kreuzberg 3.1.7__tar.gz → 3.3.0__tar.gz

kreuzberg-3.3.0/.commitlintrc

@@ -0,0 +1 @@
+{ "extends": ["@commitlint/config-conventional"] }

kreuzberg-3.3.0/.github/benchmarks/README.md

@@ -0,0 +1,15 @@
+# Performance Baseline
+
+This directory contains baseline performance metrics for the Kreuzberg library.
+
+## Files
+
+- `baseline.json` - Performance baseline automatically updated from main branch CI
+- This file is used for performance regression detection in PRs
+
+## How it works
+
+1. When code is pushed to `main`, CI runs benchmarks and stores results as `baseline.json`
+1. When PRs are opened, CI compares current performance against this baseline
+1. If performance degrades beyond threshold (20%), the CI check fails
+1. The baseline is automatically updated when new changes are merged to main

kreuzberg-3.3.0/.github/dependabot.yaml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"

kreuzberg-3.3.0/.github/workflows/ci.yaml

@@ -0,0 +1,124 @@
+name: CI
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+      - feat/smart-multiprocessing
+
+jobs:
+  validate:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: "pyproject.toml"
+
+      - name: Install Dependencies
+        shell: bash
+        run: |
+          if [[ "${{ runner.os }}" == "Windows" ]] && [[ -d ".venv" ]]; then
+            echo "Removing existing .venv directory on Windows"
+            rm -rf .venv
+          fi
+          uv sync --all-packages --all-extras --dev
+
+      - name: Load Cached Pre-Commit Dependencies
+        id: cached-pre-commit-dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pre-commit/
+          key: pre-commit|${{ env.pythonLocation }}|${{ hashFiles('.pre-commit-config.yaml') }}
+
+      - name: Execute Pre-Commit
+        run: uv run pre-commit run --show-diff-on-failure --color=always --all-files
+
+  test:
+    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"]') }}
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 30
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+
+      - name: Install Python
+        uses: actions/setup-python@v5
+        id: setup-python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Cache Python Dependencies
+        id: python-cache
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache/uv
+            .venv
+          key: python-dependencies-${{ matrix.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('uv.lock') }}
+          restore-keys: |
+            python-dependencies-${{ matrix.os }}-${{ matrix.python }}-
+
+      - name: Install Dependencies
+        shell: bash
+        run: |
+          if [[ "${{ runner.os }}" == "Windows" ]] && [[ -d ".venv" ]]; then
+            echo "Removing existing .venv directory on Windows"
+            rm -rf .venv
+          fi
+          uv sync --all-packages --all-extras --dev
+
+      - name: Cache Test Artifacts
+        uses: actions/cache@v4
+        with:
+          path: .pytest_cache/
+          key: pytest-cache-${{ matrix.os }}-${{ matrix.python }}
+
+      - name: Cache and Install Homebrew (macOS)
+        if: runner.os == 'macOS'
+        uses: tecolicom/actions-use-homebrew-tools@v1
+        with:
+          tools: 'tesseract tesseract-lang pandoc'
+          key: 'homebrew-tools-${{ runner.os }}'
+          cache: yes
+          verbose: false
+
+      - name: Cache and Install APT Packages (Linux)
+        if: runner.os == 'Linux'
+        uses: awalsh128/cache-apt-pkgs-action@latest
+        with:
+          packages: tesseract-ocr tesseract-ocr-deu pandoc
+          version: 1.0
+
+      - name: Install System Dependencies (Windows)
+        if: runner.os == 'Windows'
+        run: |
+          choco install -y tesseract pandoc
+          Write-Output "C:\Program Files\Tesseract-OCR" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+          Write-Output "C:\Program Files\Pandoc" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
+          $env:PATH = "C:\Program Files\Tesseract-OCR;C:\Program Files\Pandoc;" + $env:PATH
+          tesseract --version
+          pandoc --version
+
+      - name: Run Tests
+        run: uv run pytest -s -vvv

