<details> <summary><b>Why is vector search useful?</b></summary>

Vector search is widely used for queries where relevance is important. For example, searching a large corpus of documents for documents related to a specific use case or generating recommended items for a shopping cart. Increasingly, vector stores are also being used as a persistent cache for generative AI models to prevent the need for recomputation.

</details> <details> <summary><b>What vector dataypes does Rockset support?</b></summary>

Rockset vector operations support [float](🔗) and [int](🔗) type vectors.

</details> <details> <summary><b>What are the max vector dimensions?</b></summary>

Vectors are syntactically identical to arrays and there is no limit on array size, so there is no limit on vector size.

</details> <details> <summary><b>How do I ingest my vectors?</b></summary>

Vectors can be [bulk ingested](🔗) and [stream ingested](🔗) as part of incoming documents the same as arrays. Just be sure to use [`VECTOR_ENFORCE`](🔗) on the vector field in your collection's [<<glossary:Ingest Transformation>>](🔗).

</details> <details> <summary><b>Can you update vectors?</b></summary>

Yes, you manipulate vectors in all of the same ways you would manipulate arrays. Rockset sits on top of an [LSM tree based RocksdDB](🔗) storage engine, which means random mutations are fast. Updates, inserts, and deletes are immediately visible in any ANN index associated with the vector.

</details> <details> <summary><b>Is there a limit on the number of vectors?</b></summary>

There is no general limit on the number of vectors that can be stored in Rockset. Rockset's disaggregated [Storage Architecture](🔗) allows your storage tier to scale independently of your compute needs.

</details> <details> <summary><b>Why use Rockset for vector search?</b></summary>

Rockset is already built for low-latency complex analytics on real-time data which perfectly complements vector search use cases.