0
Fork 0
mirror of https://github.com/mastra-ai/mastra.git synced 2026-11-17 08:44:46 +00:00
mastra/embedders/voyageai
Ward Peeters b2ce66cef8
chore: run lint-staged for root files and the 16 packages without a config (#29898)
Co-authored-by: mastracode <284800079+mastra-platform[bot]@users.noreply.github.com>
History 2026-11-10 14:08:55 +01:00
..
src Add voyage-code-4 to @mastra/voyageai (#27761) 2026-10-19 20:32:12 -07:00
CHANGELOG.md chore: version - exit prerelease mode 2026-10-28 13:15:52 +00:00
lint-staged.config.js chore: run lint-staged for root files and the 16 packages without a config (#29898) 2026-11-10 14:08:55 +01:00
package.json chore: version - exit prerelease mode 2026-10-28 13:15:52 +00:00
README.md chore(*): Update/unify/add READMEs (#22858) 2026-09-02 14:36:59 +02:00
tsconfig.build.json feat(voyageai): add VoyageAI embeddings and reranker integration (#14296) 2026-06-09 08:01:38 -07:00
tsconfig.json chore: migrate package builds to tsdown (#19829) 2026-07-28 12:32:21 +02:00
tsdown.config.ts chore: migrate package builds to tsdown (#19829) 2026-07-28 12:32:21 +02:00
vitest.config.ts feat(voyageai): add VoyageAI embeddings and reranker integration (#14296) 2026-06-09 08:01:38 -07:00

@mastra/voyageai

VoyageAI embeddings integration for Mastra. Provides text, multimodal, and contextualized chunk embeddings using the official VoyageAI TypeScript SDK.

Installation

npm install @mastra/voyageai

Usage

Text Embeddings

import { voyage, voyageEmbedding } from '@mastra/voyageai';

// Use default model (voyage-3.5)
const result = await voyage.doEmbed({ values: ['Hello world'] });
console.log(result.embeddings[0].length);

// Use specific model with options
const model = voyageEmbedding({
  model: 'voyage-3-large',
  inputType: 'query',
  outputDimension: 512,
});
const queryResult = await model.doEmbed({ values: ['search query'] });

Documentation

Changelog

See the package changelog for version history and release notes.

Support

We have an open community Discord. Come and say hello and let us know if you have any questions or need any help getting things running.