kreuzberg-3.3.0/.github/workflows/pr-title.yaml

@@ -0,0 +1,20 @@
+name: "Check PR Title"
+
+on:
+  pull_request_target:
+    types:
+      - opened
+      - edited
+      - synchronize
+
+permissions:
+  pull-requests: read
+
+jobs:
+  main:
+    name: Validate PR title
+    runs-on: ubuntu-latest
+    steps:
+      - uses: amannn/action-semantic-pull-request@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

kreuzberg-3.3.0/.github/workflows/release.yaml

@@ -0,0 +1,31 @@
+name: Release
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          enable-cache: true
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: "pyproject.toml"
+
+      - name: Install Dependencies
+        run: uv build
+
+      - name: Publish
+        uses: pypa/gh-action-pypi-publish@release/v1

kreuzberg-3.3.0/.gitignore

@@ -0,0 +1,33 @@
+*$py.class
+*.Cache
+*.cscfg
+*.egg-info/
+*.log
+*.py[cod]
+*.suo
+*.user
+.DS_store
+.coverage
+.coverage*
+.dist/
+.env
+.idea/
+.mypy_cache/
+.pytest_cache/
+.python-version
+.ruff_cache/
+.run/
+.venv/
+.vscode/
+.windsurfrules
+.cursorrules
+CLAUDE.md
+GEMINI.md
+__pycache__/
+coverage.xml
+prompt_template.egg-info/
+requirements.txt
+Dockerfile
+docker-compose.yaml
+benchmark_results.json
+.kreuzberg/

kreuzberg-3.3.0/.markdownlint.yaml

@@ -0,0 +1,17 @@
+default: true
+
+MD007:
+  indent: 4
+
+MD033: false
+
+MD041: false
+
+MD013: false
+
+MD014: false
+
+MD024:
+  siblings_only: true
+
+MD046: false

kreuzberg-3.3.0/.pre-commit-config.yaml

@@ -0,0 +1,86 @@
+repos:
+  - repo: https://github.com/alessandrojcm/commitlint-pre-commit-hook
+    rev: "v9.22.0"
+    hooks:
+      - id: commitlint
+        stages: [commit-msg]
+        additional_dependencies: ["@commitlint/config-conventional"]
+  - repo: https://github.com/Goldziher/ai-rulez
+    rev: v1.1.2
+    hooks:
+      - id: ai-rulez-validate
+      - id: ai-rulez-generate
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: name-tests-test
+        args:
+          - --pytest
+        exclude: factories|test_utils|completion.py|test_data
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-toml
+      - id: check-case-conflict
+      - id: detect-private-key
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: v0.24.1
+    hooks:
+      - id: validate-pyproject
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.22
+    hooks:
+      - id: mdformat
+        additional_dependencies:
+          - mdformat-mkdocs==4.0.0
+  - repo: https://github.com/igorshubovych/markdownlint-cli
+    rev: v0.45.0
+    hooks:
+      - id: markdownlint-fix
+  - repo: https://github.com/adamchainz/blacken-docs
+    rev: 1.19.1
+    hooks:
+      - id: blacken-docs
+        args: ["--pyi", "--line-length", "130"]
+        additional_dependencies:
+          - black==25.1.0
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: "v3.6.2"
+    hooks:
+      - id: prettier
+        exclude: ^tests|^.idea|^migrations|^.git|README.md|^docs
+  - repo: https://github.com/tox-dev/pyproject-fmt
+    rev: "v2.6.0"
+    hooks:
+      - id: pyproject-fmt
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.12.1
+    hooks:
+      - id: ruff
+        args: ["--fix", "--unsafe-fixes"]
+      - id: ruff-format
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.4.1
+    hooks:
+      - id: codespell
+        exclude: ^tests|^scripts|^kreuzberg/_tesseract|^kreuzberg/_mime_types
+        additional_dependencies:
+          - tomli
+  - repo: https://github.com/jsh9/pydoclint
+    rev: 0.6.7
+    hooks:
+      - id: pydoclint
+        args:
+          [
+            --style=google,
+            --check-return-types=False,
+            --arg-type-hints-in-docstring=False,
+          ]
+        exclude: ^benchmarks/|^kreuzberg/_|^tests/|^scripts/|^run_benchmarks\.py
+  - repo: local
+    hooks:
+      - id: mypy
+        name: mypy
+        entry: uv run mypy
+        require_serial: true
+        language: system
+        types: [python]

