I am using deep java library and i want to implement reranking on retrieved documents for my chatbot implementation.

cross encoders are used to find similarity score between 2 strings

Below is the code that generates text embeddings using all-MiniLM-L6-v2 but i want to use it for cross encoding.

package ai.djl.examples.inference.nlp;
import ai.djl.ModelException;
import ai.djl.huggingface.translator.TextEmbeddingTranslatorFactory;
import ai.djl.huggingface.translator.CrossEncoderTranslator;
import ai.djl.inference.Predictor;
import ai.djl.repository.zoo.Criteria;
import ai.djl.repository.zoo.ZooModel;
import ai.djl.training.util.ProgressBar;
import ai.djl.translate.TranslateException;

import java.io.IOException;
import java.util.Arrays;

public class TextEmbedding {

    private TextEmbedding() {}

    public static void main(String[] args) throws IOException, ModelException, TranslateException {
        String text = "This is an example sentence";

        Criteria<String, float[]> criteria =
                Criteria.builder()
                        .setTypes(String.class, float[].class)
                        .optModelUrls(
                                "djl://ai.djl.huggingface.pytorch/sentence-transformers/all-MiniLM-L6-v2")
                        .optEngine("PyTorch")
                        .optTranslatorFactory(new TextEmbeddingTranslatorFactory())
                        .optProgress(new ProgressBar())
                        .build();

        try (ZooModel<String, float[]> model = criteria.loadModel();
             Predictor<String, float[]> predictor = model.newPredictor()) {
            float[] res = predictor.predict(text);
            System.out.println("Embedding: " + Arrays.toString(res));
        }
    }
}

Would really appreciate any help!

I am looking for a code that outputs similarity score for a pair of given input sequences.