langchain4j+Tika小试牛刀

最新推荐文章于 2025-09-11 09:57:31 发布

原创

最新推荐文章于 2025-09-11 09:57:31 发布 · 559 阅读

6 ·

CC 4.0 BY-SA版权

文章标签：

#人工智能

序

本文主要研究一下langchain4j结合Apache Tika进行文档解析

步骤

pom.xml

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-document-parser-apache-tika</artifactId>
            <version>1.0.0-beta1</version>
        </dependency>

example

public class TikaTest {

    public static void main(String[] args) {
        String path = System.getProperty("user.home") + "/downloads/tmp.xlsx";
        DocumentParser parser = new ApacheTikaDocumentParser();
        Document document = FileSystemDocumentLoader.loadDocument(path, parser);
        log.info("textSegment:{}", document.toTextSegment());
        log.info("meta data:{}", document.metadata().toMap());
        log.info("text:{}", document.text());
    }
}

指定好了文件路径，通过ApacheTikaDocumentParser来解析，最后统一返回Document对象，它可以返回textSegment，这个可以跟向量数据库结合在一起

			EmbeddingModel embeddingModel = new AllMiniLmL6V2EmbeddingModel();
            TextSegment segment1 = document.toTextSegment();
            Embedding embedding1 = embeddingModel.embed(segment1).content();
            embeddingStore.add(embedding1, segment1);

源码

DocumentParser

dev/langchain4j/data/document/DocumentParser.java

public interface DocumentParser {

    /**
     * Parses a given {@link InputStream} into a {@link Document}.
     * The specific implementation of this method will depend on the type of the document being parsed.
     * <p>
     * Note: This method does not close the provided {@link InputStream} - it is the
     * caller's responsibility to manage the lifecycle of the stream.
     *
     * @param inputStream The {@link InputStream} that contains the content of the {@link Document}.
     * @return The parsed {@link Document}.
     * @throws BlankDocumentException when the parsed {@link Document} is blank/empty.
     */