The Evolution of Vector Search in YDB
summary
Describes YDB’s development of vector search from a simple initial implementation to an advanced indexing system, detailing the key development stages, challenges encountered, and the solutions used. Covers how YDB scaled to efficiently handle billions of vectors and the architectural and algorithmic changes made to achieve that.
AI-written summary · about
chapters (11)
- 0:00Introduction to vector search
- 7:05LLM and RAG applications
- 8:30Vector search in YDB
- 10:42Exact vector search
- 13:35Approximate search with quantization
- 15:40Vector indexes for billions
- 16:43YDB index architecture
- 20:58Creating and using index
- 24:34Updating vector index
- 25:58Results and availability
- 26:18Q&A
related talks
35mImpact of Vector Search
39mWhat's in a Vector Database?
27mUnified AI & Relational Power: Scalable Distributed Vector Search with
40mUnder the hood of vector search with JVector
26mThe Rise of Vector Databases - Lessons from the Milvus Community
44mVector Search Beyond the Hype: Real-World Implementation and Performance Insights
41mGetting Started With Vector Databases
45mA gentle introduction to Vector Databases