kreuzberg 3.3.0__py3-none-any.whl → 3.8.1__py3-none-any.whl

kreuzberg-3.8.1.dist-info/METADATA

@@ -0,0 +1,301 @@
+Metadata-Version: 2.4
+Name: kreuzberg
+Version: 3.8.1
+Summary: Advanced document intelligence framework for extracting structured content from PDFs, images, and office documents
+Project-URL: homepage, https://github.com/Goldziher/kreuzberg
+Author-email: Na'aman Hirschfeld <nhirschfed@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: automation,content-extraction,data-processing,document-analysis,document-intelligence,document-processing,entity-extraction,image-to-text,information-extraction,ocr,pdf-extraction,rag,structured-data,table-extraction,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-GitHub_Pages-blue)](https://goldziher.github.io/kreuzberg/)
+[![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)
+
+**Advanced Document Intelligence for Modern Python Applications.** Transform PDFs, images, and office documents into structured data with production-grade performance. Built by engineers who understand that speed, reliability, and developer experience matter.
+
+📖 **[Complete Documentation](https://goldziher.github.io/kreuzberg/)**
+
+## Why Choose Kreuzberg?
+
+### ⚡ Proven Performance
+
+[Benchmarked](https://goldziher.github.io/python-text-extraction-libs-benchmarks/) 6-126x faster than alternatives while using minimal resources. Process up to 14 files per second with 87MB install size and ~360MB memory usage. Optimized for production workloads and resource-constrained environments.
+
+### 🏗️ Production Engineering
+
+Comprehensive test coverage (95%+), robust error handling, and true async/await support. Built with modern Python practices for reliability in production environments.
+
+### 🔧 Developer Experience
+
+Works immediately with smart defaults, scales as you grow. Native MCP integration for AI tools, full type safety, and clear documentation.
+
+### 🚀 Flexible Deployment
+
+Deploy on serverless platforms, containers, or traditional servers. Supports both CPU and GPU processing (via PaddleOCR and EasyOCR). No external API dependencies. Multiple deployment modes: CLI, REST API, MCP server.
+
+### 📄 Comprehensive Format Support
+
+Extract from PDFs, images, Office documents, HTML, spreadsheets, and presentations. Multiple OCR engines with intelligent fallbacks, table extraction, and content preparation for RAG workflows.
+
+## Quick Start
+
+### Installation
+
+```bash
+# Basic installation
+pip install kreuzberg
+
+# With optional features
+pip install "kreuzberg[cli,api]"        # CLI + REST API
+pip install "kreuzberg[easyocr,gmft]"   # EasyOCR + table extraction
+pip install "kreuzberg[all]"            # Everything
+```
+
+### System Dependencies
+
+```bash
+# Ubuntu/Debian
+sudo apt-get install tesseract-ocr pandoc
+
+# macOS
+brew install tesseract pandoc
+
+# Windows
+choco install tesseract pandoc
+```
+
+### Basic Usage
+
+```python
+import asyncio
+from kreuzberg import extract_file
+
+async def main():
+    # Extract content from files
+    result = await extract_file("document.pdf")
+    print(result.content)
+    print(result.metadata)
+
+asyncio.run(main())
+```
+
+## Deployment Options
+
+### 🤖 MCP Server (AI Integration)
+
+**Connect directly to Claude Desktop, Cursor, and other AI tools with the Model Context Protocol:**
+
+```bash
+# Install and run MCP server with all features (recommended)
+pip install "kreuzberg[all]"
+kreuzberg-mcp
+
+# Or with uvx (recommended for Claude Desktop)
+uvx --with "kreuzberg[all]" kreuzberg-mcp
+
+# Basic installation (core features only)
+pip install kreuzberg
+kreuzberg-mcp
+```
+
