kreuzberg 3.4.0__tar.gz → 3.4.2__tar.gz

{kreuzberg-3.4.0 → kreuzberg-3.4.2}/.github/workflows/ci.yaml

@@ -50,7 +50,7 @@ jobs:
     strategy:
       matrix:
         os: [ ubuntu-latest, macOS-latest, windows-latest ]
-        python: ${{ github.event_name == 'pull_request' && fromJSON('["3.13"]') || fromJSON('["3.9", "3.10", "3.11", "3.12", "3.13"]') }}
+        python: ${{ github.event_name == 'pull_request' && fromJSON('["3.13"]') || fromJSON('["3.10", "3.11", "3.12", "3.13"]') }}
     runs-on: ${{ matrix.os }}
     timeout-minutes: 30
     steps:

kreuzberg-3.4.2/.github/workflows/docs.yml

@@ -0,0 +1,66 @@
+name: Deploy Documentation
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'docs/**'
+      - 'mkdocs.yaml'
+      - '.github/workflows/docs.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: |
+          uv sync --group doc
+
+      - name: Setup Pages
+        uses: actions/configure-pages@v5
+
+      - name: Build documentation
+        run: |
+          uv run mkdocs build --clean --strict
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: ./site
+
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

{kreuzberg-3.4.0 → kreuzberg-3.4.2}/.github/workflows/publish-docker.yml

@@ -9,11 +9,12 @@ on:
       - completed
     branches:
       - main
+  workflow_dispatch:
 
 jobs:
   build-and-push:
     runs-on: ubuntu-latest
-    if: ${{ github.event.workflow_run.conclusion == 'success' }}
+    if: ${{ github.event.workflow_run.conclusion == 'success' || github.event_name == 'workflow_dispatch' }}
     permissions:
       contents: read
       packages: write
@@ -41,20 +42,28 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
-          ref: ${{ github.event.workflow_run.head_branch }}
+          ref: ${{ github.event.workflow_run.head_branch || github.ref }}
 
       - name: Get release version
         id: get_version
         run: |
-          echo "VERSION=${{ github.event.workflow_run.head_branch }}" >> $GITHUB_OUTPUT
-          # If triggered by a tag, extract version
-          if [[ "${{ github.event.workflow_run.head_branch }}" =~ ^v[0-9]+\.[0-9]+\.[0-9]+ ]]; then
-            echo "VERSION=${{ github.event.workflow_run.head_branch }}" >> $GITHUB_OUTPUT
-          else
-            # Get the latest tag
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            # For manual dispatch, get the latest tag by listing all tags
             git fetch --tags
-            echo "VERSION=$(git describe --tags --abbrev=0)" >> $GITHUB_OUTPUT
+            VERSION=$(git tag --sort=-version:refname | head -n1)
+          else
+            # For workflow_run, use the head branch
+            VERSION="${{ github.event.workflow_run.head_branch }}"
+            # If triggered by a tag, extract version
+            if [[ "$VERSION" =~ ^v[0-9]+\.[0-9]+\.[0-9]+ ]]; then
+              VERSION="$VERSION"
+            else
+              # Get the latest tag by listing all tags
+              git fetch --tags
+              VERSION=$(git tag --sort=-version:refname | head -n1)
+            fi
           fi
+          echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
 
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
@@ -94,6 +103,7 @@ jobs:
       - name: Update Docker Hub README
         uses: peter-evans/dockerhub-description@v4
         if: matrix.name == 'core'
+        continue-on-error: true
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}

{kreuzberg-3.4.0 → kreuzberg-3.4.2}/.gitignore

@@ -32,3 +32,4 @@ docker-compose.yaml
 GEMINI.md
 prompt_template.egg-info/
 requirements.txt
+site/

