Sakhanda Wire
NVDA $152.58 -2.28% MSFT $506.11 -2.29% GOOGL $279.81 -1.38% META $619.07 -1.17% AMZN $256.55 -0.47%
← Back to the news

Sentence Transformers v6.0 adds ColBERT-style multi-vector retrieval

Sentence Transformers v6.0 introduces MultiVectorEncoder, a fourth model type for ColBERT-style late-interaction retrieval. The Python library already supports dense, sparse and reranker models for uses including semantic search and retrieval-augmented generation. MultiVectorEncoder can load PyLate and Stanford-NLP ColBERT checkpoints, while ColPali-family models support visual document retrieval through the same API.

Unlike a conventional embedding model, which compresses a document into one vector, a multi-vector model retains one projected vector for each token. At scoring time, MaxSim finds the strongest document-token match for every query token and sums those similarities. This preserves token-level evidence, including exact identifiers and separate requirements in a query, but produces a substantially larger index.

In the article’s Natural Questions example, 4,874 passages generated 608,414 128-dimensional token vectors, occupying 311.5 MB in float32. A compressed fast-plaid index reduced that representation to 92 MB. The package can be installed with pip; Sentence Transformers v6.0 requires transformers v5.x, torch 2.2+ and huggingface-hub v1.x. Image dependencies are additionally required for ColPali-style visual retrieval.

Written by Sakhanda Wire AI from reporting by Hugging Face. Facts, quotes and full context are in the original article below.

Originally published by Hugging Face on

Read the original on Hugging Face ↗

The reporting and the image belong to Hugging Face and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news