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/models

5 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 embedding usage example

Use Voyage AI embedding models with the embed function: import { voyage } from '@ai-sdk/voyage'; import { embed } from 'ai'; const { embedding } = await embed({ model: voyage.embedding('voyage-3.5'), value: 'sunny day at the beach', });

Voyage AI reranking model creation

Create reranking models using the .reranking() factory method on the voyage provider instance: voyage.reranking('rerank-2.5')

Voyage AI reranking usage example

Use Voyage AI reranking models with the rerank function: import { voyage } from '@ai-sdk/voyage'; import { rerank } from 'ai'; const documents = ['sunny day at the beach', 'rainy afternoon in the city', 'snowy night in the mountains']; const { ranking } = await rerank({ model: voyage.reranking('rerank-2.5'), documents, query: 'talk about rain', topN: 2, }); console.log(ranking);

Voyage AI reranking models with capabilities

Available reranking models and their context length: rerank-2.5 (32,000 context), rerank-2.5-lite (32,000), rerank-2 (16,000), rerank-2-lite (8,000), rerank-1 (8,000), rerank-lite-1 (4,000).

Voyage AI text embedding model creation

Create a text embedding model using the `.embeddingModel()` factory method on the voyage provider instance with a model ID. For example: `voyage.embeddingModel('voyage-3.5-lite')` or `voyage.embeddingModel('voyage-3.5')`. Alternatively, the `.embedding()` factory method can also be used: `voyage.embedding('voyage-3.5')`.

Give your agent this brain