← Back to the wire

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

AnnouncementModelAug 18, 2026

MultiVectorEncoder supports ColBERT-style late interaction retrieval, loading any PyLate checkpoint, any Stanford-NLP ColBERT checkpoint, and colpali-engine models through a single API. Unlike dense embedding models that compress text into one vector, multi-vector models retain per-token vectors and score using the MaxSim operator, preserving token-level matching for stronger retrieval. The tradeoff is larger index size, though compression methods like PLAID bring storage costs in line with standard dense indexes.

Receipt № 14421 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

PyLateCompanyStanford-NLPCompanycolpali-engineCompanyMultiVectorEncoderModelColBERTModel
Canonical: https://huggingface.co/blog/multi-vector-encoder