ci: add action for python linting and formatting

.github/workflows/lint.yml

@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: Apache-2.0
+
+name: Lint, Format, and MyPy
+
+on:
+  push:
+    branches:
+      - "main"
+      - "release-**"
+    paths:
+      - '**.py'
+      - 'pyproject.toml'
+      - 'requirements*.txt'
+      - 'tox.ini'
+      - 'scripts/*.sh'
+      - '.github/**'
+  pull_request:
+    branches:
+      - "main"
+      - "release-**"
+    paths:
+      - '**.py'
+      - 'pyproject.toml'
+      - 'requirements*.txt'
+      - 'tox.ini'
+      - 'scripts/*.sh'
+      - '.github/**'
+
+env:
+  PYTHON_VERSION: 3.11
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          # https://github.com/actions/checkout/issues/249
+          fetch-depth: 0
+          submodules: true
+
+      - name: Setup Python 3.11
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.11
+          cache: pip
+          cache-dependency-path: |
+            **/pyproject.toml
+            **/requirements*.txt
+
+      - name: Install dependencies
+        id: deps
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install tox
+
+      - name: Run Ruff check
+        run: |
+          tox -e ruff -- check
+
+      - name: Run linting
+        if: ${{ !cancelled() && (steps.deps.outcome == 'success') }}
+        run: |
+          echo "::add-matcher::.github/workflows/matchers/pylint.json"
+          tox -e lint
+
+      - name: Run mypy type checks
+        if: ${{ !cancelled() && (steps.deps.outcome == 'success') }}
+        run: |
+          tox -e mypy

.github/workflows/matchers/pylint.json

@@ -0,0 +1,33 @@
+{
+    "problemMatcher": [
+      {
+        "owner": "pylint-error",
+        "severity": "error",
+        "pattern": [
+          {
+            "regexp": "^(.+):(\\d+):(\\d+):\\s(([EF]\\d{4}):\\s.+)$",
+            "file": 1,
+            "line": 2,
+            "column": 3,
+            "message": 4,
+            "code": 5
+          }
+        ]
+      },
+      {
+        "owner": "pylint-warning",
+        "severity": "warning",
+        "pattern": [
+          {
+            "regexp": "^(.+):(\\d+):(\\d+):\\s(([CRW]\\d{4}):\\s.+)$",
+            "file": 1,
+            "line": 2,
+            "column": 3,
+            "message": 4,
+            "code": 5
+          }
+        ]
+      }
+    ]
+  }
+

Makefile

@@ -63,5 +63,5 @@ spellcheck-sort: .spellcheck-en-custom.txt ## Sort spellcheck directory
 	sort -d -f -o $< $<
 
 .PHONY: verify
-verify: check-tox ## Run linting and formatting checks via tox
-	tox p -e ruff,fastlint,spellcheck
+verify: check-tox ## Run linting, typing, and formatting checks via tox
+	tox p -e fastlint,mypy,ruff

pyproject.toml

@@ -38,7 +38,7 @@ source = "https://github.com/instructlab/sdg"
 issues = "https://github.com/instructlab/sdg/issues"
 
 [tool.setuptools_scm]
-version_file = "src/sdg/_version.py"
+version_file = "src/instructlab_sdg/_version.py"
 # do not include +gREV local version, required for Test PyPI upload
 local_scheme = "no-local-version"
 
@@ -103,3 +103,12 @@ from-first = true
 # import-heading-firstparty=First Party
 # import-heading-localfolder=Local
 known-local-folder = ["tuning"]
+
+[tool.mypy]
+disable_error_code = ["import-not-found", "import-untyped"]
+exclude = [
+    "^src/instructlab_sdg/generate_data\\.py$",
+    "^src/instructlab_sdg/utils\\.py$",
+]
+# honor excludes by not following there through imports
+follow_imports = "silent"

requirements-dev.txt

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # TODO: Uncomment below line once requirements.txt is created
-# -r requirements.txt
+-r requirements.txt
 
 pre-commit>=3.0.4,<4.0
 pylint>=2.16.2,<4.0

requirements.txt

@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: Apache-2.0
+click>=8.1.7,<9.0.0
+httpx>=0.25.0,<1.0.0
+jinja2
+openai>=1.13.3,<2.0.0
+rouge_score
+tqdm>=4.66.2,<5.0.0
+# TODO: remove 'instructlab' once https://github.com/instructlab/sdg/issues/6 is resolved
+instructlab

src/instructlab_sdg/__init__.py

@@ -1 +1,2 @@
+# First Party
 from instructlab_sdg.generate_data import generate_data

src/instructlab_sdg/generate_data.py

@@ -1,30 +1,33 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # Standard
+from datetime import datetime
+from functools import partial
+from pathlib import Path
+from typing import Optional
 import json
 import multiprocessing
 import os
 import random
 import re
 import string
 import time
-from datetime import datetime
-from functools import partial
-from pathlib import Path
-from typing import Optional
 
-import click
-import tqdm
-# instructlab - All of these need to go away - issue #6
-from instructlab.config import (DEFAULT_MULTIPROCESSING_START_METHOD,
-                                get_model_family)
-from instructlab.utils import (chunk_document, max_seed_example_tokens,
-                               num_chars_from_tokens, read_taxonomy)
 # Third Party
+# instructlab - All of these need to go away - issue #6
+from instructlab.config import DEFAULT_MULTIPROCESSING_START_METHOD, get_model_family
+from instructlab.utils import (
+    chunk_document,
+    max_seed_example_tokens,
+    num_chars_from_tokens,
+    read_taxonomy,
+)
 from jinja2 import Template
 from rouge_score import rouge_scorer
+import click
+import tqdm
 
-# Local
+# First Party
 from instructlab_sdg import utils
 
 DEFAULT_PROMPT_TEMPLATE_MERLINITE = """\

src/instructlab_sdg/utils.py

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # Standard
+from typing import Optional, Sequence, Union
 import copy
 import dataclasses
 import io
@@ -9,14 +10,13 @@
 import math
 import os
 import sys
-from typing import Optional, Sequence, Union
 
-import httpx
+# Third Party
 # instructlab - TODO these need to go away, issue #6
 from instructlab.config import DEFAULT_API_KEY, DEFAULT_MODEL_OLD
 from instructlab.utils import get_sysprompt
-# Third Party
 from openai import OpenAI, OpenAIError
+import httpx
 
 StrOrOpenAIObject = Union[str, object]
 

tox.ini

@@ -3,7 +3,7 @@
 [tox]
 # py3-unit runs unit tests with 'python3'
 # py311-unit runs the same tests with 'python3.11'
-envlist = ruff, lint, spellcheck
+envlist = ruff, lint, mypy, spellcheck
 minversion = 4.4
 
 # format, check, and linting targets don't build and install the project to
@@ -49,3 +49,13 @@ commands =
     sh -c 'command -v aspell || (echo "aspell is not installed. Please install it." && exit 1)'
     {envpython} -m pyspelling --config {toxinidir}/.spellcheck.yml --spellchecker aspell
 allowlist_externals = sh
+
+[testenv:mypy]
+description = Python type checking with mypy
+deps =
+  mypy>=1.10.0,<2.0
+  types-tqdm
+  types-PyYAML
+  pytest
+commands =
+  mypy src