kreuzberg 3.8.1__tar.gz → 3.8.2__tar.gz

kreuzberg-3.8.2/PKG-INFO

@@ -0,0 +1,265 @@
+Metadata-Version: 2.4
+Name: kreuzberg
+Version: 3.8.2
+Summary: Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats
+Project-URL: documentation, https://kreuzberg.dev
+Project-URL: homepage, https://github.com/Goldziher/kreuzberg
+Author-email: Na'aman Hirschfeld <nhirschfed@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: async,document-analysis,document-intelligence,document-processing,extensible,information-extraction,mcp,metadata-extraction,model-context-protocol,ocr,pandoc,pdf-extraction,pdfium,plugin-architecture,rag,retrieval-augmented-generation,structured-data,table-extraction,tesseract,text-extraction
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Database
+Classifier: Topic :: Multimedia :: Graphics :: Capture :: Scanners
+Classifier: Topic :: Office/Business :: Office Suites
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: General
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: anyio>=4.9.0
+Requires-Dist: chardetng-py>=0.3.4
+Requires-Dist: exceptiongroup>=1.2.2; python_version < '3.11'
+Requires-Dist: html-to-markdown[lxml]>=1.8.0
+Requires-Dist: mcp>=1.11.0
+Requires-Dist: msgspec>=0.18.0
+Requires-Dist: playa-pdf>=0.6.1
+Requires-Dist: psutil>=7.0.0
+Requires-Dist: pypdfium2==4.30.0
+Requires-Dist: python-calamine>=0.3.2
+Requires-Dist: python-pptx>=1.0.2
+Requires-Dist: typing-extensions>=4.14.0; python_version < '3.12'
+Provides-Extra: additional-extensions
+Requires-Dist: mailparse>=1.0.15; extra == 'additional-extensions'
+Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'additional-extensions'
+Provides-Extra: all
+Requires-Dist: click>=8.2.1; extra == 'all'
+Requires-Dist: easyocr>=1.7.2; extra == 'all'
+Requires-Dist: fast-langdetect>=0.3.2; extra == 'all'
+Requires-Dist: gmft>=0.4.2; extra == 'all'
+Requires-Dist: keybert>=0.9.0; extra == 'all'
+Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.16.0; extra == 'all'
+Requires-Dist: mailparse>=1.0.15; extra == 'all'
+Requires-Dist: paddleocr>=3.1.0; extra == 'all'
+Requires-Dist: paddlepaddle>=3.1.0; extra == 'all'
+Requires-Dist: rich>=14.0.0; extra == 'all'
+Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'all'
+Requires-Dist: setuptools>=80.9.0; extra == 'all'
+Requires-Dist: spacy>=3.8.7; extra == 'all'
+Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'all'
+Provides-Extra: api
+Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.16.0; extra == 'api'
+Provides-Extra: chunking
+Requires-Dist: semantic-text-splitter>=0.27.0; extra == 'chunking'
+Provides-Extra: cli
+Requires-Dist: click>=8.2.1; extra == 'cli'
+Requires-Dist: rich>=14.0.0; extra == 'cli'
+Requires-Dist: tomli>=2.0.0; (python_version < '3.11') and extra == 'cli'
+Provides-Extra: easyocr
+Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
+Provides-Extra: entity-extraction
+Requires-Dist: keybert>=0.9.0; extra == 'entity-extraction'
+Requires-Dist: spacy>=3.8.7; extra == 'entity-extraction'
+Provides-Extra: gmft
+Requires-Dist: gmft>=0.4.2; extra == 'gmft'
+Provides-Extra: langdetect
+Requires-Dist: fast-langdetect>=0.3.2; extra == 'langdetect'
+Provides-Extra: paddleocr
+Requires-Dist: paddleocr>=3.1.0; extra == 'paddleocr'
+Requires-Dist: paddlepaddle>=3.1.0; extra == 'paddleocr'
+Requires-Dist: setuptools>=80.9.0; extra == 'paddleocr'
+Description-Content-Type: text/markdown
+
+# Kreuzberg
+
+[![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
+[![PyPI version](https://badge.fury.io/py/kreuzberg.svg)](https://badge.fury.io/py/kreuzberg)
+[![Documentation](https://img.shields.io/badge/docs-kreuzberg.dev-blue)](https://kreuzberg.dev/)
+[![Benchmarks](https://img.shields.io/badge/benchmarks-fastest%20CPU-orange)](https://benchmarks.kreuzberg.dev/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Test Coverage](https://img.shields.io/badge/coverage-95%25-green)](https://github.com/Goldziher/kreuzberg)
+
+**A document intelligence framework for Python.** Extract text, metadata, and structured information from diverse document formats through a unified, extensible API. Built on established open source foundations including Pandoc, PDFium, and Tesseract.
+
+📖 **[Complete Documentation](https://kreuzberg.dev/)**
+
+## Framework Overview
+
+### Document Intelligence Capabilities
+
+- **Text Extraction**: High-fidelity text extraction preserving document structure and formatting
+- **Metadata Extraction**: Comprehensive metadata including author, creation date, language, and document properties
+- **Format Support**: 18 document types including PDF, Microsoft Office, images, HTML, and structured data formats
+- **OCR Integration**: Multiple OCR engines (Tesseract, EasyOCR, PaddleOCR) with automatic fallback
+- **Table Detection**: Structured table extraction with cell-level precision via GMFT integration
+
+### Technical Architecture
+
+- **Performance**: Highest throughput among Python document processing frameworks (30+ docs/second)
+- **Resource Efficiency**: 71MB installation, ~360MB runtime memory footprint
+- **Extensibility**: Plugin architecture for custom extractors via the Extractor base class
+- **API Design**: Synchronous and asynchronous APIs with consistent interfaces
+- **Type Safety**: Complete type annotations throughout the codebase
+
+### Open Source Foundation
+
