What you'll learn

Building reliable and scalable retrieval systems for LLM applications is complex. From ingesting diverse data sources to optimizing similarity search and hybrid querying, many developers struggle to design retrieval architectures that work effectively. In this course, Working with Data: Retrieval and Vector Stores in LangChain, you’ll gain the ability to build scalable retrieval systems for LLM applications. First, you’ll explore data ingestion, text splitting, embeddings, and vector stores that power semantic search. Next, you’ll discover how retrievers work, how to improve recall and precision, and how to evaluate and optimize retrieval performance. Finally, you’ll learn how to implement structured querying and hybrid retrieval workflows. When you’re finished with this course, you’ll have the skills and knowledge of advanced retrieval in LangChain needed to build and optimize scalable LLM retrieval systems.