+**Configure in Claude Desktop (`claude_desktop_config.json`):**
+
+```json
+{
+  "mcpServers": {
+    "kreuzberg": {
+      "command": "uvx",
+      "args": ["--with", "kreuzberg[all]", "kreuzberg-mcp"]
+    }
+  }
+}
+```
+
+**Basic configuration (core features only):**
+
+```json
+{
+  "mcpServers": {
+    "kreuzberg": {
+      "command": "uvx",
+      "args": ["kreuzberg-mcp"]
+    }
+  }
+}
+```
+
+**Available MCP capabilities:**
+
+- **Tools**: `extract_document`, `extract_bytes`, `extract_simple`
+- **Resources**: Configuration, supported formats, OCR backends
+- **Prompts**: Extract-and-summarize, structured analysis workflows
+
+### 🐳 Docker (Recommended)
+
+```bash
+# Run API server
+docker run -p 8000:8000 goldziher/kreuzberg:latest
+
+# Extract files
+curl -X POST http://localhost:8000/extract -F "data=@document.pdf"
+```
+
+Available variants: `latest`, `v3.8.0`, `v3.8.0-easyocr`, `v3.8.0-paddle`, `v3.8.0-gmft`, `v3.8.0-all`
+
+### 🌐 REST API
+
+```bash
+# Install and run
+pip install "kreuzberg[api]"
+litestar --app kreuzberg._api.main:app run
+
+# Health check
+curl http://localhost:8000/health
+
+# Extract files
+curl -X POST http://localhost:8000/extract -F "data=@file.pdf"
+```
+
+### 💻 Command Line
+
+```bash
+# Install CLI
+pip install "kreuzberg[cli]"
+
+# Extract to stdout
+kreuzberg extract document.pdf
+
+# JSON output with metadata
+kreuzberg extract document.pdf --output-format json --show-metadata
+
+# Batch processing
+kreuzberg extract *.pdf --output-dir ./extracted/
+```
+
+## 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 Comparison
+
+[Comprehensive benchmarks](https://goldziher.github.io/python-text-extraction-libs-benchmarks/) across ~100 real-world documents • [View source](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) • [**Detailed Analysis**](https://goldziher.github.io/kreuzberg/performance-analysis/):
+
+| Framework     | Speed        | Memory | Install Size | Dependencies | Success Rate |
+| ------------- | ------------ | ------ | ------------ | ------------ | ------------ |
+| **Kreuzberg** | 14.4 files/s | 360MB  | 87MB         | 43           | 100%         |
+| Unstructured  | ~12 files/s  | ~1GB   | 146MB        | 54           | 88%+         |
+| MarkItDown    | ~15 files/s  | ~1.5GB | 251MB        | 25           | 80%\*        |
+| Docling       | ~1 file/min  | ~5GB   | 1,032MB      | 88           | 45%\*        |
+
+\*_Performance varies significantly with document complexity and size_
+
+**Key strengths:**
+
+- 6-126x faster processing than comparable frameworks
+- Smallest installation footprint and memory usage
+- Only framework with built-in async/await support
+- Supports both CPU and GPU processing
+- Built by software engineers for production reliability
+
+> **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://goldziher.github.io/kreuzberg/getting-started/installation/) - Setup and dependencies
+- [User Guide](https://goldziher.github.io/kreuzberg/user-guide/) - Comprehensive usage guide
+- [Performance Analysis](https://goldziher.github.io/kreuzberg/performance-analysis/) - Detailed benchmark results
+- [API Reference](https://goldziher.github.io/kreuzberg/api-reference/) - Complete API documentation
+- [Docker Guide](https://goldziher.github.io/kreuzberg/user-guide/docker/) - Container deployment
+- [REST API](https://goldziher.github.io/kreuzberg/user-guide/api-server/) - HTTP endpoints
+- [CLI Guide](https://goldziher.github.io/kreuzberg/cli/) - Command-line usage
+- [OCR Configuration](https://goldziher.github.io/kreuzberg/user-guide/ocr-configuration/) - OCR engine setup
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.

