https://store-images.s-microsoft.com/image/apps.57941.61840741-28d9-40ba-b146-4b34bc32eb88.7529d00f-ac6b-4568-b24b-9cb18b82c093.a7ad88b5-9a97-4271-b21a-4672074e42d4
voyage-3 Embedding Model
Voyage AI Innovations Inc
voyage-3 Embedding Model
Voyage AI Innovations Inc
voyage-3 Embedding Model
Voyage AI Innovations Inc
Text embedding model for general-purpose (incl. multilingual) retrieval and AI. 32K context length.
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-3 is a general-purpose embedding that: [1] outperforms OpenAI v3 large across all eight evaluated domains (tech, code, web, law, finance, multilingual, conservation, and long-context) by 7.55% on average, [2] has a 3-4x smaller embedding dimension (1024) compared to OpenAI (3072) and E5 Mistral (4096), resulting in 3-4x lower vectorDB costs, and [3] supports a 32K-token context length, compared to OpenAI (8K) and Cohere (512). Learn more about voyage-3 here.