> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/firebase/genkit/llms.txt
> Use this file to discover all available pages before exploring further.
# Embedders API
> API reference for embedders in Genkit (JavaScript/TypeScript)
Embedders convert text and documents into vector embeddings for semantic search and retrieval.
## defineEmbedder()
Defines and registers an embedder.
```typescript theme={null}
import { defineEmbedder } from '@genkit-ai/ai';
import { z } from 'zod';
const myEmbedder = defineEmbedder(
registry,
{
name: 'myEmbedder',
configSchema: z.object({
dimensions: z.number().optional(),
}),
info: {
label: 'My Custom Embedder',
dimensions: 768,
supports: {
input: ['text'],
},
},
},
async (input, options) => {
// Generate embeddings for each document
const embeddings = input.map(doc => ({
embedding: generateEmbedding(doc.text()),
}));
return { embeddings };
}
);
```
### Parameters
The Genkit registry instance
Embedder configuration
Unique name for the embedder
Zod schema for embedder-specific configuration options
Metadata about the embedder's capabilities
Human-readable label for the embedder
Embedding vector dimension size
Supported input types
Whether the embedder supports multiple languages
Implementation function
**Function signature:**
```typescript theme={null}
(input: Document[], options?: z.infer) => Promise
```
### Returns
An embedder action that can be used with `embed()`
## embed()
Generates embeddings for text or documents.
```typescript theme={null}
import { embed } from '@genkit-ai/ai';
const embeddings = await embed(registry, {
embedder: 'myEmbedder',
content: 'Hello, world!',
});
console.log(embeddings[0].embedding); // [0.123, 0.456, ...]
```
### Parameters
The Genkit registry instance
Embedding request parameters
Embedder to use (string name, EmbedderAction, or EmbedderReference)
Text or document to embed
Metadata to attach to the document
Embedder-specific configuration options
### Returns
Array of embedding objects
```typescript theme={null}
{
embedding: number[]; // Vector representation
metadata?: Record;
}
```
## embedMany()
Generates embeddings for multiple documents in a batch.
```typescript theme={null}
import { embedMany } from '@genkit-ai/ai';
const embeddings = await embedMany(registry, {
embedder: 'myEmbedder',
content: ['First document', 'Second document', 'Third document'],
});
console.log(embeddings.length); // 3
```
### Parameters
The Genkit registry instance
Embedder to use
Array of texts or documents to embed
Metadata to attach to all documents
Embedder-specific options
### Returns
Batch of embeddings
```typescript theme={null}
type EmbeddingBatch = { embedding: number[] }[];
```
## embedderRef()
Creates a reference to an embedder with configuration.
```typescript theme={null}
import { embedderRef } from '@genkit-ai/ai';
import { z } from 'zod';
const myEmbedderRef = embedderRef({
name: 'myEmbedder',
config: { dimensions: 512 },
info: {
label: 'My Embedder',
dimensions: 512,
},
});
// Use the reference
const embeddings = await embed(registry, {
embedder: myEmbedderRef,
content: 'Hello',
});
```
### Parameters
Embedder name
Configuration schema
Embedder metadata
Configuration values
Embedder version
Optional namespace prefix
### Returns
An embedder reference that can be passed to `embed()`
## Types
### EmbedRequest
```typescript theme={null}
interface EmbedRequest {
input: Document[];
options?: O;
}
```
### EmbedResponse
```typescript theme={null}
interface EmbedResponse {
embeddings: Embedding[];
}
```
### Embedding
```typescript theme={null}
interface Embedding {
embedding: number[];
metadata?: Record;
}
```
### EmbedderAction
```typescript theme={null}
type EmbedderAction =
Action & {
__configSchema?: CustomOptions;
};
```
## Example: Custom Embedder
```typescript theme={null}
import { ai } from './genkit';
import { Document } from '@genkit-ai/ai';
import { z } from 'zod';
const customEmbedder = ai.defineEmbedder(
{
name: 'custom/embedder',
configSchema: z.object({
model: z.string().default('base'),
batchSize: z.number().default(32),
}),
info: {
label: 'Custom Embedder',
dimensions: 768,
supports: {
input: ['text'],
multilingual: false,
},
},
},
async (documents, options) => {
const embeddings = [];
// Process in batches
for (let i = 0; i < documents.length; i += options.batchSize) {
const batch = documents.slice(i, i + options.batchSize);
const batchEmbeddings = await generateEmbeddingsBatch(
batch.map(d => d.text()),
options.model
);
embeddings.push(...batchEmbeddings);
}
return {
embeddings: embeddings.map((embedding, i) => ({
embedding,
metadata: documents[i].metadata,
})),
};
}
);
// Use the embedder
const result = await ai.embed({
embedder: customEmbedder,
content: 'Sample text to embed',
});
```