Vector Similarity Search in Spring
summary
Shows how to build vector search with Spring plus the Redis Stack and DJL for embeddings, using a retina-face model to detect and index faces and a fashion demo with ~2,800 products; a preloaded index of 11,637 celebrities returns matches (top score ~92.8) by cosine similarity, with HNSW and flat indexes available for speed vs. precision. Code uses Spring annotations to vectorize and index fields and the demos run end-to-end.
AI-written summary · about
chapters (14)
- 0:00Introduction
- 1:22Why vector databases now
- 4:15Vector similarity search basics
- 7:09AI and ML in Java
- 17:07What is Redis
- 21:20Understanding vectors and embeddings
- 28:59Demo word vector math
- 31:15Similarity metrics explained
- 38:02Vectorization process
- 41:57Redis OM Spring framework
- 44:48Vector search in e-commerce
- 48:41Celebrity face recognition demo
- 57:12Fashion product finder demo
- 1:00:24Summary and resources
related talks
55mVector Similarity Search in Spring with Redis Stack
01h 01mVector Similarity Search in Spring with Redis Stack
29mUnleashing the Power of Vector Search and Semantic Caching in Java
50mA fun and absurd introduction to Vector Databases
14mSearch on Steroids
46mA fun and absurd introduction to Vector Databases
47mA fun and absurd introduction to Vector Databases
59mContextual search with vector search: exploring your options with open source tools