{kreuzberg-3.1.7 → kreuzberg-3.3.0}/PKG-INFO

@@ -1,56 +1,60 @@
 Metadata-Version: 2.4
 Name: kreuzberg
-Version: 3.1.7
+Version: 3.3.0
 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
-Project-URL: homepage, https://github.com/Goldziher/kreuzberg
+License-File: LICENSE
 Keywords: document-processing,image-to-text,ocr,pandoc,pdf-extraction,rag,table-extraction,tesseract,text-extraction,text-processing
 Classifier: Development Status :: 4 - Beta
 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
-Description-Content-Type: text/markdown
-License-File: LICENSE
+Requires-Python: >=3.13
 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>=1.3.3
-Requires-Dist: playa-pdf>=0.5.1
+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"
+Requires-Dist: typing-extensions>=4.14.0; python_version < '3.12'
 Provides-Extra: all
-Requires-Dist: easyocr>=1.7.2; extra == "all"
-Requires-Dist: gmft>=0.4.1; extra == "all"
-Requires-Dist: paddleocr>=3.0.1; extra == "all"
-Requires-Dist: paddlepaddle>=3.0.0; extra == "all"
-Requires-Dist: semantic-text-splitter>=0.27.0; extra == "all"
-Requires-Dist: setuptools>=80.9.0; 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: 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: chunking
-Requires-Dist: semantic-text-splitter>=0.27.0; 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"
+Requires-Dist: easyocr>=1.7.2; extra == 'easyocr'
 Provides-Extra: gmft
-Requires-Dist: gmft>=0.4.1; extra == "gmft"
+Requires-Dist: gmft>=0.4.2; extra == 'gmft'
 Provides-Extra: paddleocr
-Requires-Dist: paddleocr>=3.0.1; extra == "paddleocr"
-Requires-Dist: paddlepaddle>=3.0.0; extra == "paddleocr"
-Requires-Dist: setuptools>=80.9.0; extra == "paddleocr"
-Dynamic: license-file
+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
 
@@ -68,6 +72,7 @@ Kreuzberg is a Python library for text extraction from documents. It provides a
 - **Resource Efficient**: Lightweight processing without GPU requirements
 - **Format Support**: Comprehensive support for documents, images, and text formats
 - **Multiple OCR Engines**: Support for Tesseract, EasyOCR, and PaddleOCR
+- **Command Line Interface**: Powerful CLI for batch processing and automation
 - **Metadata Extraction**: Get document metadata alongside text content
 - **Table Extraction**: Extract tables from documents using the excellent GMFT library
 - **Modern Python**: Built with async/await, type hints, and a functional-first approach
@@ -77,6 +82,9 @@ Kreuzberg is a Python library for text extraction from documents. It provides a
 
 ```bash
 pip install kreuzberg
+
+# Or install with CLI support
+pip install "kreuzberg[cli]"
 ```
 
