Embeddings
POST https://gateway-api.mastra.ai/v1/embeddings
Compatible with the OpenAI Embeddings API. input accepts a string, an array of strings, or token arrays.
import OpenAI from 'openai'
const client = new OpenAI({
apiKey: process.env.MASTRA_GATEWAY_API_KEY,
baseURL: 'https://gateway-api.mastra.ai/v1',
})
const result = await client.embeddings.create({
model: 'openai/text-embedding-3-small',
input: ['first document', 'second document'],
})
console.log(result.data[0].embedding.length)
From a Mastra application, use the model router:
import { ModelRouterEmbeddingModel } from '@mastra/core/llm'
const embedder = new ModelRouterEmbeddingModel('mastra/openai/text-embedding-3-small')