Source: Qdrant docs: Vectors (multivectors)
Qdrant's vector concepts page: native multivector points scored with MaxSim, configuration, and the hard per-point size limit.
Contents
- What: vendor documentation
- Author/publisher: Qdrant
- Date: read 2026-11-14 (multivectors available since v1.10.0)
- Original: qdrant.tech/documentation/concepts/vectors
Summary
Documents how a Qdrant point can hold a matrix of same-sized vectors instead of one vector, used either for several views of one object or for late-interaction token embeddings such as ColBERT.
Key claims
- Configure a dense vector with
multivector_configandcomparator: max_sim; MaxSim is currently the only comparator. - MaxSim sums, over each query vector, its best similarity to any document vector, and returns one score per point.
- Hard limit: number of sub-vectors x vector size must stay under 1,048,576 (for 4096-dim vectors, at most 255 sub-vectors). Workarounds: pool token vectors, or split a document into several points and aggregate.
- Compressed datatypes (
turbo16,turbo8,turbo4) support multivectors.