Crate kreuzberg 

Kreuzberg - High-Performance Document Intelligence Library

Kreuzberg is a Rust-first document extraction library with language-agnostic plugin support. It provides fast, accurate extraction from PDFs, images, Office documents, emails, and more.

Quick Start

use kreuzberg::{extract_file_sync, ExtractionConfig};

// Extract content from a file
let config = ExtractionConfig::default();
let result = extract_file_sync("document.pdf", None, &config)?;
println!("Extracted: {}", result.content);

Architecture

• Core Module (core): Main extraction orchestration, MIME detection, config loading
• Plugin System: Language-agnostic plugin architecture
• Extractors: Format-specific extraction (PDF, images, Office docs, email, etc.)
• OCR: Multiple OCR backend support (Tesseract, EasyOCR, PaddleOCR)

Features

• Fast parallel processing with async/await
• Priority-based extractor selection
• Comprehensive MIME type detection (118+ file extensions)
• Configurable caching and quality processing
• Cross-language plugin support (Python, Node.js planned)

Re-exports

pub use error::KreuzbergError;

pub use error::Result;

pub use core::extractor::batch_extract_bytes;

pub use core::extractor::batch_extract_file;

pub use core::extractor::extract_bytes;

pub use core::extractor::extract_file;

pub use core::extractor::batch_extract_bytes_sync;

pub use core::extractor::extract_bytes_sync;

pub use core::extractor::batch_extract_file_sync;

pub use core::extractor::extract_file_sync;

pub use core::config::AccelerationConfig;

pub use core::config::ChunkSizing;

pub use core::config::ChunkerType;

pub use core::config::ChunkingConfig;

pub use core::config::EmailConfig;

pub use core::config::EmbeddingConfig;

pub use core::config::EmbeddingModelType;

pub use core::config::ExecutionProviderType;

pub use core::config::ExtractionConfig;

pub use core::config::FileExtractionConfig;

pub use core::config::ImageExtractionConfig;

pub use core::config::LanguageDetectionConfig;

pub use core::config::OcrConfig;

pub use core::config::OutputFormat;

pub use core::config::PageConfig;

pub use core::config::PostProcessorConfig;

pub use core::config::TokenReductionConfig;

pub use core::mime::DOCX_MIME_TYPE;

pub use core::mime::EXCEL_MIME_TYPE;

pub use core::mime::HTML_MIME_TYPE;

pub use core::mime::JSON_MIME_TYPE;

pub use core::mime::MARKDOWN_MIME_TYPE;

pub use core::mime::PDF_MIME_TYPE;

pub use core::mime::PLAIN_TEXT_MIME_TYPE;

pub use core::mime::POWER_POINT_MIME_TYPE;

pub use core::mime::SupportedFormat;

pub use core::mime::XML_MIME_TYPE;

pub use core::mime::detect_mime_type;

pub use core::mime::detect_mime_type_from_bytes;

pub use core::mime::detect_or_validate;

pub use core::mime::get_extensions_for_mime;

pub use core::mime::list_supported_formats;

pub use core::mime::validate_mime_type;

pub use core::formats::KNOWN_FORMATS;

pub use core::formats::is_valid_format_field;

pub use plugins::registry::get_document_extractor_registry;

pub use plugins::registry::get_ocr_backend_registry;

pub use plugins::registry::get_post_processor_registry;

pub use plugins::registry::get_validator_registry;

pub use types::*;

Modules

cache

Generic cache implementation with lock poisoning recovery.

core

Core extraction orchestration module.

error

Error types for Kreuzberg.

extraction

extractors

Built-in document extractors.

model_cache

Generic global model cache for ONNX-based models.

panic_context

plugins

Plugin system for extending Kreuzberg functionality.

rendering

Unified rendering of DocumentStructure to output formats.

text

types

Core types for document extraction.

utils

Text utility functions for quality processing and string manipulation.