Vector Similarity Search in Spring with Redis Stack
summary
Shows how to turn images and text into embeddings in Java using Redis Stack and Spring, storing 512‑dim vectors and running k‑NN searches with cosine similarity inside Redis Search so queries never pull full vectors over the network. Uses DJL to load PyTorch models (retinaface for face detection, Vision/NLP models for embeddings), demos a celebrity‑match app over ~6–9k images that returns top matches in ~1–2 seconds, and wires vectorization to entity save hooks for realtime updates.
AI-written summary · about
chapters (8)
- 0:00Redis and vector search intro
- 14:09Redis as real-time data platform
- 22:19Vector embeddings and AI models
- 33:28Demo: Vectorizing Images with Java
- 43:03Redis OM Spring for vector search
- 47:01Demo: Celebrity match app
- 51:22Unstructured data with AI tools
- 52:02Closing and resources
related talks
01h 01mVector Similarity Search in Spring with Redis Stack
01h 01mVector Similarity Search in Spring
29mUnleashing the Power of Vector Search and Semantic Caching in Java
50mA fun and absurd introduction to Vector Databases
54mPresentation: Finding Your Meme Twin with Embeddings & Vector Databases
47mA fun and absurd introduction to Vector Databases
46mA fun and absurd introduction to Vector Databases
48mA fun and absurd introduction to Vector Databases