# EmbeddingModel

## Overview

EmbeddingModel provides methods to generate embeddings for text and manage embedding stores. It supports in-memory and Servoy (pgvector) embedding stores.

## Methods Summarized

| Type                                                                                                        | Name                                                                      | Summary                                                                                  |
| ----------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| [EmbeddingStore](/reference/servoyextensions/server-plugins/ai/embeddingstore.md)                           | [createInMemoryStore()](#createinmemorystore)                             | Creates an in-memory embedding store for storing and retrieving embeddings.              |
| [ServoyEmbeddingStoreBuilder](/reference/servoyextensions/server-plugins/ai/servoyembeddingstorebuilder.md) | [createServoyEmbeddingStoreBuilder()](#createservoyembeddingstorebuilder) | Creates a builder for servoy embedding stores.                                           |
| [Array](/reference/servoycore/dev-api/js-lib/array.md)                                                      | [embedding(text)](#embedding-text)                                        | Generates an embedding for a single text string this can be used to use in the foundset. |
| [Promise](/reference/servoycore/dev-api/js-lib/promise.md)                                                  | [embedding(texts)](#embedding-texts)                                      | Generates embeddings for an array of text strings asynchronously.                        |
| [Number](/reference/servoycore/dev-api/js-lib/number.md)                                                    | [getDimension()](#getdimension)                                           | Gets the dimension of the embeddings produced by the model.                              |

## Methods Detailed

### createInMemoryStore()

Creates an in-memory embedding store for storing and retrieving embeddings.

**Returns:** [EmbeddingStore](/reference/servoyextensions/server-plugins/ai/embeddingstore.md) An EmbeddingStore backed by an in-memory store.

### createServoyEmbeddingStoreBuilder()

Creates a builder for servoy embedding stores.

**Returns:** [ServoyEmbeddingStoreBuilder](/reference/servoyextensions/server-plugins/ai/servoyembeddingstorebuilder.md) ServoyEmbeddingStoreBuilder instance.

### embedding(text)

Generates an embedding for a single text string this can be used to use in the foundset.sort(vectorColumn, embeddingModel.embed("text"), maxRows);

**Parameters**

* [String](/reference/servoycore/dev-api/js-lib/string.md) **text** The text string to create embeddings for.

**Returns:** [Array](/reference/servoycore/dev-api/js-lib/array.md) The embedding as a float array, or null if input is empty.

### embedding(texts)

Generates embeddings for an array of text strings asynchronously.

**Parameters**

* [Array](/reference/servoycore/dev-api/js-lib/array.md) **texts** The array of text strings to embed.

**Returns:** [Promise](/reference/servoycore/dev-api/js-lib/promise.md) A Promise resolving to a float array of embeddings, or null if input\
is empty.

### getDimension()

Gets the dimension of the embeddings produced by the model. This can be used when createing a vector column in a database, to use as the "size" of the vector.

**Returns:** [Number](/reference/servoycore/dev-api/js-lib/number.md) The embeddings model dimension.

***


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.servoy.com/reference/servoyextensions/server-plugins/ai/embeddingmodel.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.