kreuzberg-3.4.2/PKG-INFO

@@ -0,0 +1,232 @@
+Metadata-Version: 2.4
+Name: kreuzberg
+Version: 3.4.2
+Summary: A text extraction library supporting PDFs, images, office documents and more
+Project-URL: homepage, https://github.com/Goldziher/kreuzberg
+Author-email: Na'aman Hirschfeld <nhirschfed@gmail.com>
+License: MIT
+License-File: LICENSE
+Keywords: document-processing,image-to-text,ocr,pandoc,pdf-extraction,rag,table-extraction,tesseract,text-extraction,text-processing
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+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 :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: General
+Classifier: Topic :: Utilities
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: anyio>=4.9.0
+Requires-Dist: charset-normalizer>=3.4.2
+Requires-Dist: exceptiongroup>=1.2.2; python_version < '3.11'
+Requires-Dist: html-to-markdown>=1.4.0
+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: all
+Requires-Dist: click>=8.2.1; extra == 'all'
+Requires-Dist: easyocr>=1.7.2; extra == 'all'
+Requires-Dist: gmft>=0.4.2; extra == 'all'
+Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.1.6; 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: tomli>=2.0.0; (python_version < '3.11') and extra == 'all'
+Provides-Extra: api
+Requires-Dist: litestar[opentelemetry,standard,structlog]>=2.1.6; 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: gmft
+Requires-Dist: gmft>=0.4.2; extra == 'gmft'
+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)
+
+**High-performance Python library for text extraction from documents.** Extract text from PDFs, images, office documents, and more with both async and sync APIs.
+
+📖 **[Complete Documentation](https://goldziher.github.io/kreuzberg/)**
+
+## Why Kreuzberg?
+
+- **🚀 Fastest Performance**: [Benchmarked](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) as the fastest text extraction library
+- **💾 Memory Efficient**: 14x smaller than alternatives (71MB vs 1GB+)
+- **⚡ Dual APIs**: Only library with both sync and async support
+- **🔧 Zero Configuration**: Works out of the box with sane defaults
+- **🏠 Local Processing**: No cloud dependencies or external API calls
+- **📦 Rich Format Support**: PDFs, images, Office docs, HTML, and more
+- **🔍 Multiple OCR Engines**: Tesseract, EasyOCR, and PaddleOCR support
+- **🐳 Production Ready**: CLI, REST API, and Docker images included
+
+## 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 from any document type
+    result = await extract_file("document.pdf")
+    print(result.content)
+    print(result.metadata)
+
+asyncio.run(main())
+```
+
+## Deployment Options
+
+### 🐳 Docker (Recommended)
+
+```bash
+# Run API server
+docker run -p 8000:8000 goldziher/kreuzberg:3.4.0
+
+# Extract files
+curl -X POST http://localhost:8000/extract -F "data=@document.pdf"
+```
+
+Available variants: `3.4.0`, `3.4.0-easyocr`, `3.4.0-paddle`, `3.4.0-gmft`, `3.4.0-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
+
+**Fastest extraction speeds** with minimal resource usage:
+
+| Library       | Speed          | Memory        | Size        | Success Rate |
+| ------------- | -------------- | ------------- | ----------- | ------------ |
+| **Kreuzberg** | ⚡ **Fastest** | 💾 **Lowest** | 📦 **71MB** | ✅ **100%**  |
+| Unstructured  | 2-3x slower    | 2x higher     | 146MB       | 95%          |
+| MarkItDown    | 3-4x slower    | 3x higher     | 251MB       | 90%          |
+| Docling       | 4-5x slower    | 10x higher    | 1,032MB     | 85%          |
+
+> **Rule of thumb**: Use async API for complex documents and batch processing (up to 4.5x faster)
+
+## 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
+- [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
+
+## Advanced Features
+
+- **📊 Table Extraction**: Extract tables from PDFs with GMFT
+- **🧩 Content Chunking**: Split documents for RAG applications
+- **🎯 Custom Extractors**: Extend with your own document handlers
+- **🔧 Configuration**: Flexible TOML-based configuration
+- **🪝 Hooks**: Pre/post-processing customization
+- **🌍 Multi-language OCR**: 100+ languages supported
+- **⚙️ Metadata Extraction**: Rich document metadata
+- **🔄 Batch Processing**: Efficient bulk document processing
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.
+
+______________________________________________________________________
+
+<div align="center">
+
+**[Documentation](https://goldziher.github.io/kreuzberg/) • [PyPI](https://pypi.org/project/kreuzberg/) • [Docker Hub](https://hub.docker.com/r/goldziher/kreuzberg) • [Discord](https://discord.gg/pXxagNK2zN)**
+
+Made with ❤️ by the [Kreuzberg contributors](https://github.com/Goldziher/kreuzberg/graphs/contributors)
+
+</div>

