Kreuzberg

A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 56 formats. Available for Rust, Python, TypeScript/Node.js, Ruby, Go, Java, and C#—or use via CLI, REST API, or MCP server.

🚀 Version 4.0.0 Release Candidate This is a pre-release version. We invite you to test the library and report any issues you encounter. Help us make the stable release better!

Why Kreuzberg

• Truly polyglot – Native bindings for Rust, Python, TypeScript/Node.js, Ruby, Go, Java, C#
• Production-ready – Battle-tested with comprehensive error handling and validation
• 56 formats – PDF, Office documents, images, HTML, XML, emails, archives, and more
• OCR built-in – Multiple backends (Tesseract, EasyOCR, PaddleOCR) with table extraction support
• Flexible deployment – Use as library, CLI tool, REST API server, or MCP server
• Memory efficient – Streaming parsers with constant memory usage for multi-GB files

📖 Complete Documentation • 🚀 Installation Guides

Kreuzberg Cloud (Coming Soon)

Don't want to manage Rust infrastructure? Kreuzberg Cloud is a managed document extraction API launching soon.

• REST API with async jobs and webhooks
• Built-in chunking and embeddings for RAG pipelines
• Premium OCR backends for 95%+ accuracy
• No infrastructure to maintain

Join the waitlist →

Installation

Python

pip install kreuzberg

Python Documentation →

Ruby

gem install kreuzberg

Ruby Documentation →

TypeScript/Node.js

npm install kreuzberg

TypeScript/Node.js Documentation →

Go

go get github.com/Goldziher/kreuzberg/packages/go/kreuzberg@latest

Build the FFI crate (cargo build -p kreuzberg-ffi --release) and set LD_LIBRARY_PATH/DYLD_FALLBACK_LIBRARY_PATH to target/release so cgo can locate libkreuzberg_ffi.

Go Documentation →

Java

<dependency>
    <groupId>dev.kreuzberg</groupId>
    <artifactId>kreuzberg</artifactId>
    <version>4.0.0-rc.1</version>
</dependency>

Or with Gradle:

implementation 'dev.kreuzberg:kreuzberg:4.0.0-rc.1'

Requires Java 25+ with Foreign Function & Memory API (Panama). Build the FFI crate (cargo build -p kreuzberg-ffi --release) for native library access.

Java Documentation →

C#

dotnet add package Goldziher.Kreuzberg --version 4.0.0-rc.1

Requires .NET 10.0+. Build the FFI crate (cargo build -p kreuzberg-ffi --release) and ensure the native library is accessible.

C# Documentation →

Rust

[dependencies]
# Use git dependency for full feature support (including embeddings)
kreuzberg = { git = "https://github.com/Goldziher/kreuzberg", tag = "v4.0.0" }

# Or use a specific branch
# kreuzberg = { git = "https://github.com/Goldziher/kreuzberg", branch = "main" }

Rust Documentation →

CLI

brew install goldziher/tap/kreuzberg

cargo install kreuzberg-cli

CLI Documentation →

Quick Start

Each language binding provides comprehensive documentation with examples and best practices. Choose your platform to get started:

• Python Quick Start → – Installation, basic usage, async/sync APIs
• Ruby Quick Start → – Installation, basic usage, configuration
• TypeScript/Node.js Quick Start → – Installation, types, promises
• Go Quick Start → – Installation, native library setup, sync/async extraction + batch APIs
• Java Quick Start → – Installation, FFM API usage, Maven/Gradle setup
• C# Quick Start → – Installation, P/Invoke usage, NuGet package
• Rust Quick Start → – Crate usage, features, async/sync APIs
• CLI Quick Start → – Command-line usage, batch processing, options

Supported Formats

Documents & Productivity

Format	Extensions	Metadata	Tables	Images
PDF	.pdf	✅	✅	✅
Word	.docx, .doc	✅	✅	✅
Excel	.xlsx, .xls, .ods	✅	✅	❌
PowerPoint	.pptx, .ppt	✅	✅	✅
Rich Text	.rtf	✅	❌	❌
EPUB	.epub	✅	❌	❌

Images

All image formats support OCR: .jpg, .jpeg, .png, .tiff, .tif, .bmp, .gif, .webp, .jp2

