jina-clip-v2 brings text-to-image search across 89 languages to Elasticsearch, no GPU needed
Elasticsearch Labs
jina-clip-v2 brings text-to-image search across 89 languages to Elasticsearch, no GPU needed
Run multimodal search across 89 languages inside Elasticsearch with jina-clip-v2: one embedding space for text and images, with no separate model infrastructure to manage.
Semantic search, now multilingual by default
Elasticsearch Labs
Semantic search, now multilingual by default
semantic_text now defaults to jina-embeddings-v5-text on Elastic Inference Service, enabling multilingual semantic search in Elasticsearch.
Jina Rerankers bring fast, multilingual reranking to Elastic Inference Service (EIS)
Elasticsearch Labs
Jina Rerankers bring fast, multilingual reranking to Elastic Inference Service (EIS)
Elastic now offers jina-reranker-v2-base-multilingual and jina-reranker-v3 on EIS, enabling fast multilingual reranking directly in Elasticsearch for higher-precision retrieval, RAG, and agentic workflows without added infrastructure.
jina-embeddings-v3 is now available on Elastic Inference Service
Elasticsearch Labs
jina-embeddings-v3 is now available on Elastic Inference Service
Introducing jina-embeddings-v3 on Elastic Inference Service (EIS) and explaining how to get started.