Migrated codebase to fmcore, added Ruff formatter, and GitHub workflows.

.github/workflows/linting.yml

@@ -0,0 +1,15 @@
+name: Linting
+
+on: [push, pull_request]
+
+jobs:
+  ruff-formatter:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: astral-sh/ruff-action@v3
+        with:
+          version: '0.9.2'
+          args: format --check
+          src: './src'

.github/workflows/release.yml

@@ -0,0 +1,47 @@
+name: release
+
+on:
+  release:
+    types:
+    - published  # Published through GitHub UI: https://github.com/amazon-science/synthesizrr/releases/new
+
+jobs:
+  pypi:
+    runs-on: ubuntu-latest
+    if: >
+      ${{ github.event.workflow_run.conclusion == 'success' &&
+          github.event.workflow_run.head_branch == 'main' }}
+    steps:
+    - name: Checkout Repository
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 0  # Required for Git versioning
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.11"
+
+    - name: Install Hatch & Twine
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install uv 
+        python -m uv pip install hatch twine 
+
+    - name: Verify Version from Git Tag
+      run: hatch version
+
+    - name: Build Package
+      run: hatch build
+
+    - name: Publish to Test PyPI
+      env:
+        TWINE_USERNAME: "__token__"
+        TWINE_PASSWORD: ${{ secrets.TEST_PYPI_API_TOKEN }}
+      run: twine upload --repository testpypi dist/*
+
+    - name: Publish to PyPI
+      env:
+        TWINE_USERNAME: "__token__"
+        TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+      run: twine upload --repository pypi dist/*

.github/workflows/tests.yml

@@ -0,0 +1,32 @@
+name: tests
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out repo
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+
+      - name: Install test requirements
+        # Install package dependencies:
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install --upgrade uv
+          python -m uv pip install --upgrade pytest
+          python -m uv pip install -e .
+
+      - name: Run tests
+        run: |
+          pytest tests/

pyproject.toml

@@ -0,0 +1,58 @@
+[build-system]
+requires = ["hatchling", "hatch-vcs"]
+build-backend = "hatchling.build"
+
+[project]
+name = "synthesizrr"
+dynamic = ["version"]
+authors = [
+    { name = "Abhishek Divekar", email = "[email protected]" }
+]
+description = "Synthesizing realistic and diverse text-datasets from augmented LLMs."
+readme = "README.md"
+requires-python = ">=3.11"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+license-files = ["LICENSE"]
+dependencies = [
+    "fmcore[all]",
+]
+
+[tool.hatch.version]
+source = "vcs"
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+
+[tool.ruff]
+line-length = 110
+fix = true
+force-exclude = true
+extend-exclude = [
+    "__init__.py",
+]
+
+[tool.ruff.lint]
+fixable = [
+    "I",    # Add all rules under isort linter: https://docs.astral.sh/ruff/rules/#isort-i
+    "W",    # Add all rules under whitespace: https://docs.astral.sh/ruff/rules/#warning-w
+    "E401", # multiple-imports-on-one-line: https://docs.astral.sh/ruff/rules/multiple-imports-on-one-line/
+    "E713", # not-in-test: https://docs.astral.sh/ruff/rules/not-in-test/
+    "E721", # type-comparison: https://docs.astral.sh/ruff/rules/type-comparison/
+    "E722", # bare-except: https://docs.astral.sh/ruff/rules/bare-except/
+    "F401", # unused-import: https://docs.astral.sh/ruff/rules/unused-import/
+    "F541", # f-string-missing-placeholders: https://docs.astral.sh/ruff/rules/f-string-missing-placeholders/
+    "F811", # redefined-while-unused: https://docs.astral.sh/ruff/rules/redefined-while-unused/
+    "F841", # unused-variable: https://docs.astral.sh/ruff/rules/unused-variable/
+]
+ignore = [
+    ## Ignored because it makes the code too verbose:
+    "E731", # lambda-assignment: https://docs.astral.sh/ruff/rules/lambda-assignment/
+    "E741", # ambiguous-variable-name: https://docs.astral.sh/ruff/rules/ambiguous-variable-name/
+
+    ## Ignored because of bad interaction with `from typing import *`
+    "F405", # undefined-local-with-import-star-usage: https://docs.astral.sh/ruff/rules/undefined-local-with-import-star-usage/
+    "F403", # undefined-local-with-import-star: https://docs.astral.sh/ruff/rules/undefined-local-with-import-star/
+]