Package opennlp.dl.vectors

Class SentenceVectorsDL

java.lang.Object

opennlp.dl.AbstractDL

opennlp.dl.vectors.SentenceVectorsDL

All Implemented Interfaces:

AutoCloseable

@ThreadSafe
public class SentenceVectorsDL
extends AbstractDL

Facilitates the generation of sentence vectors using a sentence-transformers model converted to ONNX.

The model inputs follow the standard single-segment BERT encoding: attention_mask is 1 for every real token and token_type_ids is 0 throughout.

Release note (OpenNLP 3.0.0): prior releases sent an all-zero attention_mask and all-one token_type_ids, so the encoder attended to nothing and the output vectors were incorrect. Additionally, tokenization now performs BERT basic tokenization (lower casing and accent stripping by default, see BertTokenizer) before wordpiece. Output vectors change with the corrected encoding and tokenization; any embeddings persisted from the previous behavior are not comparable with the corrected output and must be re-embedded.

This class is thread-safe and may be shared across threads: getVectors(String) holds no per-call instance state and the underlying OrtSession supports concurrent execution. This thread-safety guarantee applies until AbstractDL.close() is called; callers must not race close() with inference methods.

Field Summary

Fields inherited from class opennlp.dl.AbstractDL

ATTENTION_MASK, INPUT_IDS, TOKEN_TYPE_IDS

Constructor Summary

Constructors

Constructor	Description
SentenceVectorsDL(File model, File vocabulary)	Instantiates a sentence vector generator for an uncased model.
SentenceVectorsDL(File model, File vocabulary, boolean lowerCase)	Instantiates a sentence vector generator using ONNX models.

Method Summary

Modifier and Type	Method	Description
float[]	getVectors(String sentence)	Generates vectors given a sentence.

Methods inherited from class opennlp.dl.AbstractDL

close, loadVocab

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

SentenceVectorsDL

public SentenceVectorsDL(File model,
 File vocabulary)
                  throws ai.onnxruntime.OrtException,
IOException

Instantiates a sentence vector generator for an uncased model. Input text is lower cased and accent stripped during tokenization, as required by uncased models such as the sentence-transformers MiniLM family.

Parameters:

model - The file name of a sentence vectors ONNX model.

vocabulary - The file name of the vocabulary file for the model.

Throws:

ai.onnxruntime.OrtException - Thrown if the model cannot be loaded.

IOException - Thrown if errors occurred loading the model or vocabulary.

SentenceVectorsDL

public SentenceVectorsDL(File model,
 File vocabulary,
 boolean lowerCase)
                  throws ai.onnxruntime.OrtException,
IOException

Instantiates a sentence vector generator using ONNX models.

Parameters:

model - The file name of a sentence vectors ONNX model.

vocabulary - The file name of the vocabulary file for the model.

lowerCase - true for uncased models (lower casing and accent stripping during tokenization), false for cased models.

Throws:

ai.onnxruntime.OrtException - Thrown if the model cannot be loaded.

IOException - Thrown if errors occurred loading the model or vocabulary.

Method Details

getVectors

public float[] getVectors(String sentence)
                   throws ai.onnxruntime.OrtException

Generates vectors given a sentence.

Parameters:

sentence - The input sentence.

Returns:

The sentence vector.

Throws:

ai.onnxruntime.OrtException - Thrown if an error occurs during inference.