/Patent Tracker
AmazonPatent applicationAI & softwareInterest 3/10

Amazon patents smarter caching for vector databases

Amazon describes a system that uses a router to decide which cache should store search results in a vector database. By checking a partial index search, the router directs similar requests to the same cache, increasing the chance that the data is already there.

Why it mattersThis could make large-scale AI search tools faster and cheaper by reducing the need to fetch data from slower storage.

In the filing’s own words

A vector-labeled database may improve a cache hit rate for read requests by performing a partial approximate nearest neighbor index search at a router to designate the cache that results of a read request are to be written to. The selected cache may be associated with a particular node of a layer of an approximate nearest neighbor index search. The router may direct all reads with search vectors close to the particular node to the associated cache.

What exactly they claim (claim 1)

1. A system, comprising: a router; and one or more computing resources configured to implement a set of caches and a vector-labeled database, wherein results of a prior read request are added to a given cache in response to the prior read request; wherein the router is configured to: receive a read request for one or more data items associated with one or more approximate nearest neighbor vectors of a request vector, wherein the one or more approximate nearest neighbor vectors are maintained in the vector-labeled database; determine a portion of vector space for the request vector using at least a first layer of an approximate nearest neighbor index search; select, based on the determined portion of vector space for the request vector, a particular cache of the set of caches; cause the particular cache to be checked for the one or more approximate nearest neighbor vectors of the request vector; and cause the one or more data items associated with the one or more approximate nearest neighbor vectors to be returned in response to the request.

Facts

Company
Amazon (Amazon Technologies, Inc.)
Official title
CLUSTER AWARE CACHING FOR VECTOR DATABASE
Publication number
US20260288835A1
Application number
19085883
Filed
Mar 20, 2025
Published
Sep 24, 2026
Inventors
2
Claims
20

Classified under

G06F 16/3347 Physics & computingG06F 16/322 Physics & computing

More from Amazon in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.