+Kreuzberg leverages established open source technologies:
+
+- **Pandoc**: Universal document converter for robust format support
+- **PDFium**: Google's PDF rendering engine for accurate PDF processing
+- **Tesseract**: Google's OCR engine for text recognition
+- **Python-docx/pptx**: Native Microsoft Office format support
+
+## Quick Start
+
+### Extract Text with CLI
+
+```bash
+# Extract text from any file to markdown
+uvx kreuzberg extract document.pdf > output.md
+
+# With all features (OCR, table extraction, etc.)
+uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr --format markdown
+
+# Extract with rich metadata
+uvx kreuzberg extract report.pdf --show-metadata --format json
+```
+
+### Python Usage
+
+**Async (recommended for web apps):**
+
+```python
+from kreuzberg import extract_file
+
+# In your async function
+result = await extract_file("presentation.pptx")
+print(result.content)
+
+# Rich metadata extraction
+print(f"Title: {result.metadata.title}")
+print(f"Author: {result.metadata.author}")
+print(f"Page count: {result.metadata.page_count}")
+print(f"Created: {result.metadata.created_at}")
+```
+
+**Sync (for scripts and CLI tools):**
+
+```python
+from kreuzberg import extract_file_sync
+
+result = extract_file_sync("report.docx")
+print(result.content)
+
+# Access rich metadata
+print(f"Language: {result.metadata.language}")
+print(f"Word count: {result.metadata.word_count}")
+print(f"Keywords: {result.metadata.keywords}")
+```
+
+### Docker
+
+```bash
+# Run the REST API
+docker run -p 8000:8000 goldziher/kreuzberg
+
+# Extract via API
+curl -X POST -F "file=@document.pdf" http://localhost:8000/extract
+```
+
+📖 **[Installation Guide](https://kreuzberg.dev/getting-started/installation/)** • **[CLI Documentation](https://kreuzberg.dev/cli/)** • **[API Reference](https://kreuzberg.dev/api-reference/)**
+
+## Deployment Options
+
+### 🤖 MCP Server (AI Integration)
+
+**Add to Claude Desktop with one command:**
+
+```bash
+claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
+```
+
+**Or configure manually in `claude_desktop_config.json`:**
+
+```json
+{
+  "mcpServers": {
+    "kreuzberg": {
+      "command": "uvx",
+      "args": ["--from", "kreuzberg[all]", "kreuzberg-mcp"]
+    }
+  }
+}
+```
+
+**MCP capabilities:**
+
+- Extract text from PDFs, images, Office docs, and more
+- Full OCR support with multiple engines
+- Table extraction and metadata parsing
+
+📖 **[MCP Documentation](https://kreuzberg.dev/user-guide/mcp-server/)**
+
+## Supported Formats
+
+| Category          | Formats                        |
+| ----------------- | ------------------------------ |
+| **Documents**     | PDF, DOCX, DOC, RTF, TXT, EPUB |
+| **Images**        | JPG, PNG, TIFF, BMP, GIF, WEBP |
+| **Spreadsheets**  | XLSX, XLS, CSV, ODS            |
+| **Presentations** | PPTX, PPT, ODP                 |
+| **Web**           | HTML, XML, MHTML               |
+| **Archives**      | Support via extraction         |
+
+## 📊 Performance Characteristics
+
+[View comprehensive benchmarks](https://benchmarks.kreuzberg.dev/) • [Benchmark methodology](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) • [**Detailed Analysis**](https://kreuzberg.dev/performance-analysis/)
+
+### Technical Specifications
+
+| Metric                       | Kreuzberg Sync | Kreuzberg Async | Benchmarked        |
+| ---------------------------- | -------------- | --------------- | ------------------ |
+| **Throughput (tiny files)**  | 31.78 files/s  | 23.94 files/s   | Highest throughput |
+| **Throughput (small files)** | 8.91 files/s   | 9.31 files/s    | Highest throughput |
+| **Memory footprint**         | 359.8 MB       | 395.2 MB        | Lowest usage       |
+| **Installation size**        | 71 MB          | 71 MB           | Smallest size      |
+| **Success rate**             | 100%           | 100%            | Perfect            |
+| **Supported formats**        | 18             | 18              | Comprehensive      |
+
+### Architecture Advantages
+
+- **Native C extensions**: Built on PDFium and Tesseract for maximum performance
+- **Async/await support**: True asynchronous processing with intelligent task scheduling
+- **Memory efficiency**: Streaming architecture minimizes memory allocation
+- **Process pooling**: Automatic multiprocessing for CPU-intensive operations
+- **Optimized data flow**: Efficient data handling with minimal transformations
+
+> **Benchmark details**: Tests include PDFs, Word docs, HTML, images, and spreadsheets in multiple languages (English, Hebrew, German, Chinese, Japanese, Korean) on standardized hardware.
+
+## Documentation
+
+### Quick Links
+
+- [Installation Guide](https://kreuzberg.dev/getting-started/installation/) - Setup and dependencies
+- [User Guide](https://kreuzberg.dev/user-guide/) - Comprehensive usage guide
+- [Performance Analysis](https://kreuzberg.dev/performance-analysis/) - Detailed benchmark results
+- [API Reference](https://kreuzberg.dev/api-reference/) - Complete API documentation
+- [Docker Guide](https://kreuzberg.dev/user-guide/docker/) - Container deployment
+- [REST API](https://kreuzberg.dev/user-guide/api-server/) - HTTP endpoints
+- [CLI Guide](https://kreuzberg.dev/cli/) - Command-line usage
+- [OCR Configuration](https://kreuzberg.dev/user-guide/ocr-configuration/) - OCR engine setup
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.

