Refactor/migrate poetry to uv

.github/dependabot.yml

@@ -5,7 +5,7 @@
 
 version: 2
 updates:
-  - package-ecosystem: "pip" # See documentation for possible values
+  - package-ecosystem: "uv" # See documentation for possible values
     directory: "/" # Location of package manifests
     schedule:
       interval: "weekly"

.github/workflows/python-publish.yaml

@@ -12,41 +12,31 @@ on:
   release:
     types: [published]
 
-permissions:
-  contents: read
-
 jobs:
-  deploy:
-
+  run:
     runs-on: ubuntu-latest
-
+    environment:
+      name: pypi
+    permissions:
+      id-token: write
+      contents: read
     steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: '3.12'
-
-    - name: Install Poetry
-      run: |
-        curl -sSL https://install.python-poetry.org | python3 -
-
-    - name: Update package version
-      run: |
-        VERSION=${{ github.event.release.tag_name }}
-        sed -i 's/__version__ = ".*"/__version__ = "'${VERSION}'"/' datastew/_version.py
-        sed -i "s/^version = \".*\"/version = \"${VERSION}\"/" pyproject.toml
-
-    - name: Install dependencies
-      run: |
-        poetry install
-
-    - name: Build package
-      run: |
-        poetry build
-
-    - name: Publish package
-      env:
-        POETRY_PYPI_TOKEN_PYPI: ${{ secrets.PYPI_API_TOKEN }}
-      run: |
-        poetry publish --username __token__ --password $POETRY_PYPI_TOKEN_PYPI
+      - name: Checkout
+        uses: actions/checkout@v5
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+      - name: Install Python 3.13
+        run: uv python install 3.13
+      - name: Update package version
+        run: |
+          VERSION=${{ github.event.release.tag_name }}
+          sed -i 's/__version__ = ".*"/__version__ = "'${VERSION}'"/' datastew/_version.py
+          uv version "$VERSION"
+      - name: Build
+        run: uv build
+      - name: Smoke test (wheel)
+        run: uv run --isolated --no-project --with dist/*.whl tests/smoke_test.py
+      - name: Smoke test (source distribution)
+        run: uv run --isolated --no-project --with dist/*.tar.gz tests/smoke_test.py
+      - name: Publish
+        run: uv publish

.github/workflows/tests.yml

@@ -37,27 +37,24 @@ jobs:
       TEST_POSTGRES_URI: postgresql://testuser:testpass@localhost:5432/testdb
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 
-      - name: Install Poetry
-        run: curl -sSL https://install.python-poetry.org | python3 -
-
-      - name: Configure Poetry environment
-        run: |
-          poetry config virtualenvs.create true
-          poetry env use python${{ matrix.python-version }}
+      - name: Install the latest version of uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          python-version: ${{ matrix.python-version }}
 
       - name: Install dependencies
-        run: poetry install
+        run: uv sync --locked --all-extras --dev
 
       - name: Wait for PostgreSQL to become ready
         run: |
           until pg_isready -h localhost -U testuser -d testdb; do sleep 1; done
 
       - name: Run tests
-        run: poetry run pytest
+        run: uv run pytest tests

pyproject.toml

@@ -1,72 +1,69 @@
 [build-system]
-requires = [
-    "poetry-core>=1.0.0",
-    "setuptools>=65.0",
-    "wheel",
-]
-build-backend = "poetry.core.masonry.api"
+requires = ["uv_build>=0.9.10,<0.10.0"]
+build-backend = "uv_build"
+
+[tool.uv.build-backend]
+module-name = "datastew"
+module-root = ""
 
-[tool.poetry]
+[project]
 name = "datastew"
 version = "0.1.0"
 description = "Datastew is a python library for intelligent data harmonization using Large Language Model (LLM) vector embeddings."
-authors = ["Tim Adams <tim.adams@scai.fraunhofer.de>", "Mehmet Can Ay <mehmet.ay@scai.fraunhofer.de>"]
-license = "Apache-2.0"
 readme = "README.md"
-homepage = "https://github.com/SCAI-BIO/datastew"
-repository = "https://github.com/SCAI-BIO/datastew"
-documentation = "https://github.com/SCAI-BIO/datastew#readme"
+license = { file = "LICENSE" }
+requires-python = ">=3.10,<3.14"
+authors = [
+    { name = "Tim Adams", email = "tim.adams@scai.fraunhofer.de" },
+    { name = "Mehmet Can Ay", email = "mehmet.ay@scai.fraunhofer.de" },
+]
 keywords = ["data-harmonization", "LLM", "embeddings", "data-steward"]
 classifiers = [
     "Development Status :: 3 - Alpha",
     "Intended Audience :: Developers",
-    "License :: OSI Approved :: Apache Software License",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
     "Programming Language :: Python :: 3.13",
 ]
 
