0:00 This beginner course teaches vector databases from scratch. Starting with vectors, cosine similarity and ukitian distance, then moving on to tokenization and embedding models. You'll generate embeddings in a live demo with Google's Gemini embedding model and see how a vector database works inside, including its storage indexing and the IVF and HNSW index types. The course ends with a
0:31 project where you store embeddings in Chroma DB and run semantic searches that find matches by meaning instead of by keyword. See if you want to learn vector databases in one shot then this video is for you. In this video I will literally hold your hand and teach you everything from scratch. No prior knowledge is required. I have 15 years working as a software engineer and 4 years working as a lead AI engineer. And let me tell you vector database is something you must know in 2026. Whether you are a software
1:03 engineer, an AI engineer or a machine learning engineer. Today technologies like AI agents, recommendation engines, rag application, enterprise knowledge bases are all powered by one core concept, vector databases. So by the end of this video, you will not only understand vector databases conceptually, but you will also gain hands-on experience working with vector databases. So here is what we will come. So in chapter one, we will understand the fundamentals. What exactly is a vector database? Why were vector
🔒 The full, searchable transcript is available with Pro.
Common questions about this video