Installation¶

Kreuzberg is a modular document intelligence framework with a core package and optional components for specialized functionality.

System Dependencies¶

Pandoc¶

Pandoc is the foundation of Kreuzberg's universal document conversion capabilities. This required system dependency enables reliable extraction across diverse document formats. Install Pandoc for your platform:

Ubuntu/Debian¶

1

sudo apt-get install pandoc

macOS¶

1

brew install pandoc

Windows¶

1

choco install -y pandoc

Kreuzberg Core Package¶

The Kreuzberg core package can be installed using pip with:

1

pip install kreuzberg

Optional Features¶

OCR¶

OCR is an optional feature for extracting text from images and non-searchable PDFs. Kreuzberg supports multiple OCR backends. To understand the differences between these backends, please read the OCR Configuration documentation.

Tesseract OCR¶

Tesseract OCR is built into Kreuzberg and doesn't require additional Python packages. However, you must install Tesseract 5.0 or higher on your system:

Ubuntu/Debian¶

1

sudo apt-get install tesseract-ocr

macOS¶

1

brew install tesseract

Windows¶

1

choco install -y tesseract

1
2
3
4
5
6

# For German language support on Windows
$tessDataDir = "C:\Program Files\Tesseract-OCR\tessdata"
Invoke-WebRequest -Uri "https://github.com/tesseract-ocr/tessdata/raw/main/deu.traineddata" -OutFile "$tessDataDir\deu.traineddata"

# Verify installation
tesseract --list-langs

EasyOCR¶

EasyOCR is a Python-based OCR backend with wide language support and strong performance.

1

pip install "kreuzberg[easyocr]"

PaddleOCR¶

PaddleOCR is particularly strong for Chinese and other Asian languages. It requires additional system dependencies for OpenCV support:

System Dependencies¶

1
2
3
4
5
6

# Ubuntu/Debian
sudo apt-get install libgl1 libglib2.0-0

# macOS
# OpenGL is typically included; if needed:
brew install glfw

OpenGL libraries are typically included with graphics drivers on Windows.

Python Package¶

1

pip install "kreuzberg[paddleocr]"

Chunking¶

Chunking is an optional feature - useful for RAG applications among others. Kreuzberg uses the excellent semantic-text-splitter package for chunking. To install Kreuzberg with chunking support, you can use:

1

pip install "kreuzberg[chunking]"

Table Extraction¶

If you need to keep using the legacy GMFT integration in the current series, install the extra explicitly:

1

pip install "kreuzberg[gmft]"

GMFTConfig will emit a FutureWarning whenever it is instantiated to remind you to migrate. Plan to switch to the new table extraction configuration before upgrading to v4.0.

Language Detection¶

Language detection is an optional feature that automatically detects the language of extracted text. It uses the fast-langdetect package. To install Kreuzberg with language detection support, you can use:

1

pip install "kreuzberg[langdetect]"

Document Classification¶

For automatic document type detection (invoice, contract, receipt, etc.), install the document classification extra:

1

pip install "kreuzberg[document-classification]"

This feature uses Google Translate for multi-language support and requires explicit opt-in by setting auto_detect_document_type=True in your configuration.

All Optional Dependencies¶

To install Kreuzberg with all optional dependencies, you can use the all extra group:

1

pip install "kreuzberg[all]"

This is equivalent to:

1

pip install "kreuzberg[api,chunking,cli,crypto,document-classification,easyocr,entity-extraction,gmft,langdetect,paddleocr,additional-extensions]"

Development Setup¶

For development and testing, additional system dependencies and language packs are required:

Required System Dependencies¶

1
2
3
4
5
6
7
8
9

# Ubuntu/Debian
sudo apt-get install tesseract-ocr tesseract-ocr-deu pandoc

# macOS
brew install tesseract tesseract-lang pandoc

# Windows
choco install -y tesseract pandoc
# Then install German language pack as shown above

Testing Requirements¶

The test suite includes OCR tests with German language documents that require the deu (German) language pack for Tesseract. Ensure the German language pack is installed as described in the Language Support section above.

To verify your development setup:

1
2
3
4
5
6

# Verify Tesseract has German support
tesseract --list-langs | grep deu

# Run the test suite
uv sync --all-extras --all-groups
uv run pytest