Skip to main content
Embeds a single value using an embedding model. 
import { embed } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await embed({
  model: openai.embedding('text-embedding-3-small'),
  value: 'sunny day at the beach',
});

console.log(result.embedding);

​
Parameters

​
model
EmbeddingModel
required
The embedding model to use.
​
value
string
required
The value that should be embedded.
​
maxRetries
number
default:"2"
Maximum number of retries per embedding model call. Set to 0 to disable retries.
​
abortSignal
AbortSignal
Abort signal for canceling the embedding request.
​
headers
Record<string, string>
Additional headers to include in the request. Only applicable for HTTP-based providers.
​
providerOptions
ProviderOptions
Additional provider-specific options. They are passed through to the provider from the AI SDK and enable provider-specific functionality that can be fully encapsulated in the provider.
​
experimental_telemetry
TelemetrySettings
Optional telemetry configuration (experimental).

​
Returns

​
value
string
The value that was embedded.
​
embedding
number[]
The embedding vector as an array of numbers.
​
usage
{ tokens: number }
The token usage for the embedding operation.
​
warnings
Array<CallWarning>
Warnings from the embedding model provider (e.g., unsupported settings).
​
providerMetadata
ProviderMetadata
Additional provider-specific metadata.
​
response
EmbeddingModelResponseMetadata
Response metadata from the embedding model.

​
Examples

​
Basic embedding

import { embed } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await embed({
  model: openai.embedding('text-embedding-3-small'),
  value: 'sunny day at the beach',
});

console.log(result.embedding);
// [0.123, -0.456, 0.789, ...]

​
With usage tracking

import { embed } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await embed({
  model: openai.embedding('text-embedding-3-small'),
  value: 'sunny day at the beach',
});

console.log('Tokens used:', result.usage.tokens);
console.log('Embedding dimensions:', result.embedding.length);

​
Multiple embeddings

For embedding multiple values efficiently, use embedMany instead: 
import { embedMany } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await embedMany({
  model: openai.embedding('text-embedding-3-small'),
  values: [
    'sunny day at the beach',
    'rainy day in the mountains',
    'snowy day in the city',
  ],
});

console.log(result.embeddings);