kreuzberg-3.4.2/README.md

@@ -0,0 +1,168 @@
+# 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)
+
+**High-performance Python library for text extraction from documents.** Extract text from PDFs, images, office documents, and more with both async and sync APIs.
+
+📖 **[Complete Documentation](https://goldziher.github.io/kreuzberg/)**
+
+## Why Kreuzberg?
+
+- **🚀 Fastest Performance**: [Benchmarked](https://github.com/Goldziher/python-text-extraction-libs-benchmarks) as the fastest text extraction library
+- **💾 Memory Efficient**: 14x smaller than alternatives (71MB vs 1GB+)
+- **⚡ Dual APIs**: Only library with both sync and async support
+- **🔧 Zero Configuration**: Works out of the box with sane defaults
+- **🏠 Local Processing**: No cloud dependencies or external API calls
+- **📦 Rich Format Support**: PDFs, images, Office docs, HTML, and more
+- **🔍 Multiple OCR Engines**: Tesseract, EasyOCR, and PaddleOCR support
+- **🐳 Production Ready**: CLI, REST API, and Docker images included
+
+## 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 from any document type
+    result = await extract_file("document.pdf")
+    print(result.content)
+    print(result.metadata)
+
+asyncio.run(main())
+```
+
+## Deployment Options
+
+### 🐳 Docker (Recommended)
+
+```bash
+# Run API server
+docker run -p 8000:8000 goldziher/kreuzberg:3.4.0
+
+# Extract files
+curl -X POST http://localhost:8000/extract -F "data=@document.pdf"
+```
+
+Available variants: `3.4.0`, `3.4.0-easyocr`, `3.4.0-paddle`, `3.4.0-gmft`, `3.4.0-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
+
+**Fastest extraction speeds** with minimal resource usage:
+
+| Library       | Speed          | Memory        | Size        | Success Rate |
+| ------------- | -------------- | ------------- | ----------- | ------------ |
+| **Kreuzberg** | ⚡ **Fastest** | 💾 **Lowest** | 📦 **71MB** | ✅ **100%**  |
+| Unstructured  | 2-3x slower    | 2x higher     | 146MB       | 95%          |
+| MarkItDown    | 3-4x slower    | 3x higher     | 251MB       | 90%          |
+| Docling       | 4-5x slower    | 10x higher    | 1,032MB     | 85%          |
+
+> **Rule of thumb**: Use async API for complex documents and batch processing (up to 4.5x faster)
+
+## 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
+- [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
+
+## Advanced Features
+
+- **📊 Table Extraction**: Extract tables from PDFs with GMFT
+- **🧩 Content Chunking**: Split documents for RAG applications
+- **🎯 Custom Extractors**: Extend with your own document handlers
+- **🔧 Configuration**: Flexible TOML-based configuration
+- **🪝 Hooks**: Pre/post-processing customization
+- **🌍 Multi-language OCR**: 100+ languages supported
+- **⚙️ Metadata Extraction**: Rich document metadata
+- **🔄 Batch Processing**: Efficient bulk document processing
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.
+
+______________________________________________________________________
+
+<div align="center">
+
+**[Documentation](https://goldziher.github.io/kreuzberg/) • [PyPI](https://pypi.org/project/kreuzberg/) • [Docker Hub](https://hub.docker.com/r/goldziher/kreuzberg) • [Discord](https://discord.gg/pXxagNK2zN)**
+
+Made with ❤️ by the [Kreuzberg contributors](https://github.com/Goldziher/kreuzberg/graphs/contributors)
+
+</div>

{kreuzberg-3.4.0 → kreuzberg-3.4.2}/ai-rulez.yaml

@@ -1,6 +1,6 @@
 metadata:
   name: "Kreuzberg"
-  version: "3.2.0"
+  version: "3.4.0"
   description: "A text extraction library supporting PDFs, images, office documents and more"
 
 outputs:
@@ -96,8 +96,9 @@ rules:
       - Run manually: `pre-commit run --all-files`
 
       ### Documentation
-      - Build docs: `mkdocs build`
-      - Serve docs locally: `mkdocs serve`
+      - Build docs: `uv run mkdocs build --clean --strict`
+      - Serve docs locally: `uv run mkdocs serve`
+      - Install doc dependencies: `uv sync --group doc`
 
   - name: "Architecture"
     priority: 9
@@ -115,6 +116,8 @@ rules:
       - **GMFT Integration**: Table extraction using GMFT library for PDFs
       - **Chunking**: Text splitting functionality in `_chunker.py`
       - **Async/Sync**: Primary async implementation with sync wrappers in `_utils/_sync.py`
+      - **API Server**: REST API using Litestar framework in `_api/main.py`
+      - **CLI**: Command-line interface for batch processing and automation
 
       ### Adding New Features
       - New extractors: Inherit from `BaseExtractor` and register with `ExtractorRegistry`
@@ -153,6 +156,56 @@ rules:
       - All builtin imports should be at the top level (except for cyclical or optional dependencies)
       - When committing, always use the format specified in the CLAUDE.md
 
