Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification.
-
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
Paper • 2602.15547 • Published • 23 -
jinaai/jina-embeddings-v5-text-small
Feature Extraction • Updated • 11.1k • 83 -
jinaai/jina-embeddings-v5-text-nano
Feature Extraction • Updated • 7.22k • 35 -
jinaai/jina-embeddings-v5-text-small-text-matching
Sentence Similarity • 0.6B • Updated • 13k • 4