voyage-multilingual-2 Embedding Model

Text embedding models are neural networks that transform texts into numerical vectors. They are a crucial building block for semantic search/retrieval systems and retrieval-augmented generation (RAG) and are responsible for the retrieval quality. voyage-multilingual-2 is optimized for multilingual retrieval and RAG. It demonstrates superior multilingual retrieval quality and outperforms alternatives, such as OpenAI v3 large and Cohere multilingual v3, on most languages, including major languages like French, German, Japanese, Spanish, and Korean. On average, voyage-multilingual-2 outperforms the second-best-performing model by 5.6%. Notably, voyage-multilingual-2 continues to perform well on English. voyage-multilingual-2 supports a 32K context length. Learn more about voyage-multilingual-2 here.