jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
This work addresses retrieval challenges for users needing unified text and image representations, though it appears incremental as it builds on existing embedding and adaptation techniques.
The paper tackles the problem of multimodal multilingual retrieval by introducing jina-embeddings-v4, a 3.8 billion parameter model that achieves state-of-the-art performance on both single-modal and cross-modal retrieval tasks, with particular strength in processing visually rich content like tables and charts.
We introduce jina-embeddings-v4, a 3.8 billion parameter multimodal embedding model that unifies text and image representations through a novel architecture supporting both single-vector and multi-vector embeddings in the late interaction style. The model incorporates task-specific Low-Rank Adaptation (LoRA) adapters to optimize performance across diverse retrieval scenarios, including query-document retrieval, semantic text similarity, and code search. Comprehensive evaluations demonstrate that jina-embeddings-v4 achieves state-of-the-art performance on both single-modal and cross-modal retrieval tasks, with particular strength in processing visually rich content such as tables, charts, diagrams, and mixed-media formats. To facilitate evaluation of this capability, we also introduce Jina-VDR, a novel benchmark specifically designed for visually rich image retrieval.