Class Docling

java.lang.Object

org.docling.Docling

public final class Docling
extends Object

A thin, embeddable Java wrapper around the docling command-line tool.

It does not reimplement conversion — it shells out to the docling executable, which must be installed and on your PATH (e.g. pip install docling).

Typical usage:

Docling docling = Docling.builder().build();
String markdown = docling.convert("path/to/file.pdf");

Instances are immutable and safe to reuse across conversions.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	Docling.Builder	Fluent builder for Docling.

Method Summary

Modifier and Type	Method	Description
static Docling.Builder	builder()	Creates a new builder with default settings (docling on the PATH, 600s timeout).
String	convert(byte[] data, String extension)	Converts in-memory document bytes to Markdown and returns it as a string.
String	convert(byte[] data, String extension, boolean removeBase64Images)	Converts in-memory document bytes to Markdown and returns it as a string.
String	convert(String source)	Converts the given source (local file path or URL) to Markdown and returns it as a string.
String	convert(String source, boolean removeBase64Images)	Converts the given source (local file path or URL) to Markdown and returns it as a string.
String	convert(Path source)	Converts a local file to Markdown and returns it as a string.
String	convert(Path source, boolean removeBase64Images)	Converts a local file to Markdown and returns it as a string.
Path	convertToDir(String source, Path outputDir)	Converts the given source to Markdown, writing the .md file into outputDir.

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Details

builder

public static Docling.Builder builder()

Creates a new builder with default settings (docling on the PATH, 600s timeout).

convert

public String convert(String source)

Converts the given source (local file path or URL) to Markdown and returns it as a string.

Parameters:

source - path or URL of the document to convert

Returns:

the generated Markdown

Throws:

DoclingException - if docling cannot be launched, times out, or exits non-zero

convert

public String convert(String source,
 boolean removeBase64Images)

Converts the given source (local file path or URL) to Markdown and returns it as a string.

Parameters:

source - path or URL of the document to convert

removeBase64Images - when true, strips images embedded as base64 data URIs from the generated Markdown (both ![...](data:image/...) and <img src="data:image/..."> forms)

Returns:

the generated Markdown

Throws:

DoclingException - if docling cannot be launched, times out, or exits non-zero

convert

public String convert(Path source)

Converts a local file to Markdown and returns it as a string.

convert

public String convert(Path source,
 boolean removeBase64Images)

Converts a local file to Markdown and returns it as a string.

Parameters:

source - path of the document to convert

removeBase64Images - when true, strips base64-embedded images from the output

convert

public String convert(byte[] data,
 String extension)

Converts in-memory document bytes to Markdown and returns it as a string.

docling infers the input format from the file extension, so an extension matching the data is required. The bytes are written to a temporary file (deleted afterwards) before being handed to docling.

Parameters:

data - the raw document bytes (e.g. the contents of a PDF or DOCX)

extension - the file extension describing the data, with or without a leading dot (e.g. "pdf", ".docx")

Returns:

the generated Markdown

Throws:

DoclingException - if docling cannot be launched, times out, or exits non-zero

convert

public String convert(byte[] data,
 String extension,
 boolean removeBase64Images)

Converts in-memory document bytes to Markdown and returns it as a string.

docling infers the input format from the file extension, so an extension matching the data is required. The bytes are written to a temporary file (deleted afterwards) before being handed to docling.

Parameters:

data - the raw document bytes (e.g. the contents of a PDF or DOCX)

extension - the file extension describing the data, with or without a leading dot (e.g. "pdf", ".docx")

removeBase64Images - when true, strips base64-embedded images from the output

Returns:

the generated Markdown

Throws:

DoclingException - if docling cannot be launched, times out, or exits non-zero

convertToDir

public Path convertToDir(String source,
 Path outputDir)

Converts the given source to Markdown, writing the .md file into outputDir.

Parameters:

source - path or URL of the document to convert

outputDir - directory the Markdown file is written to (created if missing)

Returns:

the path of the generated Markdown file

Throws:

DoclingException - if docling cannot be launched, times out, or exits non-zero