---
title: "Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers"
url: https://daily.dev/posts/multi-vector-late-interaction-embedding-models-with-sentence-transformers-bynexr3hj
source_url: https://huggingface.co/blog/multi-vector-encoder
type: article
source: "Hugging Face"
published: 2026-08-18T13:50:47.172Z
updated: 2026-08-25T12:21:13.940Z
tags: ["vector-search", "embeddings"]
reading_time: 39
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

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

**[Hugging Face](https://daily.dev/sources/huggingface)** · 39 min read · 0 upvotes · 0 comments

## Summary

Sentence Transformers v6.0 adds a fourth model type, MultiVectorEncoder, for ColBERT-style late interaction retrieval. It loads PyLate, Stanford-NLP ColBERT, and colpali-engine checkpoints through the same API used for dense, sparse, and reranker models. The post covers multi-vector theory (MaxSim scoring, token-level embeddings), installation, loading various checkpoint formats, encoding, scoring, semantic search, retrieve-and-rerank patterns, indexing with Qdrant/Weaviate/Vespa/fast-plaid, visual/audio/video document retrieval, interpretability, token pooling for index compression, and inference speedups via Flash Attention and quantization.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://huggingface.co/blog/multi-vector-encoder>

## Questions this post answers

### How do I load a ColBERT-style late interaction model in Sentence Transformers?

Sentence Transformers v6.0 introduces a MultiVectorEncoder class that loads any PyLate checkpoint, any Stanford-NLP ColBERT checkpoint, or a ColPali-family visual retrieval model with the same API used for dense, sparse, and reranker models. Load it with MultiVectorEncoder('lightonai/LateOn') or similar, then use encode_query and encode_document to get per-token embeddings.

_daily.dev surfaces practical guides like this for developers wiring up retrieval stacks._

### What are the minimum dependency versions required to use Sentence Transformers v6.0?

Sentence Transformers v6.0 requires transformers v5.x, torch 2.2 or newer, and huggingface-hub v1.x. Anyone pinned to lower versions of those libraries needs to plan an upgrade first, and a migration guide documents the full list of breaking changes introduced alongside the new MultiVectorEncoder model type.

_Developers planning library upgrades can track breaking changes like this one on daily.dev._

### How much extra storage does a ColBERT-style multi-vector index need compared to a dense embedding index?

Encoding 4,874 Natural Questions passages with lightonai/LateOn produced 608,414 token vectors (about 124.8 per passage), roughly 42x the storage of a dense all-MiniLM-L6-v2 index, or about 62 KiB per passage in float32. Compressed with a PLAID-based index like fast-plaid, the same vectors take just 92 MB, comparable to a dense index from a large model like Qwen3-Embedding-8B.

_Weighing retrieval quality against index cost is easier when daily.dev keeps you current on tools like this._

---

Tags: [#vector-search](https://daily.dev/tags/vector-search), [#embeddings](https://daily.dev/tags/embeddings)

[View this post on daily.dev](https://daily.dev/posts/multi-vector-late-interaction-embedding-models-with-sentence-transformers-bynexr3hj)