A fun and absurd introduction to Vector Databases
summary
Shows how vector databases store embeddings from OpenAI/Hugging Face and return semantic neighbours in milliseconds, using HNSW indexing with cosine distance and typical stacks (Weaviate/VV8, Pinecone/PGVector/Redis modules, Spring backend, Unity frontend). Demos include weapons and D&D spell search (distances ~0.22–0.69), image lookup for Pokémon and icon matching via CLIP same-space embeddings, and lyric matching using Whisper — all working live offline with expected noisy but stable results.
AI-written summary · about
chapters (12)
- 0:00Introduction and speaker
- 1:44What are vectors
- 6:23Vector databases explained
- 11:38Visualizing vector spaces
- 16:58Choosing a vector database
- 19:07How vector search works
- 24:11Demo: Weapon search
- 27:47Demo: Dungeons & Dragons spells
- 32:43Demo: Image search with Pokémon
- 39:09Demo: Cross-modal search
- 45:21Demo: Transcribing metal lyrics
- 49:37Q&A and closing
related talks
46mA fun and absurd introduction to Vector Databases
48mA fun and absurd introduction to Vector Databases
48mA Fun & Absurd Introduction to Vector Databases
47mA fun and absurd introduction to Vector Databases
46mA Fun & Absurd Introduction to Vector Databases
01h 23mVector Databases Demystified: Discover how they work
45mA gentle introduction to Vector Databases
01h 46mVector Databases (for GenAI & beyond)