kreuzberg-3.8.2/README.md

@@ -0,0 +1,182 @@
+# Kreuzberg
+
+[![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
+[![PyPI version](https://badge.fury.io/py/kreuzberg.svg)](https://badge.fury.io/py/kreuzberg)
+[![Documentation](https://img.shields.io/badge/docs-kreuzberg.dev-blue)](https://kreuzberg.dev/)
+[![Benchmarks](https://img.shields.io/badge/benchmarks-fastest%20CPU-orange)](https://benchmarks.kreuzberg.dev/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Test Coverage](https://img.shields.io/badge/coverage-95%25-green)](https://github.com/Goldziher/kreuzberg)
+
+**A document intelligence framework for Python.** Extract text, metadata, and structured information from diverse document formats through a unified, extensible API. Built on established open source foundations including Pandoc, PDFium, and Tesseract.
+
+📖 **[Complete Documentation](https://kreuzberg.dev/)**
+
+## Framework Overview
+
+### Document Intelligence Capabilities
+
+- **Text Extraction**: High-fidelity text extraction preserving document structure and formatting
+- **Metadata Extraction**: Comprehensive metadata including author, creation date, language, and document properties
+- **Format Support**: 18 document types including PDF, Microsoft Office, images, HTML, and structured data formats
+- **OCR Integration**: Multiple OCR engines (Tesseract, EasyOCR, PaddleOCR) with automatic fallback
+- **Table Detection**: Structured table extraction with cell-level precision via GMFT integration
+
+### Technical Architecture
+
+- **Performance**: Highest throughput among Python document processing frameworks (30+ docs/second)
+- **Resource Efficiency**: 71MB installation, ~360MB runtime memory footprint
+- **Extensibility**: Plugin architecture for custom extractors via the Extractor base class
+- **API Design**: Synchronous and asynchronous APIs with consistent interfaces
+- **Type Safety**: Complete type annotations throughout the codebase
+
+### Open Source Foundation
+
+Kreuzberg leverages established open source technologies:
+
+- **Pandoc**: Universal document converter for robust format support
+- **PDFium**: Google's PDF rendering engine for accurate PDF processing
+- **Tesseract**: Google's OCR engine for text recognition
+- **Python-docx/pptx**: Native Microsoft Office format support
+
+## Quick Start
+
+### Extract Text with CLI
+
+```bash
+# Extract text from any file to markdown
+uvx kreuzberg extract document.pdf > output.md
+
+# With all features (OCR, table extraction, etc.)
+uvx --from "kreuzberg[all]" kreuzberg extract invoice.pdf --ocr --format markdown
+
+# Extract with rich metadata
+uvx kreuzberg extract report.pdf --show-metadata --format json
+```
+
+### Python Usage
+
+**Async (recommended for web apps):**
+
+```python
+from kreuzberg import extract_file
+
+# In your async function
+result = await extract_file("presentation.pptx")
+print(result.content)
+
+# Rich metadata extraction
+print(f"Title: {result.metadata.title}")
+print(f"Author: {result.metadata.author}")
+print(f"Page count: {result.metadata.page_count}")
+print(f"Created: {result.metadata.created_at}")
+```
+
+**Sync (for scripts and CLI tools):**
+
+```python
+from kreuzberg import extract_file_sync
+
+result = extract_file_sync("report.docx")
+print(result.content)
+
+# Access rich metadata
+print(f"Language: {result.metadata.language}")
+print(f"Word count: {result.metadata.word_count}")
+print(f"Keywords: {result.metadata.keywords}")
+```
+
+### Docker
+
+```bash
+# Run the REST API
+docker run -p 8000:8000 goldziher/kreuzberg
+
+# Extract via API
+curl -X POST -F "file=@document.pdf" http://localhost:8000/extract
+```
+
