Embeddings

Embeddings are a way to represent words, phrases, or images as vectors in a high-dimensional space. In this space, similar words are close to each other, and the distance between words can be used to measure their similarity.

Embedding a Single Value

The AI SDK provides the embed function to embed single values, which is useful for tasks such as finding similar words or phrases or clustering text. You can use it with embeddings models, e.g. openai.embeddingModel('text-embedding-3-large') or mistral.embeddingModel('mistral-embed').

import { embed } from 'ai';

// 'embedding' is a single embedding object (number[])
const { embedding } = await embed({
  model: 'openai/text-embedding-3-small',
  value: 'sunny day at the beach',
});

Embedding Many Values

When loading data, e.g. when preparing a data store for retrieval-augmented generation (RAG), it is often useful to embed many values at once (batch embedding).

The AI SDK provides the embedMany function for this purpose. Similar to embed, you can use it with embeddings models, e.g. openai.embeddingModel('text-embedding-3-large') or mistral.embeddingModel('mistral-embed').

import { embedMany } from 'ai';

// 'embeddings' is an array of embedding objects (number[][]).
// It is sorted in the same order as the input values.
const { embeddings } = await embedMany({
  model: 'openai/text-embedding-3-small',
  values: [
    'sunny day at the beach',
    'rainy afternoon in the city',
    'snowy night in the mountains',
  ],
});

Embedding Similarity

After embedding values, you can calculate the similarity between them using the cosineSimilarity function. This is useful to e.g. find similar words or phrases in a dataset. You can also rank and filter related items based on their similarity.

import { cosineSimilarity, embedMany } from 'ai';

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

console.log(
  `cosine similarity: ${cosineSimilarity(embeddings[0], embeddings[1])}`,
);

Token Usage

Many providers charge based on the number of tokens used to generate embeddings. Both embed and embedMany provide token usage information in the usage property of the result object:

import { embed } from 'ai';

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

console.log(usage); // { tokens: 10 }

Settings

Output Dimensions

Both embed and embedMany accept an optional dimensions parameter to request an output vector size. It must be a positive integer. When omitted, the model's existing behavior is unchanged. For embedMany, the same value is forwarded to every batch.

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

const { embedding } = await embed({
  model: openai.embedding('text-embedding-3-small'),
  value: 'sunny day at the beach',
  dimensions: 512,
});

Providers map dimensions to their native output dimension setting. An explicit dimension setting in providerOptions takes precedence over dimensions. Other provider options can be combined with the top-level setting.

Support and allowed dimension values depend on the model. The SDK forwards the requested size to the provider API without truncating or resizing the returned embeddings. AI Gateway forwards dimensions and providerOptions for resolution by the selected provider.

Provider Options

Embedding model settings can be configured using providerOptions for provider-specific parameters:

import { embed } from 'ai';

const { embedding } = await embed({
  model: 'openai/text-embedding-3-small',
  value: 'sunny day at the beach',
  providerOptions: {
    openai: {
      dimensions: 512, // Reduce embedding dimensions
    },
  },
});

Google's gemini-embedding-2 model (also available as gemini-embedding-2-preview) supports multimodal embedding content through providerOptions.google.content. Each entry corresponds to the value at the same index and can contain { text: string }, { inlineData: { mimeType: string; data: string } }, or { fileData: { fileUri: string; mimeType: string } } parts. fileUri can reference remote content such as HTTP URLs or Google Cloud Storage URIs (gs://...).

Parallel Requests

The embedMany function now supports parallel processing with configurable maxParallelCalls to optimize performance:

import { embedMany } from 'ai';

const { embeddings, usage } = await embedMany({
  maxParallelCalls: 2, // Limit parallel requests
  model: 'openai/text-embedding-3-small',
  values: [
    'sunny day at the beach',
    'rainy afternoon in the city',
    'snowy night in the mountains',
  ],
});

Retries

Both embed and embedMany accept an optional maxRetries parameter of type number that you can use to set the maximum number of retries for the embedding process. It defaults to 2 retries (3 attempts in total). You can set it to 0 to disable retries.

import { embed } from 'ai';

const { embedding } = await embed({
  model: 'openai/text-embedding-3-small',
  value: 'sunny day at the beach',
  maxRetries: 0, // Disable retries
});

Abort Signals and Timeouts

Both embed and embedMany accept an optional abortSignal parameter of type AbortSignal that you can use to abort the embedding process or set a timeout.

import { embed } from 'ai';

const { embedding } = await embed({
  model: 'openai/text-embedding-3-small',
  value: 'sunny day at the beach',
  abortSignal: AbortSignal.timeout(1000), // Abort after 1 second
});

Custom Headers

Both embed and embedMany accept an optional headers parameter of type Record<string, string> that you can use to add custom headers to the embedding request.

import { embed } from 'ai';

const { embedding } = await embed({
  model: 'openai/text-embedding-3-small',
  value: 'sunny day at the beach',
  headers: { 'X-Custom-Header': 'custom-value' },
});

Response Information

Both embed and embedMany return response information that includes the raw provider response:

import { embed } from 'ai';

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

console.log(response); // Raw provider response

Embedding Middleware

You can enhance embedding models, e.g. to set default values, using wrapEmbeddingModel and EmbeddingModelMiddleware.

Here is an example that uses the built-in defaultEmbeddingSettingsMiddleware:

import {
  defaultEmbeddingSettingsMiddleware,
  embed,
  wrapEmbeddingModel,
  gateway,
} from 'ai';

const embeddingModelWithDefaults = wrapEmbeddingModel({
  model: gateway.embeddingModel('google/gemini-embedding-001'),
  middleware: defaultEmbeddingSettingsMiddleware({
    settings: {
      providerOptions: {
        google: {
          outputDimensionality: 256,
          taskType: 'CLASSIFICATION',
        },
      },
    },
  }),
});

Embedding Providers & Models

Several providers offer embedding models: