Type Alias: TextEmbedder

TextEmbedder = object

Defined in: extensions/nlp/tasks/textEmbedding.ts:40

Text embedding task runner.

Properties

dispose()

readonly dispose: () => void

Defined in: extensions/nlp/tasks/textEmbedding.ts:44

Releases all allocated native resources.

Returns

void

---

embed()

readonly embed: (input, prompt?) => Promise<Float32Array>

Defined in: extensions/nlp/tasks/textEmbedding.ts:57

Asynchronously computes the embedding vector for the given input text. Inputs longer than the model's maximum sequence length are truncated.

Parameters

input

string

The input text to embed.

prompt?

string

Optional prompt prefix overriding the model's configured TextEmbedderModel.defaultPrompt for this call.

Returns

Promise<Float32Array>

A promise resolving to the embedding vector.

Throws

With code INVALID_ARGUMENT if the input text tokenizes to zero tokens, RESOURCE_BUSY if the model is in use, or RESOURCE_DISPOSED if disposed.

---

embedWorklet()

readonly embedWorklet: (input, prompt?) => Float32Array

Defined in: extensions/nlp/tasks/textEmbedding.ts:63

Synchronous version of embed to be executed directly on the caller or worklet thread.

Parameters

input

string

prompt?

string

Returns

Float32Array