 Install pandoc:
@@ -126,12 +134,53 @@ async def main():
 asyncio.run(main())
 ```
 
+## Command Line Interface
+
+Kreuzberg includes a powerful CLI for processing documents from the command line:
+
+```bash
+# Extract text from a file
+kreuzberg extract document.pdf
+
+# Extract with JSON output and metadata
+kreuzberg extract document.pdf --output-format json --show-metadata
+
+# Extract from stdin
+cat document.html | kreuzberg extract
+
+# Use specific OCR backend
+kreuzberg extract image.png --ocr-backend easyocr --easyocr-languages en,de
+
+# Extract with configuration file
+kreuzberg extract document.pdf --config config.toml
+```
+
+### CLI Configuration
+
+Configure via `pyproject.toml`:
+
+```toml
+[tool.kreuzberg]
+force_ocr = true
+chunk_content = false
+extract_tables = true
+max_chars = 4000
+ocr_backend = "tesseract"
+
+[tool.kreuzberg.tesseract]
+language = "eng+deu"
+psm = 3
+```
+
+For full CLI documentation, see the [CLI Guide](https://goldziher.github.io/kreuzberg/cli/).
+
 ## Documentation
 
 For comprehensive documentation, visit our [GitHub Pages](https://goldziher.github.io/kreuzberg/):
 
 - [Getting Started](https://goldziher.github.io/kreuzberg/getting-started/) - Installation and basic usage
 - [User Guide](https://goldziher.github.io/kreuzberg/user-guide/) - In-depth usage information
+- [CLI Guide](https://goldziher.github.io/kreuzberg/cli/) - Command-line interface documentation
 - [API Reference](https://goldziher.github.io/kreuzberg/api-reference/) - Detailed API documentation
 - [Examples](https://goldziher.github.io/kreuzberg/examples/) - Code examples for common use cases
 - [OCR Configuration](https://goldziher.github.io/kreuzberg/user-guide/ocr-configuration/) - Configure OCR engines
@@ -157,17 +206,29 @@ Kreuzberg supports multiple OCR engines:
 
 For comparison and selection guidance, see the [OCR Backends](https://goldziher.github.io/kreuzberg/user-guide/ocr-backends/) documentation.
 
-## Contribution
+## Performance
+
+Kreuzberg offers both sync and async APIs. Choose the right one based on your use case:
+
+| Operation              | Sync Time | Async Time | Async Advantage    |
+| ---------------------- | --------- | ---------- | ------------------ |
+| Simple text (Markdown) | 0.4ms     | 17.5ms     | **❌ 41x slower**  |
+| HTML documents         | 1.6ms     | 1.1ms      | **✅ 1.5x faster** |
+| Complex PDFs           | 39.0s     | 8.5s       | **✅ 4.6x faster** |
+| OCR processing         | 0.4s      | 0.7s       | **✅ 1.7x faster** |
+| Batch operations       | 38.6s     | 8.5s       | **✅ 4.5x faster** |
+
+**Rule of thumb:**
+
+- Use **sync** for simple documents and CLI applications
+- Use **async** for complex PDFs, OCR, and batch processing
+- Use **batch operations** for multiple files
 
-This library is open to contribution. Feel free to open issues or submit PRs. It's better to discuss issues before submitting PRs to avoid disappointment.
+For detailed benchmarks and methodology, see our [Performance Documentation](https://goldziher.github.io/kreuzberg/advanced/performance/).
 
-### Local Development
+## Contributing
 
-- Clone the repo
-- Install the system dependencies
-- Install the full dependencies with `uv sync`
-- Install the pre-commit hooks with: `pre-commit install && pre-commit install --hook-type commit-msg`
-- Make your changes and submit a PR
+We welcome contributions! Please see our [Contributing Guide](docs/contributing.md) for details on setting up your development environment and submitting pull requests.
 
 ## License
 

{kreuzberg-3.1.7 → kreuzberg-3.3.0}/README.md

@@ -14,6 +14,7 @@ Kreuzberg is a Python library for text extraction from documents. It provides a
 - **Resource Efficient**: Lightweight processing without GPU requirements
 - **Format Support**: Comprehensive support for documents, images, and text formats
 - **Multiple OCR Engines**: Support for Tesseract, EasyOCR, and PaddleOCR
+- **Command Line Interface**: Powerful CLI for batch processing and automation
 - **Metadata Extraction**: Get document metadata alongside text content
 - **Table Extraction**: Extract tables from documents using the excellent GMFT library
 - **Modern Python**: Built with async/await, type hints, and a functional-first approach
@@ -23,6 +24,9 @@ Kreuzberg is a Python library for text extraction from documents. It provides a
 
