Overview

The Building RAG Systems with Open Models course is designed for developers, engineers, and technical product builders who are new to Generative AI but already have intermediate machine learning knowledge, basic Python proficiency, and familiarity with development environments such as VS Code, and who want to engineer, customize, and deploy open generative AI solutions while avoiding vendor lock-in. The course provides learners with the skills to design and implement retrieval-augmented generation (RAG) applications for real-world use cases. Learners start by exploring the fundamentals of RAG architecture, breaking down key components such as retrievers, rankers, generators, and orchestration layers, while learning design patterns for tasks like question answering, summarization, and knowledge synthesis. They then dive into embeddings and vector databases, comparing FAISS, ChromaDB, Milvus, and Pinecone, and applying indexing and chunking strategies to improve retrieval efficiency and semantic relevance. The final module brings all elements together to build production-ready RAG pipelines using LangChain and open LLMs, incorporating advanced retrieval methods, hallucination mitigation, and evaluation frameworks for accuracy and reliability. By the end, learners will have built a functional RAG application with configurable components, optimized for performance and equipped with robust evaluation metrics.

Syllabus

RAG Architecture and Design Patterns

Learn the fundamentals of Retrieval-Augmented Generation (RAG) and why it’s critical for reducing hallucinations and improving accuracy. You’ll break down RAG’s core components, retrievers, rankers, generators, and orchestration layers, and apply design patterns for use cases like Q&A, summarization, and knowledge synthesis. You’ll also explore advanced variations such as hierarchical retrieval and hybrid search, giving you practical strategies to match RAG designs to real-world needs.

Choosing Embeddings and Vector Databases

Evaluate embedding models and vector databases to understand how they impact retrieval quality and system performance. You’ll compare embedding options by dimensionality and domain fit, and explore database choices such as Facebook AI Similarity Search (FAISS), ChromaDB, Milvus, and Pinecone. You’ll also analyze indexing strategies, chunking methods, and update workflows—skills that help you make informed decisions when building retrieval systems for different environments.

Applying Embeddings and Databases in RAG Pipelines

You’ll put theory into practice by integrating embeddings and vector databases into working RAG pipelines. You’ll test indexing strategies, experiment with chunking, and observe how different configurations affect retrieval accuracy and efficiency. You’ll also practice maintaining and updating vector indices, building the skills to manage RAG systems that remain reliable as datasets grow and change.

Implementing Production RAG Pipelines

Assemble full RAG pipelines using frameworks like LangChain and open Large Language Models (LLMs). You’ll implement advanced retrieval strategies such as hybrid search, re-ranking, and query expansion, and evaluate pipelines with metrics that track accuracy, latency, and reliability. You’ll also practice handling real-world challenges, such as hallucination mitigation and citation tracking, ensuring your systems are not just demos, but production-ready solutions.