voyage-3-large
voyage-3-large is Voyage AI's general-purpose embedding model with a context window of 0 tokens, Matryoshka dimensionality (2048/1024/512/256), and quantization-aware training. It outperforms OpenAI text-embedding-3-large by 9.74% across 100 retrieval datasets.
import { embed } from 'ai';
const result = await embed({ model: 'voyage/voyage-3-large', value: 'Sunny day at the beach',})