What you'll learn

Building effective retrieval systems requires making informed decisions about how to chunk documents, what indexing strategies to use, and how to improve result quality at scale. In this course, Context Indexing and Retrieval, you'll learn to design and implement production-ready retrieval pipelines for knowledge bases and RAG applications. First, you'll explore different chunking strategies: fixed-size, recursive, and semantic, and learn when to choose vector, lexical, or hybrid indexing approaches for your data and query patterns. Next, you'll discover how to improve retrieval quality using reranking, metadata filtering, query expansion, and fusion techniques like maximal marginal relevance and reciprocal rank fusion. Finally, you'll learn how to operationalize retrieval at scale by designing ingestion pipelines, monitoring retrieval drift, and balancing online versus batch indexing strategies. When you're finished with this course, you'll have the skills and knowledge needed to build robust, context-aware retrieval systems that scale with your data and maintain quality over time.