Skip to main content
Creates a text embedding model instance that generates embeddings for text inputs using Voyage AI’s text-optimized models. 
import { voyage } from 'voyage-ai-provider';

const model = voyage.textEmbeddingModel('voyage-3-lite');

​
Parameters

​
modelId
VoyageEmbeddingModelId
required
The identifier of the text embedding model to use.Available models:
  • voyage-3.5 - Latest generation model
  • voyage-3.5-lite - Lightweight version of 3.5
  • voyage-3-large - Large capacity model
  • voyage-3 - Standard third generation model
  • voyage-3-lite - Lightweight third generation model
  • voyage-code-3 - Optimized for code embeddings
  • voyage-finance-2 - Specialized for financial text
  • voyage-multilingual-2 - Supports multiple languages
  • voyage-law-2 - Specialized for legal text
  • voyage-code-2 - Previous generation code model

​
Returns

​
EmbeddingModelV3
object
A text embedding model instance that implements the AI SDK’s EmbeddingModelV3 interface.
​
modelId
string
The model identifier passed during creation
​
provider
string
The provider identifier: "voyage.embedding"
​
maxEmbeddingsPerCall
number
Maximum number of inputs per API call: 128
​
supportsParallelCalls
boolean
Whether parallel calls are supported: false

​
Input types

The text embedding model accepts TextEmbeddingInput which can be:
  • Single text: string - A single text string
  • Multiple texts: string[] - Array of texts combined into one embedding
  • Object format: { text: string | string[] } - Alternative format with explicit text property

​
Usage examples

​
Generate single embedding

Embed a single text string to generate one embedding vector. 
import { voyage } from 'voyage-ai-provider';
import { embed } from 'ai';

const { embedding } = await embed({
  model: voyage.textEmbeddingModel('voyage-3-lite'),
  value: 'The quick brown fox jumps over the lazy dog',
});

console.log(embedding);

​
Generate multiple embeddings

Embed multiple text strings to generate separate embedding vectors. 
import { voyage } from 'voyage-ai-provider';
import { embedMany } from 'ai';

const { embeddings } = await embedMany({
  model: voyage.textEmbeddingModel('voyage-3-lite'),
  values: [
    'The quick brown fox jumps over the lazy dog',
    'Artificial intelligence is transforming the world',
    'Machine learning enables computers to learn without being explicitly programmed',
  ],
});

for (const [index, embedding] of embeddings.entries()) {
  console.log(`Embedding ${index}: length ${embedding.length}`);
}

​
Combine multiple texts into one embedding

You can combine multiple text strings into a single embedding by passing an array. This is useful for embedding documents with multiple fields. 
import { voyage } from 'voyage-ai-provider';
import { embedMany } from 'ai';

const { embeddings } = await embedMany({
  model: voyage.textEmbeddingModel('voyage-3'),
  values: [
    // Product: title + description + features
    [
      'Premium Wireless Bluetooth Headphones',
      'Experience superior sound quality with active noise cancellation',
      'Battery life: 30 hours, Quick charge: 15 min = 3 hours playback',
      'Compatible with iOS, Android, and all Bluetooth devices',
    ],
    // Blog post: title + summary + tags
    [
      'The Future of Artificial Intelligence in Healthcare',
      'Exploring how AI is revolutionizing medical diagnosis and treatment',
      'Tags: AI, healthcare, machine learning, medical technology, innovation',
    ],
  ],
});

console.log(`Generated ${embeddings.length} embeddings`);

​
Use provider options

You can customize the embedding behavior using provider-specific options. 
import { voyage } from 'voyage-ai-provider';
import { embed } from 'ai';
import type { VoyageEmbeddingOptions } from 'voyage-ai-provider';

const { embedding } = await embed({
  model: voyage.textEmbeddingModel('voyage-3-lite'),
  value: 'The quick brown fox jumps over the lazy dog',
  providerOptions: {
    voyage: {
      inputType: 'query',
      truncation: true,
    } satisfies VoyageEmbeddingOptions,
  },
});

​
Provider options

You can pass Voyage-specific options through the providerOptions parameter:
​
providerOptions.voyage.inputType
'query' | 'document'
The input type for the embeddings. Defaults to "query".
  • query: Prepends “Represent the query for retrieving supporting documents: ”
  • document: Prepends “Represent the document for retrieval: ”
​
providerOptions.voyage.outputDimension
number
The number of dimensions for the resulting output embeddings.If not specified, uses the model’s default dimension.Supported values vary by model:
  • voyage-code-3: 2048, 1024 (default), 512, 256
  • voyage-3-large: 2048, 1024 (default), 512, 256
​
providerOptions.voyage.outputDtype
'float' | 'int8' | 'uint8' | 'binary' | 'ubinary'
The data type for the resulting output embeddings. Defaults to 'float'.
  • float: 32-bit single-precision floating-point numbers (supported by all models)
  • int8: 8-bit integers from -128 to 127 (supported by voyage-code-3)
  • uint8: 8-bit integers from 0 to 255 (supported by voyage-code-3)
  • binary: Bit-packed quantized values using offset binary method (supported by voyage-code-3)
  • ubinary: Bit-packed quantized values (supported by voyage-code-3)
For binary types, the returned list length is 1/8 of outputDimension.
​
providerOptions.voyage.truncation
boolean
Whether to truncate the input texts to fit within the context length.

Build docs developers (and LLMs) love

Get started for freeTalk to us