kreuzberg 3.3.0__tar.gz → 3.4.1__tar.gz

kreuzberg-3.4.1/.docker/Dockerfile

@@ -0,0 +1,21 @@
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm as app
+ARG EXTRAS=""
+WORKDIR /app
+ENV PYTHONDONTWRITEBYTECODE 1
+ENV PYTHONUNBUFFERED 1
+ENV UV_LINK_MODE=copy
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    pandoc \
+    tesseract-ocr \
+    && apt-get clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+
+COPY pyproject.toml uv.lock README.md ./
+COPY kreuzberg kreuzberg
+
+RUN uv sync --extra api${EXTRAS:+ --extra ${EXTRAS}} --no-editable --no-dev --compile-bytecode
+
+RUN groupadd -r appuser && useradd -r -g appuser -d /app -s /sbin/nologin appuser
+USER appuser
+CMD ["litestar", "--app", "kreuzberg._api.main:app", "run", "--host", "0.0.0.0"]

kreuzberg-3.4.1/.docker/README.md

@@ -0,0 +1,87 @@
+# Kreuzberg Docker Images
+
+[![GitHub](https://img.shields.io/badge/GitHub-Goldziher%2Fkreuzberg-blue)](https://github.com/Goldziher/kreuzberg)
+[![PyPI](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://github.com/Goldziher/kreuzberg/blob/main/LICENSE)
+
+High-performance Python library for text extraction from documents, available as Docker images.
+
+**Source Code**: [github.com/Goldziher/kreuzberg](https://github.com/Goldziher/kreuzberg)
+
+## Quick Start
+
+```bash
+docker run -p 8000:8000 goldziher/kreuzberg:latest
+```
+
+## Available Tags
+
+- `latest` - Latest stable release with API server and Tesseract OCR
+- `X.Y.Z` - Specific version (e.g., `3.0.0`)
+- `X.Y.Z-easyocr` - With EasyOCR support
+- `X.Y.Z-paddle` - With PaddleOCR support
+- `X.Y.Z-gmft` - With GMFT table extraction
+- `X.Y.Z-all` - With all optional dependencies
+
+## Usage
+
+### Extract Files via API
+
+```bash
+# Single file
+curl -X POST http://localhost:8000/extract \
+  -F "data=@document.pdf"
+
+# Multiple files
+curl -X POST http://localhost:8000/extract \
+  -F "data=@document1.pdf" \
+  -F "data=@document2.docx"
+```
+
+### Docker Compose
+
+```yaml
+version: '3.8'
+
+services:
+  kreuzberg:
+    image: goldziher/kreuzberg:latest
+    ports:
+      - "8000:8000"
+    restart: unless-stopped
+```
+
+## Features
+
+- **🚀 High Performance**: Optimized for speed and efficiency
+- **📄 Multiple Formats**: PDF, DOCX, images, HTML, and more
+- **🔍 OCR Support**: Built-in Tesseract, optional EasyOCR/PaddleOCR
+- **📊 Table Extraction**: Extract tables with GMFT
+- **🔒 Secure**: Runs as non-root user, no external API calls
+- **📦 Ready to Use**: Pre-configured API server
+
+## Documentation
+
+- **[GitHub Repository](https://github.com/Goldziher/kreuzberg)** - Source code and issue tracking
+- **[Full Documentation](https://goldziher.github.io/kreuzberg/)** - Complete user guide and API reference
+- **[API Documentation](https://goldziher.github.io/kreuzberg/user-guide/api-server/)** - REST API endpoints and usage
+- **[Docker Guide](https://goldziher.github.io/kreuzberg/user-guide/docker/)** - Detailed Docker usage guide
+
+## Support
+
+- **Issues**: [github.com/Goldziher/kreuzberg/issues](https://github.com/Goldziher/kreuzberg/issues)
+- **Discussions**: [github.com/Goldziher/kreuzberg/discussions](https://github.com/Goldziher/kreuzberg/discussions)
+- **Discord**: [Join our community](https://discord.gg/pXxagNK2zN)
+
+## Contributing
+
+Contributions are welcome! See our [Contributing Guide](https://github.com/Goldziher/kreuzberg/blob/main/docs/contributing.md).
+
+## License
+
+MIT License - see [LICENSE](https://github.com/Goldziher/kreuzberg/blob/main/LICENSE) for details.
+
+______________________________________________________________________
+
+Made with ❤️ by the [Kreuzberg contributors](https://github.com/Goldziher/kreuzberg/graphs/contributors)

