency, and cost. By the end of the course, students will have developed and deployed a portfolio-ready RAG application with end-to-end documentation, demonstrating their ability to integrate vector databases, optimize retrieval strategies, implement automated evaluation using frameworks like RAGAS and TruLens, and containerize applications for scalable production environments.