Kreuzberg

npm install @kreuzberg/node

Rust

# Cargo.toml
[dependencies]
kreuzberg = { version = "4", features = ["tokio-runtime"] }
# features: tokio-runtime (required for sync + batch), pdf, ocr, chunking,
#           embeddings, language-detection, keywords-yake, keywords-rake

CLI

# Download from GitHub releases, or:
cargo install kreuzberg-cli

Quick Start

Python (Async)

from kreuzberg import extract_file

result = await extract_file("document.pdf")
print(result.content)       # extracted text
print(result.metadata)      # document metadata
print(result.tables)        # extracted tables

Python (Sync)

from kreuzberg import extract_file_sync

result = extract_file_sync("document.pdf")
print(result.content)

Node.js

import { extractFile } from '@kreuzberg/node';

const result = await extractFile('document.pdf');
console.log(result.content);
console.log(result.metadata);
console.log(result.tables);

Node.js (Sync)

import { extractFileSync } from '@kreuzberg/node';

const result = extractFileSync('document.pdf');

Rust (Async)

use kreuzberg::{extract_file, ExtractionConfig};

#[tokio::main]
async fn main() -> kreuzberg::Result<()> {
    let config = ExtractionConfig::default();
    let result = extract_file("document.pdf", None, &config).await?;
    println!("{}", result.content);
    Ok(())
}

Rust (Sync) — requires tokio-runtime feature

use kreuzberg::{extract_file_sync, ExtractionConfig};

fn main() -> kreuzberg::Result<()> {
    let config = ExtractionConfig::default();
    let result = extract_file_sync("document.pdf", None, &config)?;
    println!("{}", result.content);
    Ok(())
}

CLI

kreuzberg extract document.pdf
kreuzberg extract document.pdf --format json
kreuzberg extract document.pdf --output-format markdown

Configuration

All languages use the same configuration structure with language-appropriate naming conventions.

Python (snake_case)

from kreuzberg import (
    ExtractionConfig, OcrConfig, TesseractConfig,
    PdfConfig, ChunkingConfig,
)

config = ExtractionConfig(
    ocr=OcrConfig(
        backend="tesseract",
        language="eng",
        tesseract_config=TesseractConfig(psm=6, enable_table_detection=True),
    ),
    pdf_options=PdfConfig(passwords=["secret123"]),
    chunking=ChunkingConfig(max_chars=1000, max_overlap=200),
    output_format="markdown",
)

result = await extract_file("document.pdf", config=config)

Node.js (camelCase)

import { extractFile, type ExtractionConfig } from '@kreuzberg/node';

const config: ExtractionConfig = {
    ocr: { backend: 'tesseract', language: 'eng' },
    pdfOptions: { passwords: ['secret123'] },
    chunking: { maxChars: 1000, maxOverlap: 200 },
    outputFormat: 'markdown',
};

const result = await extractFile('document.pdf', null, config);

Rust (snake_case)

use kreuzberg::{ExtractionConfig, OcrConfig, ChunkingConfig, OutputFormat};

let config = ExtractionConfig {
    ocr: Some(OcrConfig {
        backend: "tesseract".into(),
        language: "eng".into(),
        ..Default::default()
    }),
    chunking: Some(ChunkingConfig {
        max_characters: 1000,
        overlap: 200,
        ..Default::default()
    }),
    output_format: OutputFormat::Markdown,
    ..Default::default()
};

let result = extract_file("document.pdf", None, &config).await?;

Config File (TOML)

output_format = "markdown"

[ocr]
backend = "tesseract"
language = "eng"

[chunking]
max_chars = 1000
max_overlap = 200

[pdf_options]
passwords = ["secret123"]

# CLI: auto-discovers kreuzberg.toml in current/parent directories
kreuzberg extract doc.pdf
# or explicit:
kreuzberg extract doc.pdf --config kreuzberg.toml
kreuzberg extract doc.pdf --config-json '{"ocr":{"backend":"tesseract","language":"deu"}}'

Batch Processing

Python

from kreuzberg import batch_extract_files, batch_extract_files_sync

# Async
results = await batch_extract_files(["doc1.pdf", "doc2.docx", "doc3.xlsx"])

# Sync
results = batch_extract_files_sync(["doc1.pdf", "doc2.docx"])

for result in results:
    print(f"{len(result.content)} chars extracted")

Node.js

import { batchExtractFiles } from '@kreuzberg/node';

const results = await batchExtractFiles(['doc1.pdf', 'doc2.docx']);

Rust — requires tokio-runtime feature

use kreuzberg::{batch_extract_file, ExtractionConfig};

let config = ExtractionConfig::default();
let paths = vec!["doc1.pdf", "doc2.docx"];
let results = batch_extract_file(paths, &config).await?;

CLI

kreuzberg batch *.pdf --format json
kreuzberg batch docs/*.docx --output-format markdown

OCR

OCR runs automatically for images and scanned PDFs. Tesseract is the default backend (native binding, no external install required).

Backends

• Tesseract (default): Built-in native binding. All Tesseract languages supported.
• EasyOCR (Python only): pip install kreuzberg[easyocr]. Pass easyocr_kwargs={"gpu": True}.
• PaddleOCR (Python only): Bundled since 4.8.5, no extra install needed. Pass paddleocr_kwargs={"use_angle_cls": True}.
• Guten (Node.js only): Built-in OCR backend via GutenOcrBackend.

Language Codes

config = ExtractionConfig(ocr=OcrConfig(language="eng"))       # English
config = ExtractionConfig(ocr=OcrConfig(language="eng+deu"))   # Multiple
config = ExtractionConfig(ocr=OcrConfig(language="all"))       # All installed

Force OCR

config = ExtractionConfig(force_ocr=True)  # OCR even if text is extractable

ExtractionResult Fields

Error Handling

Python

from kreuzberg import (
    extract_file_sync, KreuzbergError, ParsingError,
    OCRError, ValidationError, MissingDependencyError,
)