kreuzberg-3.4.1/.dockerignore

@@ -0,0 +1,15 @@
+*.pyc
+*.pyd
+*.pyo
+.git
+.github/
+.gitignore
+.idea
+.mypy_cache
+.pytest_cache
+.ruff_cache
+.vscode
+__pycache__
+benchmarks/
+docs/
+tests/

kreuzberg-3.4.1/.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-3.4.1/.github/workflows/publish-docker.yml

@@ -0,0 +1,111 @@
+# .github/workflows/publish-docker.yml
+
+name: Publish Docker Images
+
+on:
+  workflow_run:
+    workflows: ["Release"]
+    types:
+      - completed
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    if: ${{ github.event.workflow_run.conclusion == 'success' || github.event_name == 'workflow_dispatch' }}
+    permissions:
+      contents: read
+      packages: write
+
+    strategy:
+      matrix:
+        include:
+          - name: core
+            extras: ""
+            tag_suffix: "" # The base image tag (includes API + tesseract)
+          - name: easyocr
+            extras: "easyocr"
+            tag_suffix: "-easyocr"
+          - name: paddle
+            extras: "paddleocr"
+            tag_suffix: "-paddle"
+          - name: gmft
+            extras: "gmft"
+            tag_suffix: "-gmft"
+          - name: all
+            extras: "all"
+            tag_suffix: "-all"
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.workflow_run.head_branch || github.ref }}
+
+      - name: Get release version
+        id: get_version
+        run: |
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
+            # For manual dispatch, get the latest tag by listing all tags
+            git fetch --tags
+            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
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: goldziher/kreuzberg
+          tags: |
+            # Release version tag (e.g., v3.0.0-easyocr)
+            type=raw,value=${{ steps.get_version.outputs.VERSION }}${{ matrix.tag_suffix }}
+            # Latest tag for each variant (e.g., latest-easyocr)
+            type=raw,value=latest${{ matrix.tag_suffix }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./.docker/Dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: true
+          build-args: |
+            EXTRAS=${{ matrix.extras }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+
+      - 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 }}
+          repository: goldziher/kreuzberg
+          readme-filepath: ./.docker/README.md

{kreuzberg-3.3.0 → kreuzberg-3.4.1}/.gitignore

@@ -6,28 +6,30 @@
 *.py[cod]
 *.suo
 *.user
-.DS_store
+*temp/
 .coverage
 .coverage*
+.cursorrules
 .dist/
+.DS_store
 .env
 .idea/
+.kreuzberg/
 .mypy_cache/
 .pytest_cache/
 .python-version
+.ropeproject
 .ruff_cache/
 .run/
 .venv/
 .vscode/
 .windsurfrules
-.cursorrules
-CLAUDE.md
-GEMINI.md
 __pycache__/
+benchmark_results.json
+CLAUDE.md
 coverage.xml
+docker-compose.yaml
+GEMINI.md
 prompt_template.egg-info/
 requirements.txt
-Dockerfile
-docker-compose.yaml
-benchmark_results.json
-.kreuzberg/
+site/

kreuzberg-3.4.1/PKG-INFO

@@ -0,0 +1,233 @@
+Metadata-Version: 2.4
+Name: kreuzberg
+Version: 3.4.1
+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 :: 3.9
+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: >=3.9
+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>