+📖 **[Installation Guide](https://kreuzberg.dev/getting-started/installation/)** • **[CLI Documentation](https://kreuzberg.dev/cli/)** • **[API Reference](https://kreuzberg.dev/api-reference/)**
+
+## Deployment Options
+
+### 🤖 MCP Server (AI Integration)
+
+**Add to Claude Desktop with one command:**
+
+```bash
+claude mcp add kreuzberg uvx -- --from "kreuzberg[all]" kreuzberg-mcp
+```
+
+**Or configure manually in `claude_desktop_config.json`:**
+
+```json
+{
+  "mcpServers": {
+    "kreuzberg": {
+      "command": "uvx",
+      "args": ["--from", "kreuzberg[all]", "kreuzberg-mcp"]
+    }
+  }
+}
+```
+
+**MCP capabilities:**
+
+- Extract text from PDFs, images, Office docs, and more
+- Full OCR support with multiple engines
+- Table extraction and metadata parsing
+
+📖 **[MCP Documentation](https://kreuzberg.dev/user-guide/mcp-server/)**
+
+## Supported Formats
+
+| Category          | Formats                        |
+| ----------------- | ------------------------------ |
+| **Documents**     | PDF, DOCX, DOC, RTF, TXT, EPUB |
+| **Images**        | JPG, PNG, TIFF, BMP, GIF, WEBP |
+| **Spreadsheets**  | XLSX, XLS, CSV, ODS            |
+| **Presentations** | PPTX, PPT, ODP                 |
+| **Web**           | HTML, XML, MHTML               |
+| **Archives**      | Support via extraction         |
+
+## 📊 Performance Characteristics
+
+[View comprehensive benchmarks](https://benchmarks.kreuzberg.dev/) • [Benchmark methodology](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) • [**Detailed Analysis**](https://kreuzberg.dev/performance-analysis/)
+
+### Technical Specifications
+
+| Metric                       | Kreuzberg Sync | Kreuzberg Async | Benchmarked        |
+| ---------------------------- | -------------- | --------------- | ------------------ |
+| **Throughput (tiny files)**  | 31.78 files/s  | 23.94 files/s   | Highest throughput |
+| **Throughput (small files)** | 8.91 files/s   | 9.31 files/s    | Highest throughput |
+| **Memory footprint**         | 359.8 MB       | 395.2 MB        | Lowest usage       |
+| **Installation size**        | 71 MB          | 71 MB           | Smallest size      |
+| **Success rate**             | 100%           | 100%            | Perfect            |
+| **Supported formats**        | 18             | 18              | Comprehensive      |
+
+### Architecture Advantages
+
+- **Native C extensions**: Built on PDFium and Tesseract for maximum performance
+- **Async/await support**: True asynchronous processing with intelligent task scheduling
+- **Memory efficiency**: Streaming architecture minimizes memory allocation
+- **Process pooling**: Automatic multiprocessing for CPU-intensive operations
+- **Optimized data flow**: Efficient data handling with minimal transformations
+
+> **Benchmark details**: Tests include PDFs, Word docs, HTML, images, and spreadsheets in multiple languages (English, Hebrew, German, Chinese, Japanese, Korean) on standardized hardware.
+
+## Documentation
+
+### Quick Links
+
+- [Installation Guide](https://kreuzberg.dev/getting-started/installation/) - Setup and dependencies
+- [User Guide](https://kreuzberg.dev/user-guide/) - Comprehensive usage guide
+- [Performance Analysis](https://kreuzberg.dev/performance-analysis/) - Detailed benchmark results
+- [API Reference](https://kreuzberg.dev/api-reference/) - Complete API documentation
+- [Docker Guide](https://kreuzberg.dev/user-guide/docker/) - Container deployment
+- [REST API](https://kreuzberg.dev/user-guide/api-server/) - HTTP endpoints
+- [CLI Guide](https://kreuzberg.dev/cli/) - Command-line usage
+- [OCR Configuration](https://kreuzberg.dev/user-guide/ocr-configuration/) - OCR engine setup
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/benchmarks/benchmark_baseline.py

