Class: TextEmbeddingsModule
Defined in: packages/react-native-executorch/src/modules/natural_language_processing/TextEmbeddingsModule.ts:12
Module for generating text embeddings from input text.
Extends
BaseModule
Constructors
Constructor
new TextEmbeddingsModule():
TextEmbeddingsModule
Returns
TextEmbeddingsModule
Inherited from
BaseModule.constructor
Properties
nativeModule
nativeModule:
any=null
Defined in: packages/react-native-executorch/src/modules/BaseModule.ts:8
Native module instance
Inherited from
BaseModule.nativeModule
Methods
delete()
delete():
void
Defined in: packages/react-native-executorch/src/modules/BaseModule.ts:41
Unloads the model from memory.
Returns
void
Inherited from
BaseModule.delete
forward()
forward(
input):Promise<Float32Array<ArrayBufferLike>>
Defined in: packages/react-native-executorch/src/modules/natural_language_processing/TextEmbeddingsModule.ts:54
Executes the model's forward pass, where input is a text that will be embedded.
Parameters
input
string
The text string to embed.
Returns
Promise<Float32Array<ArrayBufferLike>>
A Float32Array containing the vector embeddings.
forwardET()
protectedforwardET(inputTensor):Promise<TensorPtr[]>
Defined in: packages/react-native-executorch/src/modules/BaseModule.ts:23
Runs the model's forward method with the given input tensors. It returns the output tensors that mimic the structure of output from ExecuTorch.
Parameters
inputTensor
Array of input tensors.
Returns
Promise<TensorPtr[]>
Array of output tensors.
Inherited from
BaseModule.forwardET
getInputShape()
getInputShape(
methodName,index):Promise<number[]>
Defined in: packages/react-native-executorch/src/modules/BaseModule.ts:34
Gets the input shape for a given method and index.
Parameters
methodName
string
method name
index
number
index of the argument which shape is requested
Returns
Promise<number[]>
The input shape as an array of numbers.
Inherited from
BaseModule.getInputShape
load()
load(
model,onDownloadProgressCallback):Promise<void>
Defined in: packages/react-native-executorch/src/modules/natural_language_processing/TextEmbeddingsModule.ts:21
Loads the model and tokenizer specified by the config object.
Parameters
model
Object containing model and tokenizer sources.
modelSource
ResourceSource that specifies the location of the text embeddings model binary.
tokenizerSource
ResourceSource that specifies the location of the tokenizer JSON file.
onDownloadProgressCallback
(progress) => void
Optional callback to track download progress (value between 0 and 1).
Returns
Promise<void>
Overrides
BaseModule.load