Vector Databases

Vector Databases

Duration: 1 Day

Description

Vector databases power semantic search and retrieval in modern AI applications, storing and querying the embeddings that let systems find information by meaning rather than keywords. This focused course gives developers a practical understanding of how vector databases work and how to use them well: how embeddings and similarity search work, how to design indexes and queries, and how to choose and operate a vector store. Hands-on exercises build the skills needed to add reliable semantic retrieval to AI applications.
Class time is divided between instructor-led explanation (40 percent) and hands-on exercises (60 percent).

Audience

Developers and data practitioners building AI applications that need semantic search or retrieval. A useful elective alongside LLM application and RAG work.

Objectives

  • Explain how embeddings and vector similarity search work
  • Describe what vector databases do and when to use them
  • Design indexes, metadata, and queries
  • Perform similarity and hybrid search
  • Compare vector database options and tradeoffs
  • Operate a vector store reliably in an application

Prerequisites

Participants should be comfortable writing code. The following will help:

  • Working knowledge of Python (see Python Foundations)
  • Familiarity with embeddings or AI application concepts

Course Outline

  • Module 1 – Course Introduction
    • Welcome and objectives
    • Why vector databases
    • Semantic versus keyword search
  • Module 2 – Embeddings and Similarity
    • How embeddings represent meaning
    • Distance and similarity measures
    • Indexing and approximate nearest neighbor search
    • Hands-on exercise: similarity search basics
  • Module 3 – Working with a Vector Database
    • Storing vectors and metadata
    • Designing collections and indexes
    • Querying: similarity, filtering, and hybrid search
    • Hands-on exercise: build a searchable store
  • Module 4 – Choosing and Operating
    • Comparing vector database options
    • Performance, scale, and cost
    • Reliability and maintenance
    • Integration with AI applications
  • Module 5 – Course Wrap-Up
    • Key takeaways
    • Resources for continued learning
    • Next steps