@@ -1,6 +1,7 @@
 """Baseline performance benchmark before implementing multi-layer caching."""
 
 import asyncio
+import json
 import time
 from pathlib import Path
 
@@ -110,8 +111,6 @@ async def run_baseline_benchmark() -> dict[str, object] | None:
 if __name__ == "__main__":
     baseline_results = asyncio.run(run_baseline_benchmark())
 
-    import json
-
     baseline_file = Path("baseline_results.json")
     with baseline_file.open("w") as f:
         json.dump(baseline_results, f, indent=2, default=str)

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/benchmarks/end_to_end_benchmark.py

@@ -1,8 +1,10 @@
 """End-to-end reproducible benchmark with proper statistics."""
 
 import asyncio
+import json
 import statistics
 import time
+from datetime import datetime
 from pathlib import Path
 from typing import Any
 
@@ -201,9 +203,6 @@ if __name__ == "__main__":
     try:
         results = asyncio.run(run_end_to_end_benchmark(trials=30))
 
-        import json
-        from datetime import datetime
-
         timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
         results_file = Path(f"benchmark_msgpack_{timestamp}.json")
 

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/benchmarks/serialization_benchmark.py

@@ -1,7 +1,8 @@
 """Direct serialization performance comparison: JSON vs msgpack."""
 
-import time
+import json
 import statistics
+import time
 from pathlib import Path
 
 from kreuzberg._types import ExtractionResult
@@ -151,8 +152,6 @@ if __name__ == "__main__":
     try:
         results = benchmark_serialization()
 
-        import json
-
         results_file = Path("serialization_benchmark_results.json")
         with results_file.open("w") as f:
             json.dump(results, f, indent=2, default=str)

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/benchmarks/src/kreuzberg_benchmarks/models.py

@@ -11,7 +11,7 @@ from typing import Any
 import psutil
 
 
-@dataclass
+@dataclass(slots=True)
 class SystemInfo:
     """System information for benchmark context."""
 
@@ -42,7 +42,7 @@ class SystemInfo:
         )
 
 
-@dataclass
+@dataclass(slots=True)
 class PerformanceMetrics:
     """Performance metrics for a single benchmark run."""
 
@@ -55,7 +55,7 @@ class PerformanceMetrics:
     exception_info: str | None = None
 
 
-@dataclass
+@dataclass(slots=True)
 class MetadataQualityMetrics:
     """Metadata quality metrics for extraction result."""
 
@@ -71,7 +71,7 @@ class MetadataQualityMetrics:
     extraction_backend: str | None = None
 
 
-@dataclass
+@dataclass(slots=True)
 class ExtractionQualityMetrics:
     """Quality metrics for extraction result."""
 
@@ -86,7 +86,7 @@ class ExtractionQualityMetrics:
     metadata_quality: MetadataQualityMetrics | None = None
 
 
-@dataclass
+@dataclass(slots=True)
 class BenchmarkResult:
     """Complete result of a single benchmark."""
 
