{"@attributes":{"version":"2.0"},"channel":{"title":"Redis vector sets on Docs","link":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/","description":"Recent content in Redis vector sets on Docs","generator":"Hugo","language":"en","item":[{"title":"Filter expressions","link":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/filtered-search\/","pubDate":"Mon, 01 Jan 0001 00:00:00 +0000","guid":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/filtered-search\/","description":"

\n Overview\n \n \n <\/path>\n <\/svg>\n <\/a>\n<\/h2>\n

Filtered search lets you combine vector similarity search with scalar filtering. You can associate JSON attributes with elements in a vector set, and then filter results using those attributes during VSIM<\/code><\/a> queries.<\/p>"},{"title":"Performance","link":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/performance\/","pubDate":"Mon, 01 Jan 0001 00:00:00 +0000","guid":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/performance\/","description":"

\n Query performance\n \n \n <\/path>\n <\/svg>\n <\/a>\n<\/h2>\n

Vector similarity queries using the VSIM<\/code><\/a> are threaded by default. Redis uses up to 32 threads to process these queries in parallel.<\/p>"},{"title":"Scalability","link":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/scalability\/","pubDate":"Mon, 01 Jan 0001 00:00:00 +0000","guid":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/scalability\/","description":"

\n Multi-instance scalability\n \n \n <\/path>\n <\/svg>\n <\/a>\n<\/h2>\n

Vector sets can scale horizontally by sharding your data across multiple Redis instances. This is done by partitioning the dataset manually across keys and nodes.<\/p>"},{"title":"Memory optimization","link":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/memory\/","pubDate":"Mon, 01 Jan 0001 00:00:00 +0000","guid":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/memory\/","description":"

\n Overview\n \n \n <\/path>\n <\/svg>\n <\/a>\n<\/h2>\n

Redis vector sets are efficient, but vector similarity indexing and graph traversal require memory tradeoffs. This guide helps you manage memory use through quantization, graph tuning, and attribute choices.<\/p>"},{"title":"Troubleshooting","link":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/troubleshooting\/","pubDate":"Mon, 01 Jan 0001 00:00:00 +0000","guid":"https:\/\/redis.io\/docs\/latest\/develop\/data-types\/vector-sets\/troubleshooting\/","description":"

\n Common challenges\n \n \n <\/path>\n <\/svg>\n <\/a>\n<\/h2>\n

Vector sets are approximate by design. That makes debugging trickier than with exact match queries. This section helps you understand issues with recall, filtering, and graph structure.<\/p>"}]}}