langchain4j+PDFBox小试牛刀

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

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

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

public class ApachePdfBoxDocumentParser implements DocumentParser {

    private final boolean includeMetadata;

    public ApachePdfBoxDocumentParser() {
        this(false);
    }

    public ApachePdfBoxDocumentParser(boolean includeMetadata) {
        this.includeMetadata = includeMetadata;
    }

    @Override
    public Document parse(InputStream inputStream) {
        try (PDDocument pdfDocument = PDDocument.load(inputStream)) {
            PDFTextStripper stripper = new PDFTextStripper();
            String text = stripper.getText(pdfDocument);
            if (isNullOrBlank(text)) {
                throw new BlankDocumentException();
            }
            return includeMetadata
                    ? Document.from(text, toMetadata(pdfDocument))
                    : Document.from(text);
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }

    private Metadata toMetadata(PDDocument pdDocument) {
        PDDocumentInformation documentInformation = pdDocument.getDocumentInformation();
        Metadata metadata = new Metadata();
        for (String metadataKey : documentInformation.getMetadataKeys()) {
            String value = documentInformation.getCustomMetadataValue(metadataKey);
            if (value != null) metadata.put(metadataKey, value);
        }
        return metadata;
    }
}