TextEmbedder

public final class TextEmbedder

Performs embedding extraction on text.

This API expects a TFLite model with (optional) TFLite Model Metadata.

Metadata is required for models with int32 input tensors because it contains the input process unit for the model's Tokenizer. No metadata is required for models with string input tensors.

• Input tensors
  • Three input tensors (kTfLiteInt32) of shape [batch_size x bert_max_seq_len] representing the input ids, mask ids, and segment ids. This input signature requires a Bert Tokenizer process unit in the model metadata.
  • Or one input tensor (kTfLiteInt32) of shape [batch_size x max_seq_len] representing the input ids. This input signature requires a Regex Tokenizer process unit in the model metadata.
  • Or one input tensor (kTfLiteString) that is shapeless or has shape [1] containing the input string.
• At least one output tensor (kTfLiteFloat32/kTfLiteUint8) with shape [1 x N] where N is the number of dimensions in the produced embeddings.

Nested Classes

class

TextEmbedder.TextEmbedderOptions

Options for setting up a TextEmbedder.

Public Methods

void	close() Closes and cleans up the TextEmbedder.
static double	cosineSimilarity(Embedding u, Embedding v) Utility function to compute cosine similarity between two Embedding objects.
static TextEmbedder	createFromFile(Context context, String modelPath) Creates a TextEmbedder instance from a model file and the default TextEmbedder.TextEmbedderOptions.
static TextEmbedder	createFromFile(Context context, File modelFile) Creates a TextEmbedder instance from a model file and the default TextEmbedder.TextEmbedderOptions.
static TextEmbedder	createFromOptions(Context context, TextEmbedder.TextEmbedderOptions options) Creates a TextEmbedder instance from TextEmbedder.TextEmbedderOptions.
TextEmbedderResult	embed(String inputText) Performs embedding extraction on the input text.

Inherited Methods

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

From interface java.lang.AutoCloseable

abstract void

close()

Public Methods

public void close ()

Closes and cleans up the TextEmbedder.

public static double cosineSimilarity (Embedding u, Embedding v)

Utility function to compute cosine similarity between two Embedding objects.

Parameters

u
v

Throws

IllegalArgumentException	if the embeddings are of different types (float vs. quantized), have different sizes, or have an L2-norm of 0.

public static TextEmbedder createFromFile (Context context, String modelPath)

Creates a TextEmbedder instance from a model file and the default TextEmbedder.TextEmbedderOptions.

Parameters

context	an Android ERROR(/Context).
modelPath	path to the text model with metadata in the assets.

Throws

	if there is is an error during TextEmbedder creation.

public static TextEmbedder createFromFile (Context context, File modelFile)

Creates a TextEmbedder instance from a model file and the default TextEmbedder.TextEmbedderOptions.

Parameters

context	an Android ERROR(/Context).
modelFile	the text model File instance.

Throws

IOException	if an I/O error occurs when opening the tflite model file.
	if there is an error during TextEmbedder creation.

public static TextEmbedder createFromOptions (Context context, TextEmbedder.TextEmbedderOptions options)

Creates a TextEmbedder instance from TextEmbedder.TextEmbedderOptions.

Parameters

context	an Android ERROR(/Context).
options	a TextEmbedder.TextEmbedderOptions instance.

Throws

	if there is an error during TextEmbedder creation.

public TextEmbedderResult embed (String inputText)

Performs embedding extraction on the input text.

Parameters

inputText	a String for processing.