https://store-images.s-microsoft.com/image/apps.19458.348e3b08-7e55-487b-9881-8d82d3a4f4e2.08609ea8-2081-4ab4-a640-73714b6565a8.a17dd991-71e2-4cb2-ba8b-c1c2a42c4883
voyage-context-3 Embedding Model
MongoDB, Inc.
voyage-context-3 Embedding Model
MongoDB, Inc.
voyage-context-3 Embedding Model
MongoDB, Inc.
Contextualized chunk embedding model for vectors with full document context. 32K context length.
Contextualized chunk embedding models are novel neural networks that encode not only the chunk’s own content, but also capture the contextual information from the full document 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-context-3 is a contextualized chunk embedding model that produces vectors for chunks that capture the full document context without any manual metadata and context augmentation, leading to higher retrieval accuracies than with or without augmentation. On chunk-level and document-level retrieval tasks, voyage-context-3 outperforms OpenAI-v3-large by 14.24% and 12.56%, Cohere-v4 by 7.89% and 5.64%, Jina-v3 late chunking by 23.66% and 6.76%, and contextual retrieval by 20.54% and 2.40%, respectively.
voyage-context-3 is a contextualized chunk embedding model that produces vectors for chunks that capture the full document context without any manual metadata and context augmentation, leading to higher retrieval accuracies than with or without augmentation. On chunk-level and document-level retrieval tasks, voyage-context-3 outperforms OpenAI-v3-large by 14.24% and 12.56%, Cohere-v4 by 7.89% and 5.64%, Jina-v3 late chunking by 23.66% and 6.76%, and contextual retrieval by 20.54% and 2.40%, respectively.