@@ -98,7 +98,7 @@ class BenchmarkResult:
     extraction_quality: ExtractionQualityMetrics | None = None
 
 
-@dataclass
+@dataclass(slots=True)
 class BenchmarkSuite:
     """Complete benchmark suite results."""
 
@@ -193,7 +193,7 @@ class BenchmarkSuite:
         }
 
 
-@dataclass
+@dataclass(slots=True)
 class FlameGraphConfig:
     """Configuration for flame graph generation."""
 

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/benchmarks/src/kreuzberg_benchmarks/runner.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import asyncio
+import json
 import time
 import traceback
 from typing import TYPE_CHECKING, Any, Callable
@@ -392,7 +393,6 @@ class BenchmarkRunner:
 
     def save_results(self, suite: BenchmarkSuite, output_path: Path) -> None:
         """Save benchmark results to JSON file."""
-        import json
 
         output_path.parent.mkdir(parents=True, exist_ok=True)
 

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/benchmarks/statistical_benchmark.py

@@ -1,6 +1,7 @@
 """Statistical benchmark comparing JSON vs msgpack with proper error analysis."""
 
 import asyncio
+import json
 import statistics
 import time
 from pathlib import Path
@@ -194,8 +195,6 @@ if __name__ == "__main__":
     try:
         results = asyncio.run(run_statistical_benchmark())
 
-        import json
-
         results_file = Path("statistical_benchmark_results.json")
         with results_file.open("w") as f:
             json.dump(results, f, indent=2, default=str)

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/docs/advanced/custom-extractors.md

@@ -1,6 +1,6 @@
 # Custom Extractors
 
-Kreuzberg provides a flexible system for adding and removing custom extractors through the `ExtractorRegistry`. This allows you to extend Kreuzberg's capabilities to handle additional file formats or customize how existing formats are processed.
+The Kreuzberg document intelligence framework provides an extensible architecture through the `ExtractorRegistry` system. This plugin mechanism enables developers to extend document processing capabilities by implementing custom extractors for specialized formats or processing requirements.
 
 ## Creating a Custom Extractor
 

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/docs/advanced/index.md

@@ -1,6 +1,6 @@
 # Advanced Topics
 
-This section covers advanced features and usage patterns for Kreuzberg.
+This section explores advanced capabilities of the Kreuzberg document intelligence framework, including extensibility mechanisms, performance optimization, and custom integration patterns.
 
 ## Topics
 

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/docs/advanced/performance.md

@@ -16,13 +16,13 @@ Kreuzberg provides both synchronous and asynchronous APIs, each optimized for di
 
 ## Competitive Performance
 
-[Comprehensive benchmarks](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) comparing Kreuzberg against other popular Python text extraction libraries demonstrate:
+[Live benchmarks](https://benchmarks.kreuzberg.dev/) ([source code](https://github.com/Goldziher/python-text-extraction-libs-benchmarks)) demonstrate Kreuzberg as the fastest Python CPU-based text extraction framework:
 
-- **Fastest Extraction**: Consistently fastest processing times across file formats
-- **Lowest Memory Usage**: Most memory-efficient text extraction solution
-- **Smallest Installation**: 71.0 MB vs competitors ranging from 145.8 MB to 1,031.9 MB
-- **100% Success Rate**: Reliable extraction across all tested document types
-- **Optimal for High-Throughput**: Designed for real-time, production applications
+- **Leading Performance**: 31.78 files/second for small documents, 2.42 files/second for medium files
+- **Minimal Memory**: ~360MB average usage, lowest among tested frameworks
+- **Smallest Installation**: 71MB package size for maximum deployment flexibility
+- **High Reliability**: 100% success rate across all 18 tested file formats
+- **Production Optimized**: Built for high-throughput, real-time applications
 
 ## Internal Benchmark Results
 

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/docs/api-reference/index.md

@@ -1,6 +1,6 @@
 # API Reference
 
-Detailed documentation for Kreuzberg's public API.
+Complete reference documentation for the Kreuzberg document intelligence framework's public API.
 
 ## Core Components
 

{kreuzberg-3.8.1 → kreuzberg-3.8.2}/docs/getting-started/installation.md

@@ -1,12 +1,12 @@
 # Installation
 
-Kreuzberg is composed of a core package and several `optional` dependencies, which users can install at their discretion.
+Kreuzberg is a modular document intelligence framework with a core package and optional components for specialized functionality.
 
 ## System Dependencies
 
 ### Pandoc
 
-Kreuzberg relies on `pandoc`, which is a **required** system dependency. To install it, follow the instructions below:
+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