Free Lesson
Build a vector database from scratch
Part of Maven Rewind
60 min
May 7, 2025 12:00 PM
Virtual (Zoom)
In this video
What you'll learn
Learn how embedding similarity search works
Learn the most common graph-based vector search algorithm used in Elasticsearch, Weaviate, QDrant, Pinecone, etc
See where vector search goes wrong
As you watch an expert live-code, see where the algorithm falls apart as a real-life expert makes a mistake
Deepen your vector search knowledge
Dense vectors provide specific constraints on retrieval solutions - learn what these are, how they can go wrong
Why this topic matters
RAG systems all use vector databases. HNSW (Hierarchical Navigable Small Worlds) is the most common algorithm. If you want to build RAG, you should appreciate how this algorithm works
You'll learn from

Doug Turnbull
Search Consultant and Coach

John Berryman
Founding member Github Copilot
Previously at
