CS 594: Vector Databases

The rapid rise of large language models (LLMs) and Retrieval-Augmented Generation (RAG) for tasks such as information retrieval, question answering, and knowledge-intensive reasoning, together with the increasing prevalence of large-scale unstructured data, has driven the emergence of vector database management systems. These systems are designed to extend traditional database architectures by efficiently storing, indexing, and querying vector representations such as embeddings, which are central to modern machine learning and AI-driven applications.

This course explores advanced topics in Vector Databases and Retrieval-Augmented Generation (RAG), with a focus on the underlying data structures, algorithms, and system designs. Students will learn about information retrieval fundamentals, embedding models, vector database architectures, indexing techniques for high-dimensional data, and modern approaches for efficient query processing in vector databases. The course also covers other data models, such as knowledge graphs, and a practical implementation of RAG pipelines using vector databases.