voyage-multimodal-3

voyage-multimodal-3 is a state-of-the-art multimodal embedding model and a big step towards seamless RAG and semantic search for documents rich with both visuals and text. Unlike existing multimodal embedding models, voyage-multimodal-3 can vectorize interleaved texts + images and capture key visual features from screenshots of PDFs, slides, tables, figures, and more, thereby eliminating the need for complex document parsing. When evaluated against seven competing models across 54 datasets, voyage-multimodal-3 consistently achieves the highest retrieval accuracy.