ai.djl.huggingface.translator.TextEmbeddingTranslatorFactory Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of tokenizers Show documentation
Deep Java Library (DJL) NLP utilities for Huggingface tokenizers
The newest version!
/*
 * Copyright 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
 *
 * Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
 * with the License. A copy of the License is located at
 *
 * http://aws.amazon.com/apache2.0/
 *
 * or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES
 * OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
 * and limitations under the License.
 */
package ai.djl.huggingface.translator;

import ai.djl.Model;
import ai.djl.huggingface.tokenizers.HuggingFaceTokenizer;
import ai.djl.modality.Input;
import ai.djl.modality.Output;
import ai.djl.modality.nlp.translator.CrossEncoderServingTranslator;
import ai.djl.modality.nlp.translator.TextEmbeddingServingTranslator;
import ai.djl.translate.ArgumentsUtil;
import ai.djl.translate.TranslateException;
import ai.djl.translate.Translator;
import ai.djl.translate.TranslatorFactory;
import ai.djl.util.Pair;
import ai.djl.util.StringPair;

import java.io.IOException;
import java.io.Serializable;
import java.lang.reflect.Type;
import java.nio.file.Path;
import java.util.HashSet;
import java.util.Map;
import java.util.Set;

/** A {@link TranslatorFactory} that creates a {@link TextEmbeddingTranslator} instance. */
public class TextEmbeddingTranslatorFactory implements TranslatorFactory, Serializable {

    private static final long serialVersionUID = 1L;

    private static final Set> SUPPORTED_TYPES = new HashSet<>();

    static {
        SUPPORTED_TYPES.add(new Pair<>(String.class, float[].class));
        SUPPORTED_TYPES.add(new Pair<>(StringPair.class, float[].class));
        SUPPORTED_TYPES.add(new Pair<>(Input.class, Output.class));
    }

    /** {@inheritDoc} */
    @Override
    public Set> getSupportedTypes() {
        return SUPPORTED_TYPES;
    }

    /** {@inheritDoc} */
    @Override
    @SuppressWarnings("unchecked")
    public  Translator newInstance(
            Class input, Class output, Model model, Map arguments)
            throws TranslateException {
        Path modelPath = model.getModelPath();
        try {
            HuggingFaceTokenizer tokenizer =
                    HuggingFaceTokenizer.builder(arguments)
                            .optTokenizerPath(modelPath)
                            .optManager(model.getNDManager())
                            .build();
            if (ArgumentsUtil.booleanValue(arguments, "reranking")) {
                CrossEncoderTranslator translator =
                        CrossEncoderTranslator.builder(tokenizer, arguments).build();
                if (input == StringPair.class && output == float[].class) {
                    return (Translator) translator;
                } else if (input == Input.class && output == Output.class) {
                    return (Translator) new CrossEncoderServingTranslator(translator);
                }
                throw new IllegalArgumentException("Unsupported input/output types.");
            }

            TextEmbeddingTranslator translator =
                    TextEmbeddingTranslator.builder(tokenizer, arguments).build();
            if (input == String.class && output == float[].class) {
                return (Translator) translator;
            } else if (input == Input.class && output == Output.class) {
                return (Translator) new TextEmbeddingServingTranslator(translator);
            }
            throw new IllegalArgumentException("Unsupported input/output types.");
        } catch (IOException e) {
            throw new TranslateException("Failed to load tokenizer.", e);
        }
    }
}