Google Cloud has introduced scalable vector-search capabilities to its Memorystore for Valkey and Redis Cluster, enabling ultra-low latency searches over billions of vectors.
This update's architecture accelerates index build times as nodes are added, optimizing search performance logarithmically for HNSW searches and linearly for brute-force searches.
Developers can now scale their clusters to 250 shards, essential for enterprise applications needing semantic searches over extensive datasets.
The introduction of hybrid queries allows developers to combine vector searches with numeric and tag field filters, enhancing the fine-tuning of search results.
Collection
[
|
...
]