Web & Structured Data

Format	Extensions	Features
HTML	.html, .htm	Metadata extraction, link preservation
XML	.xml	Streaming parser for multi-GB files
JSON	.json	Intelligent field detection
YAML	.yaml	Structure preservation
TOML	.toml	Configuration parsing

Email & Archives

Format	Extensions	Features
Email	.eml, .msg	Full metadata, attachment extraction
Archives	.zip, .tar, .gz, .7z	File listing, metadata

Academic & Technical

LaTeX (.tex), BibTeX (.bib), Jupyter (.ipynb), reStructuredText (.rst), Org Mode (.org), Markdown (.md)

Complete Format Documentation

Key Features

OCR with Table Extraction

Multiple OCR backends (Tesseract, EasyOCR, PaddleOCR) with intelligent table detection and reconstruction. Extract structured data from scanned documents and images with configurable accuracy thresholds.

OCR Backend Documentation →

Batch Processing

Process multiple documents concurrently with configurable parallelism. Optimize throughput for large-scale document processing workloads with automatic resource management.

Batch Processing Guide →

Password-Protected PDFs

Handle encrypted PDFs with single or multiple password attempts. Supports both RC4 and AES encryption with automatic fallback strategies.

PDF Configuration →

Language Detection

Automatic language detection in extracted text using fast-langdetect. Configure confidence thresholds and access per-language statistics.

Language Detection Guide →

Metadata Extraction

Extract comprehensive metadata from all supported formats: authors, titles, creation dates, page counts, EXIF data, and format-specific properties.

Metadata Guide →

Deployment Options

REST API Server

Production-ready API server with OpenAPI documentation, health checks, and telemetry support. Deploy standalone or in containers with automatic format detection and streaming support.

API Server Documentation →

MCP Server (AI Integration)

Model Context Protocol server for Claude and other AI assistants. Enables AI agents to extract and process documents directly with full configuration support.

MCP Server Documentation →

Docker

Official Docker images available in multiple variants:

• Core (~1.0-1.3GB): Tesseract OCR, Pandoc, modern Office formats
• Full (~1.5-2.1GB): Adds LibreOffice for legacy Office formats (.doc, .ppt)

All images support API server, CLI, and MCP server modes with automatic platform detection for linux/amd64 and linux/arm64.

Docker Deployment Guide →

Comparison with Alternatives

Feature	Kreuzberg	docling	unstructured	LlamaParse
Formats	56	PDF, DOCX	30+	PDF only
Self-hosted	✅ Yes (MIT)	✅ Yes	✅ Yes	❌ API only
Programming Languages	Rust, Python, Ruby, TS, Java, Go, C#	Python	Python	API (any)
Table Extraction	✅ Good	✅ Good	✅ Basic	✅ Excellent
OCR	✅ Multiple backends	✅ Yes	✅ Yes	✅ Yes
Embeddings	✅ Built-in	❌ No	❌ No	❌ No
Chunking	✅ Built-in	❌ No	✅ Yes	❌ No
Cost	Free (MIT)	Free (MIT)	Free (Apache 2.0)	$0.003/page
Air-gap deployments	✅ Yes	✅ Yes	✅ Yes	❌ No

When to use Kreuzberg:

• ✅ Need high throughput (thousands of documents)
• ✅ Memory-constrained environments
• ✅ Non-Python ecosystems (Ruby, TypeScript, Java, Go)
• ✅ RAG pipelines (built-in chunking + embeddings)
• ✅ Self-hosted or air-gapped deployments
• ✅ Multi-GB files requiring streaming

When to consider alternatives:

• LlamaParse: If you need best-in-class table extraction and only process PDFs (requires internet, paid)
• docling: If you're Python-only and don't need extreme performance
• unstructured: If you need extensive pre-built integrations with vector databases

Architecture

Kreuzberg is built with a Rust core for efficient document extraction and processing.

Design Principles

• Rust core – Native code for text extraction and processing
• Async throughout – Asynchronous processing with Tokio runtime
• Memory efficient – Streaming parsers for large files
• Parallel batch processing – Configurable concurrency for multiple documents
• Zero-copy operations – Efficient data handling where possible

Documentation

• Installation Guide – Setup and dependencies
• User Guide – Comprehensive usage guide
• API Reference – Complete API documentation
• Format Support – Supported file formats
• OCR Backends – OCR engine setup
• CLI Guide – Command-line usage
• Migration Guide – Upgrading from v3

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

License

MIT License - see LICENSE for details.