kreuzberg-3.8.1.dist-info/RECORD

@@ -0,0 +1,53 @@
+kreuzberg/__init__.py,sha256=wVxbug-w1cO2xHcP04Bf6QeIKmT2Ep6aeenb8EOYLA0,1534
+kreuzberg/__main__.py,sha256=s2qM1nPEkRHAQP-G3P7sf5l6qA_KJeIEHS5LpPz04lg,183
+kreuzberg/_chunker.py,sha256=2eHSRHcZdJ2ZjR3in49y3o9tPl5HMO3vkbnMqaVCbHI,1887
+kreuzberg/_cli_config.py,sha256=WD_seFjbuay_NJv77vGLBW6BVV9WZNujdzf3zQkhzPc,5691
+kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
+kreuzberg/_entity_extraction.py,sha256=nqpQPmR2Rf1vOwoQsjm22nPLDIcsXdYfMwCL3h8iUTQ,7802
+kreuzberg/_gmft.py,sha256=Heovj2n2kgi7eHtvvRzpBgSLGyXjz8M9PAQMX-npd40,25295
+kreuzberg/_language_detection.py,sha256=22-uXoOu_ws0K8Hz2M7U_SF9QX3npRYLhntAE1dNLFU,3283
+kreuzberg/_mime_types.py,sha256=OhJ6gEyyLHjyvRtkk37zyLFBsRcSd_QybBaV8TxinIg,8471
+kreuzberg/_playa.py,sha256=rU6ii2Qnrj8tkDYlSiab5h-BCYLJnUg4QwSLVDEXF5g,11883
+kreuzberg/_registry.py,sha256=wGSlkS0U1zqruWQCLE95vj4a2mw1yyvf0j6rgz80sJg,3473
+kreuzberg/_types.py,sha256=R_0Xc2kq4nEwkruvkB3qfrLeJ996419hBQ_1C6Xrqjo,13388
+kreuzberg/cli.py,sha256=H9xxh4-zhGLfbhya2iD-NcEs-BvajVttm6cSiNx3ANU,12452
+kreuzberg/exceptions.py,sha256=xRaiJh11i8E6Nc-gAQPgNW5xvhiiFBhRS-CBbCEbHQM,2881
+kreuzberg/extraction.py,sha256=hY5d4oelwocX6eOBF0Bu3nHCcCbTL5JOIbaPCCFNKsU,16972
+kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/main.py,sha256=kZCMPPzP4BGzEege9pdhQTJPKKVjCaC6kZdMMeaqP2M,2599
+kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_extractors/_base.py,sha256=yNVQSECFad-8_MjqpQZ4q0jQoNdzP6-tqw6l3TfgsMc,4418
+kreuzberg/_extractors/_email.py,sha256=6-Mk1TRXPyy9ylWKCpgdrogyzhiFnJOTuTRld1ghO8I,5695
+kreuzberg/_extractors/_html.py,sha256=lOM1Tgrrvd7vpEeFAxC1dp0Tibr6N2FEHCjgFx0FK64,1745
+kreuzberg/_extractors/_image.py,sha256=eZ7mR4F-mTwYwUzd70xrY7SZYZrNiDxnP5bYDY5P75U,4455
+kreuzberg/_extractors/_pandoc.py,sha256=51k7XISfKaPorhapG7aIeQb94KGsfozxKyT2rwhk9Bk,26553
+kreuzberg/_extractors/_pdf.py,sha256=Deb1ZIcqDY18CHa7cJL4vO4S7gy09yXWNSuH7O7kSzY,16430
+kreuzberg/_extractors/_presentation.py,sha256=CUlqZl_QCdJdumsZh0BpROkFbvi9uq7yMoIt3bRTUeE,10859
+kreuzberg/_extractors/_spread_sheet.py,sha256=Nvyz7XT7C2ai4QeUashBeENQpuP5rs8SmKfumxEqlCg,13712
+kreuzberg/_extractors/_structured.py,sha256=i3jAvhHZt_BsRGgZZfgcsUqlwAg_RNc8vsuecb04T0c,5581
+kreuzberg/_mcp/__init__.py,sha256=8PYV-omC8Rln7Cove8C3rHu3d7sR1FuiwSBG1O7vkAE,92
+kreuzberg/_mcp/server.py,sha256=BQHeKI89aKf24BIE4n6m8r1rVA1Zgt6vM8Ki_OHuGnc,6780
