05:01Vector Databases Full Course for Beginners – Embeddings, Similarity Search & ChromaDB
From the creator
Learn how vector databases work, from the math behind vectors to building semantic search with ChromaDB. This beginner course covers vectors, cosine similarity, Euclidean distance, tokenization, and embedding models, then walks through a live demo of generating embeddings with Google's Gemini embedding model. You will also explore the internal architecture of a vector database, including storage, indexing, and the IVF and HNSW index types. By the end, you will store embeddings in ChromaDB and run semantic searches that find matches by meaning instead of by keyword. Course from @codeEdx Course resources: https://codeedx.gumroad.com/l/vector-databases-course-resources ❤️ Support for this channel comes from our friends at Scrimba – the coding platform that's reinvented interactive learning: https://scrimba.com/freecodecamp ⭐️ Chapters ⭐️ - 0:00:00 Introduction & Course Overview - 0:03:42 What Is a Vector Database? - 0:22:40 What Are Vectors? - 0:33:37 Cosine Similarity - 0:40:37 Euclidean Distance - 0:45:16 Tokens & Tokenization - 0:57:23 Embeddings & Embedding Models - 1:11:48 Demo: Generating Embeddings with Gemini - 1:19:43 Visualizing Embeddings with PCA - 1:22:07 Inside a Vector Database: Architecture - 1:26:00 Indexing with IVF & HNSW - 1:29:26 Project: Storing & Querying Embeddings with ChromaDB - 1:38:22 Semantic Search in Action 🎉 Thanks to our Champion and Sponsor supporters: 👾 @omerhattapoglu1158 👾 @goddardtan 👾 @akihayashi6629 👾 @kikilogsin 👾 @anthonycampbell21
Published 2026-11-03 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.