+  - name: "CI/CD and Deployment"
+    priority: 6
+    content: |
+      ### GitHub Actions Workflows
+      - **Release**: Automated PyPI publishing via GitHub releases
+      - **Docker**: Multi-platform Docker builds (linux/amd64, linux/arm64)
+      - **Documentation**: Auto-deploy to GitHub Pages on docs changes
+
+      ### Docker Variants
+      - **Core** (`goldziher/kreuzberg:v3.4.0`): API + Tesseract OCR
+      - **EasyOCR** (`goldziher/kreuzberg:v3.4.0-easyocr`): Core + EasyOCR
+      - **PaddleOCR** (`goldziher/kreuzberg:v3.4.0-paddle`): Core + PaddleOCR
+      - **GMFT** (`goldziher/kreuzberg:v3.4.0-gmft`): Core + table extraction
+      - **All** (`goldziher/kreuzberg:v3.4.0-all`): All features included
+
+      ### Manual Triggers
+      - Docker builds: `gh workflow run "Publish Docker Images"`
+      - Documentation: Auto-deploys on docs/ changes
+
+      ### Common Issues
+      - **Docker version detection**: Use `git tag --sort=-version:refname | head -n1` not `git describe`
+      - **Docs dependencies**: Use `uv sync --group doc` for proper mkdocs-material[imaging] support
+      - **Docker Hub README**: May fail due to permissions, use `continue-on-error: true`
+
+  - name: "Package Management"
+    priority: 6
+    content: |
+      ### Optional Dependencies Structure
+      ```toml
+      [project.optional-dependencies]
+      api = ["litestar[standard,structlog,opentelemetry]>=2.1.6"]
+      cli = ["click>=8.2.1", "rich>=14.0.0", "tomli>=2.0.0; python_version<'3.11'"]
+      chunking = ["semantic-text-splitter>=0.27.0"]
+      easyocr = ["easyocr>=1.7.2"]
+      gmft = ["gmft>=0.4.2"]
+      paddleocr = ["paddleocr>=3.1.0", "paddlepaddle>=3.1.0", "setuptools>=80.9.0"]
+      all = ["kreuzberg[api,chunking,cli,easyocr,gmft,paddleocr]"]
+      ```
+
+      ### Installation Patterns
+      - Basic: `pip install kreuzberg`
+      - With features: `pip install "kreuzberg[api,cli]"`
+      - All features: `pip install "kreuzberg[all]"`
+      - Development: `uv sync --all-extras`
+
+      ### Dependencies
+      - **Core**: pypdfium2, playa-pdf, python-pptx, etc.
+      - **System**: tesseract-ocr, pandoc (via package manager)
+      - **Development**: Uses dependency groups in pyproject.toml
+
 sections:
   - title: "Planned Features"
     content: |

{kreuzberg-3.4.0 → kreuzberg-3.4.2}/docs/contributing.md

@@ -68,7 +68,7 @@ Use [Conventional Commits](https://www.conventionalcommits.org/):
 
 ## Notes
 
-- Python 3.9-3.13 supported
+- Python 3.10-3.13 supported
 - System dependencies (optional): Tesseract, Pandoc
 - Pre-commit runs automatically on commit
 - Join our [Discord](https://discord.gg/pXxagNK2zN) for help

{kreuzberg-3.4.0 → kreuzberg-3.4.2}/docs/user-guide/docker.md

@@ -7,11 +7,12 @@ Kreuzberg provides official Docker images for easy deployment and containerized
 Docker images are available on [Docker Hub](https://hub.docker.com/r/goldziher/kreuzberg):
 
 - `goldziher/kreuzberg:latest` - Core image with API server and Tesseract OCR
-- `goldziher/kreuzberg:VERSION` - Specific version (e.g., `3.0.0`)
-- `goldziher/kreuzberg:VERSION-easyocr` - With EasyOCR support
-- `goldziher/kreuzberg:VERSION-paddle` - With PaddleOCR support
-- `goldziher/kreuzberg:VERSION-gmft` - With GMFT table extraction
-- `goldziher/kreuzberg:VERSION-all` - With all optional dependencies
+- `goldziher/kreuzberg:latest-easyocr` - With EasyOCR support
+- `goldziher/kreuzberg:latest-paddle` - With PaddleOCR support
+- `goldziher/kreuzberg:latest-gmft` - With GMFT table extraction
+- `goldziher/kreuzberg:latest-all` - With all optional dependencies
+
+> **Note**: Specific version tags are also available (e.g., `v3.4.0`, `v3.4.0-easyocr`)
 
 ## Quick Start
 
@@ -45,8 +46,6 @@ curl -X POST http://localhost:8000/extract \
 Create a `docker-compose.yml`:
 
 ```yaml
-version: '3.8'
-
 services:
   kreuzberg:
     image: goldziher/kreuzberg:latest
@@ -54,9 +53,6 @@ services:
       - "8000:8000"
     environment:
       - PYTHONUNBUFFERED=1
-    volumes:
-      # Optional: Mount local directory for file access
-      - ./documents:/app/documents
     restart: unless-stopped
 ```
 
@@ -107,7 +103,7 @@ CMD ["python", "custom_config.py"]
 
 ### Base Image
 
-- Based on `python:3.13-bookworm`
+- Based on `python:3.13-bookworm` (requires Python 3.10+)
 - Includes system dependencies: `pandoc`, `tesseract-ocr`
 - Runs as non-root user `appuser`
 - Exposes port 8000