This version is still in development and is not considered stable yet. For the latest stable version, please use Spring AI 2.1.0!

PDF Document Readers

PDF Page

The PagePdfDocumentReader uses Apache PdfBox library to parse PDF documents.

Dependencies

Add the dependency to your project using Maven or Gradle.

  • Maven

  • Gradle

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-pdf-document-reader</artifactId>
</dependency>
dependencies {
    implementation 'org.springframework.ai:spring-ai-pdf-document-reader'
}

Example

@Component
public class MyPagePdfDocumentReader {

	List<Document> getDocsFromPdf() {

		PagePdfDocumentReader pdfReader = new PagePdfDocumentReader("classpath:/sample1.pdf",
				PdfDocumentReaderConfig.builder()
					.withPageTopMargin(0)
					.withPageExtractedTextFormatter(ExtractedTextFormatter.builder()
						.withNumberOfTopTextLinesToDelete(0)
						.build())
					.withPagesPerDocument(1)
					.build());

		return pdfReader.read();
    }

}

Configuration

PdfDocumentReaderConfig.builder() provides the following options:

  • withPagesPerDocument(int): the number of pages to put into one Document (default 1). 0 (PdfDocumentReaderConfig.ALL_PAGES) puts all pages into a single Document.

  • withPageTopMargin(int) and withPageBottomMargin(int): the height, in points (1/72 inch), to leave out at the top and at the bottom of each page, for example to drop headers and footers (default 0).

  • addPageRange(int startPage, int endPage): reads only the pages of the inclusive, one-based range. Call it several times to read several ranges; with no range, the whole document is read. An end page beyond the last page is clamped to the last page. A Document never spans pages outside the ranges, so with disjoint ranges pagesPerDocument is a maximum.

  • withPageExtractedTextFormatter(ExtractedTextFormatter): post-processes the text of each page. ExtractedTextFormatter.builder() can delete text lines at the top and bottom of a page (withNumberOfTopTextLinesToDelete, withNumberOfBottomTextLinesToDelete, withNumberOfTopPagesToSkipBeforeDelete), align the text to the left (withLeftAlignment) and set the line separator (overrideLineSeparator).

  • withReversedParagraphPosition(boolean): kept in the configuration, but neither reader uses it.

PagePdfDocumentReader pdfReader = new PagePdfDocumentReader("classpath:/sample1.pdf",
        PdfDocumentReaderConfig.builder()
            .addPageRange(3, 10)       // skip the cover and the table of contents
            .addPageRange(15, 20)
            .withPageBottomMargin(50)  // leave out the footer
            .build());

PDF Paragraph

The ParagraphPdfDocumentReader uses the PDF catalog (e.g. TOC) information to split the input PDF into text paragraphs and output a single Document per paragraph.

Not all PDF documents contain the PDF catalog.

The ParagraphPdfDocumentReader uses only the text formatter of the configuration. It ignores the margins and pagesPerDocument, and it rejects a configuration with page ranges with an IllegalArgumentException.

Dependencies

Add the dependency to your project using Maven or Gradle.

  • Maven

  • Gradle

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-pdf-document-reader</artifactId>
</dependency>
dependencies {
    implementation 'org.springframework.ai:spring-ai-pdf-document-reader'
}

Example

@Component
public class MyPagePdfDocumentReader {

	List<Document> getDocsFromPdfWithCatalog() {

        ParagraphPdfDocumentReader pdfReader = new ParagraphPdfDocumentReader("classpath:/sample1.pdf",
                PdfDocumentReaderConfig.builder()
                    .withPageTopMargin(0)
                    .withPageExtractedTextFormatter(ExtractedTextFormatter.builder()
                        .withNumberOfTopTextLinesToDelete(0)
                        .build())
                    .withPagesPerDocument(1)
                    .build());

	    return pdfReader.read();
    }
}