✳flâneur — a map of the web's best reading

ScaNN for AlloyDB: The postgres vector index that works well for all sizes | Google Cloud Blog

cloud.google.com · 1,707 words · saved by 1 readers

Executive Summary - ScaNN for AlloyDB is the first Postgres-based vector search extension that supports vector indexes of all sizes, while providing fast index builds, fast transactional updates, small memory footprint, and accurate and fast search. Many customers use AlloyDB for PostgreSQL to power sophisticated semantic search and generative AI use cases, performing vector search on 100 million to 1 billion+ vectors. At the same time, they want a large vector search index that works with the rest of their operational database, and the first place they look is the pgvector HNSW graph algorithm from the Postgres OSS community. pgvector extends the PostgreSQL SQL language to support combining SQL queries with filters and joins, together with vector search, an invaluable combination for modern applications. We have supported the popular pgvector extension featuring HNSW in AlloyDB since 2023, and we are committed to continuing to do so. Over time we expect there to be multiple alternativ

Databases ScaNN for AlloyDB: The first PostgreSQL vector search index that works well from millions to billion of vectors March 11, 2025 Alan Li Software Engineer Yannis Papakonstantinou Distinguished Engineer Try Gemini Enterprise Business Edition today The front door to AI in the workplace Try now Executive Summary - ScaNN for AlloyDB is the first Postgres-based vector search extension that supports vector indexes of all sizes, while providing fast index builds, fast transactional updates, small memory footprint, and accurate and fast search. Many customers use AlloyDB for PostgreSQL to powe

Explore this link on the map →

related reading