+kreuzberg/_ocr/__init__.py,sha256=grshVFwVQl2rMvH1hg1JNlYXjy5-Tdb_rusLD1Cselk,706
+kreuzberg/_ocr/_base.py,sha256=CUzYMsJjCqCmHzWckmDeIB2L5hd261xrPrK8Ql-Gdm0,3876
+kreuzberg/_ocr/_easyocr.py,sha256=sWyVnF7My4F1GU-IPSVtpaDJPYogw8N-NYxwuy-6loc,17098
+kreuzberg/_ocr/_paddleocr.py,sha256=nXfQq6t2a7O-IpbCZRv8BvzP_lEBLgyYwXI5-wjzec0,17480
+kreuzberg/_ocr/_tesseract.py,sha256=RjJ_C8c74LmLN53sdDo8WPCpUYeJ6fmRwsQdp6dJYio,31490
+kreuzberg/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_utils/_cache.py,sha256=6T2K9BXWaPkEKphSFrfXtFFE7ck5q9CYV9NmAFS56e4,15204
+kreuzberg/_utils/_device.py,sha256=rnaSSB5ibf2wr7EDxrcmOUZ4Ocor0pHkwb3N1pC46EY,10276
+kreuzberg/_utils/_document_cache.py,sha256=z8irioKsOu8xve1YgHatm__wIFvs9I1gDK3tLNsNyqM,6926
+kreuzberg/_utils/_errors.py,sha256=4OseKJI5qscD9jHxpP8CtpPWNHAOdhrJwcg6dlQl2fk,6310
+kreuzberg/_utils/_pdf_lock.py,sha256=nqxAYCNlfWDrJtP4ZNu57st1YnkDl-gYXdr0q8nv0kA,1961
+kreuzberg/_utils/_process_pool.py,sha256=4BqhmRspwMyPT2EBfTu_rrn7v722wlMLD8qlYvYsc00,8621
+kreuzberg/_utils/_quality.py,sha256=dgFLt40NSqB8Ciej5QcZQLiV4U7LcrGux0vXckiE31U,7568
+kreuzberg/_utils/_serialization.py,sha256=Rt5zSkvzf1SVNDrI6F2Zvnkel24mQkD1QvP0WjgZUgk,2195
+kreuzberg/_utils/_string.py,sha256=5YKu9EZlZQ-LkphXUq8fdwKQrX9jWACFEhMGfjIysf4,6381
+kreuzberg/_utils/_sync.py,sha256=7LSavBmxVKQUzdjfx9fYRAI9IbJtRw8iGf_Q8B7RX9g,4923
+kreuzberg/_utils/_table.py,sha256=C2skLtcyczxDEH33Qw2dOwnR15SGillvNEP-NzBG3R8,8156
+kreuzberg/_utils/_tmp.py,sha256=hVn-VVijIg2FM7EZJ899gc7wZg-TGoJZoeAcxMX-Cxg,1044
+kreuzberg-3.8.1.dist-info/METADATA,sha256=IqJ6RTcFlwkMN6JZIkb9c8O4rgTrPqIuzXWerD6He1I,11507
+kreuzberg-3.8.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kreuzberg-3.8.1.dist-info/entry_points.txt,sha256=GplGhFryCP7kyAG_k-Mdahznvo2fwi73qLFg5yQfH_A,91
+kreuzberg-3.8.1.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
+kreuzberg-3.8.1.dist-info/RECORD,,

{kreuzberg-3.3.0.dist-info → kreuzberg-3.8.1.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
 kreuzberg = kreuzberg.cli:cli
+kreuzberg-mcp = kreuzberg._mcp.server:main

kreuzberg/_multiprocessing/__init__.py

@@ -1,6 +0,0 @@
-"""Multiprocessing utilities for kreuzberg."""
-
-from .process_manager import ProcessPoolManager
-from .tesseract_pool import TesseractProcessPool
-
-__all__ = ["ProcessPoolManager", "TesseractProcessPool"]