 ```bash
 pip install kreuzberg
+
+# Or install with CLI support
+pip install "kreuzberg[cli]"
 ```
 
 Install pandoc:
@@ -72,12 +76,53 @@ async def main():
 asyncio.run(main())
 ```
 
+## Command Line Interface
+
+Kreuzberg includes a powerful CLI for processing documents from the command line:
+
+```bash
+# Extract text from a file
+kreuzberg extract document.pdf
+
+# Extract with JSON output and metadata
+kreuzberg extract document.pdf --output-format json --show-metadata
+
+# Extract from stdin
+cat document.html | kreuzberg extract
+
+# Use specific OCR backend
+kreuzberg extract image.png --ocr-backend easyocr --easyocr-languages en,de
+
+# Extract with configuration file
+kreuzberg extract document.pdf --config config.toml
+```
+
+### CLI Configuration
+
+Configure via `pyproject.toml`:
+
+```toml
+[tool.kreuzberg]
+force_ocr = true
+chunk_content = false
+extract_tables = true
+max_chars = 4000
+ocr_backend = "tesseract"
+
+[tool.kreuzberg.tesseract]
+language = "eng+deu"
+psm = 3
+```
+
+For full CLI documentation, see the [CLI Guide](https://goldziher.github.io/kreuzberg/cli/).
+
 ## Documentation
 
 For comprehensive documentation, visit our [GitHub Pages](https://goldziher.github.io/kreuzberg/):
 
 - [Getting Started](https://goldziher.github.io/kreuzberg/getting-started/) - Installation and basic usage
 - [User Guide](https://goldziher.github.io/kreuzberg/user-guide/) - In-depth usage information
+- [CLI Guide](https://goldziher.github.io/kreuzberg/cli/) - Command-line interface documentation
 - [API Reference](https://goldziher.github.io/kreuzberg/api-reference/) - Detailed API documentation
 - [Examples](https://goldziher.github.io/kreuzberg/examples/) - Code examples for common use cases
 - [OCR Configuration](https://goldziher.github.io/kreuzberg/user-guide/ocr-configuration/) - Configure OCR engines
@@ -103,17 +148,29 @@ Kreuzberg supports multiple OCR engines:
 
 For comparison and selection guidance, see the [OCR Backends](https://goldziher.github.io/kreuzberg/user-guide/ocr-backends/) documentation.
 
-## Contribution
+## Performance
+
+Kreuzberg offers both sync and async APIs. Choose the right one based on your use case:
+
+| Operation              | Sync Time | Async Time | Async Advantage    |
+| ---------------------- | --------- | ---------- | ------------------ |
+| Simple text (Markdown) | 0.4ms     | 17.5ms     | **❌ 41x slower**  |
+| HTML documents         | 1.6ms     | 1.1ms      | **✅ 1.5x faster** |
+| Complex PDFs           | 39.0s     | 8.5s       | **✅ 4.6x faster** |
+| OCR processing         | 0.4s      | 0.7s       | **✅ 1.7x faster** |
+| Batch operations       | 38.6s     | 8.5s       | **✅ 4.5x faster** |
+
+**Rule of thumb:**
+
+- Use **sync** for simple documents and CLI applications
+- Use **async** for complex PDFs, OCR, and batch processing
+- Use **batch operations** for multiple files
 
-This library is open to contribution. Feel free to open issues or submit PRs. It's better to discuss issues before submitting PRs to avoid disappointment.
+For detailed benchmarks and methodology, see our [Performance Documentation](https://goldziher.github.io/kreuzberg/advanced/performance/).
 
-### Local Development
+## Contributing
 
-- Clone the repo
-- Install the system dependencies
-- Install the full dependencies with `uv sync`
-- Install the pre-commit hooks with: `pre-commit install && pre-commit install --hook-type commit-msg`
-- Make your changes and submit a PR
+We welcome contributions! Please see our [Contributing Guide](docs/contributing.md) for details on setting up your development environment and submitting pull requests.
 
 ## License