-[tool.poetry.urls]
-homepage = "https://github.com/SCAI-BIO/datastew"
-repository = "https://github.com/SCAI-BIO/datastew"
-documentation = "https://github.com/SCAI-BIO/datastew#readme"
-tracker = "https://github.com/SCAI-BIO/datastew/issues"
+dependencies = [
+    "matplotlib>=3.10.7,<4.0.0",
+    "numpy>=2.2.6,<3.0.0",
+    "openai>=2.7.1,<3.0.0",
+    "openpyxl>=3.1.5,<4.0.0",
+    "pandas>=2.3.3,<3.0.0",
+    "plotly>=6.4.0,<7.0.0",
+    "python-dateutil>=2.9.0.post0,<3.0.0",
+    "python-dotenv>=1.2.1,<2.0.0",
+    "pytz>=2025.2,<2026.0",
+    "seaborn>=0.13.2,<1.0.0",
+    "sentence-transformers>=5.1.2,<6.0.0",
+    "scikit-learn>=1.7.2,<2.0.0",
+    "six>=1.17.0,<2.0.0",
+    "thefuzz>=0.22.1,<1.0.0",
+    "tzdata>=2025.2,<2026.0",
+    "wheel>=0.45.1,<1.0.0",
+    "aiofiles>=25.1.0,<26.0.0",
+    "SQLAlchemy>=2.0.44,<3.0.0",
+    "scipy>=1.15.3,<2.0.0",
+    "pydantic>=2.12.4,<3.0.0",
+    "requests>=2.32.5,<3.0.0",
+    "uuid>=1.30,<2.0.0",
+    "weaviate-client>=4.17.0,<5.0.0",
+    "cachetools>=6.2.1,<7.0.0",
+    "ollama>=0.6.0,<1.0.0",
+    "pgvector>=0.4.1,<1.0.0",
+    "psycopg2-binary>=2.9.11,<3.0.0",
+    "torch>=2.9.0,<3.0.0",
+]
 
-[[tool.poetry.packages]]
-include = "datastew"
+[project.optional-dependencies]
+dev = ["flake8>=7.3.0,<8.0.0", "pytest>=9.0.0,<10.0.0"]
 
-[tool.poetry.dependencies]
-python = ">=3.10,<3.14"
-matplotlib = "^3.10.7"
-numpy = "^2.2.6"
-openai = "^2.7.1"
-openpyxl = "^3.1.5"
-pandas = "^2.3.3"
-plotly = "^6.4.0"
-python-dateutil = "^2.9.0.post0"
-python-dotenv = "^1.2.1"
-pytz = "^2025.2"
-seaborn = "^0.13.2"
-sentence-transformers = "^5.1.2"
-scikit-learn = "^1.7.2"
-six = "^1.17.0"
-thefuzz = "^0.22.1"
-tzdata = "^2025.2"
-wheel = "^0.45.1"
-aiofiles = "^25.1.0"
-SQLAlchemy = "^2.0.44"
-scipy = "^1.15.3"
-pydantic = "^2.12.4"
-requests = "^2.32.5"
-uuid = "^1.30"
-weaviate-client = "^4.17.0"
-cachetools = "^6.2.1"
-ollama = "^0.6.0"
-pgvector = "^0.4.1"
-psycopg2-binary = "^2.9.11"
-torch = "^2.9.0"
 
-[tool.poetry.group.dev.dependencies]
-flake8 = "^7.3.0"
-pytest = "^9.0.0"
+[project.urls]
+Homepage = "https://github.com/SCAI-BIO/datastew"
+Repository = "https://github.com/SCAI-BIO/datastew"
+Documentation = "https://github.com/SCAI-BIO/datastew#readme"
+Tracker = "https://github.com/SCAI-BIO/datastew/issues"

tests/smoke_test.py

@@ -0,0 +1,17 @@
+def test_package_imports():
+    """
+    Basic check that the installed wheel can be imported.
+    """
+    import datastew
+
+    assert datastew is not None
+
+
+def test_version_exists():
+    """
+    Ensure version metadata is accessible.
+    """
+    from datastew import __version__
+
+    assert isinstance(__version__, str)
+    assert len(__version__) > 0