A fun and absurd introduction to Vector Databases
summary
A practical demo builds an offline pipeline with vv8 as vector store, a Spring Boot Kotlin backend and Unity 3D front end, using CLIP, ResNet50 and BERT-style embeddings (384 dims typical) and OpenAI/Whisper for audio. Indexing uses HNSW and retrieval uses cosine distance; nearest-neighbor scores shown (example distances 0.3, 0.228, 0.4). Demos include weapon, D&D spell and icon matching that work well, an image Pokémon search that needs more angles, and a lyrics match that fails on noisy transcriptions.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 1:55What is a Vector
- 5:46What is a Database
- 7:02What are they used for
- 9:27Vector Space
- 10:24Data Visualization
- 12:02Vector Databases
- 14:31The Stack
- 18:21Indexing
- 21:31Weapon Search
- 34:11Icon Search
- 39:20Lyrics Search
- 42:49Outro
related talks
47mA fun and absurd introduction to Vector Databases
46mA Fun & Absurd Introduction to Vector Databases
48mA Fun & Absurd Introduction to Vector Databases
50mA fun and absurd introduction to Vector Databases
46mA fun and absurd introduction to Vector Databases
41mGetting Started With Vector Databases
45mA gentle introduction to Vector Databases
01h 23mVector Databases Demystified: Discover how they work