No Special Index Needed: Qdrant, Milvus & Vespa Natively Index Multi-Vectors

tomaarsen · x · 2026-08-18

Sentence Transformers doesn't ship a late-interaction index and doesn't need one: these indexes store whatever encodedocument returned. Qdrant, Weaviate, Vespa, LanceDB, VectorChord & Milvus index multi-vectors natively, and LightOn's fast-plaid is a pip install away. The post also covers the new interpretability module: since MaxSum is a sum of per-query-token maxima, a ranking decomposes exactly — every score point belongs to one query token and one document token — rendered as the standard ColPali heatmap, aggregated or per query token.

Related event: Sentence Transformers v6.0 Ships Late-Interaction Multi-Vector Models(27 posts)→

Original post →

More from coding & agent

coding & agent channel →