Skip to content

Level 1 · Entry Foundations

Goal: understand what embeddings actually are, how similarity search works under the hood, and get comfortable running real queries against a vector database.

Modules

  1. What Are Embeddings & Why Vector Search
  2. Setup: Python, NumPy & Your First Vectors
  3. Distance Metrics (Cosine, Euclidean, Dot Product)
  4. Brute-Force Similarity Search
  5. Generating Real Embeddings
  6. Intro to Approximate Nearest Neighbor Search
  7. Your First Vector DB: Chroma
  8. Indexing & Querying Basics
  9. Metadata Filtering
  10. Project — Semantic Search CLI

By the end of this level you'll be able to explain what an embedding is in plain terms, compute similarity by hand, generate real embeddings from text, and run queries against a working vector database — the foundation everything later in this course builds on.