Jina ColBERT v2

Multilingual late-interaction retrieval model supporting embedding and re-ranking

InternationalSelectionProductivity\Multilingual support\\Information retrieval\
Jina ColBERT v2 is an advanced late-interaction retrieval model built on the ColBERT architecture, supporting 89 languages with superior retrieval performance, user-controllable output dimensions, and processing capabilities for text lengths up to 8192 tokens. It represents a revolutionary advancement in information retrieval, approximating the joint query-document attention of cross-encoders through late-interaction scoring, while maintaining inference efficiency close to traditional dense retrieval models.
Visit

Jina ColBERT v2 Visit Over Time

Monthly Visits

424099

Bounce Rate

48.38%

Page per Visit

2.5

Visit Duration

00:02:14

Jina ColBERT v2 Visit Trend

Jina ColBERT v2 Visit Geography

Jina ColBERT v2 Traffic Sources