Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

RAG with Vector Databases

University of Kansas School of Business

The previous chapter built RAG from scratch with numpy arrays. In practice, you use a vector database to store and search embeddings efficiently. This chapter explores ChromaDB — a popular open-source vector database — applied to real-world datasets.

You’ll see how the same retrieve-augment-generate pattern scales from a few documents to hundreds, and how ChromaDB handles the embedding storage, indexing, and similarity search automatically.