https://store-images.s-microsoft.com/image/apps.10812.5993fd08-1d8b-4276-b380-e083ecc6a062.63cb316e-0940-4d30-be64-bb5005b0ac77.160e4119-8d99-47de-b997-6f911b74beed

Jina Reranker v2 Base - Multilingual

Jina AI

Categories
AI + Machine LearningCompute
Support
Support
Legal
License AgreementPrivacy Policy

Jina Reranker v2 Base - Multilingual

Jina AI

New state-of-the-art neural text reranking model for 100+ languages.

  • Jina Reranker v2 model is a neural text reranking model, designed to enhance the relevance of search results.
  • It complements text embedding models and refines search results by prioritizing documents relevant to a query.
  • This state-of-the-art reranker model enables a variety of applications that rely on precise search results across different languages, improved information retrieval, and high document throughput. Use-cases: Vector search, retrieval augmented generation.

Hightlights:

  • High multilingual performance across the board: This reranker model ranks at the top compared to its competitors, in terms of 'Mean Reciprocal Rank' (MRR), recall and NDCG, according to BEIR, MKQA and AirBench.

  • Extended context length: This reranker model is capable of handling queries up to 512 tokens and documents as large as 8192 tokens.

  • Ultra-fast: 15x more documents throughput than bge-reranker-v2-m3, and 6x more than jina-reranker-v1-base-en.