new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

voyage-ai/models

3 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Voyage AI text embedding models and capabilities

Text embedding models: voyage-3.5 (default dimensions: 1024, 256, 512, 2048; context: 32,000), voyage-3.5-lite (1024, 256, 512, 2048; 32,000), voyage-3-large (1024, 256, 512, 2048; 32,000), voyage-3 (1024; 32,000), voyage-code-3 (1024, 256, 512, 2048; 32,000), voyage-3-lite (512; 32,000), voyage-finance-2 (1024; 32,000), voyage-multilingual-2 (1024; 32,000), voyage-law-2 (1024; 32,000), voyage-code-2 (1024; 16,000).

Voyage AI multimodal embedding model creation

Create a multimodal embedding model using the `.multimodalEmbeddingModel()` factory method, for example: `voyage.multimodalEmbeddingModel('voyage-multimodal-3')`

Voyage AI multimodal embedding model capabilities

The voyage-multimodal-3 model has a context length of 32,000 tokens and an embedding dimension of 1024.

Give your agent this brain