chore: add pre-commit hooks and lint code (#2)

Author: masci

.github/workflows/lint.yml

@@ -0,0 +1,20 @@
+name: Linting
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+
+      - name: Run linter
+        shell: bash
+        run: uv run -- pre-commit run -a

.github/workflows/publish_release.yml

@@ -18,7 +18,7 @@ jobs:
       - uses: actions/checkout@v4
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@v6
 
       - name: Build and publish
         env:

.pre-commit-config.yaml

@@ -0,0 +1,59 @@
+---
+default_language_version:
+  python: python3
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-byte-order-marker
+      - id: check-merge-conflict
+      - id: check-toml
+      - id: check-yaml
+        args: [--allow-multiple-documents]
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+      - id: trailing-whitespace
+
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.11.13
+    hooks:
+      - id: ruff-format
+      - id: ruff-check
+        args: [--fix, --exit-non-zero-on-fix]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.15.0
+    hooks:
+      - id: mypy
+        additional_dependencies:
+          [
+            "types-Deprecated",
+            "types-PyYAML",
+            "types-botocore",
+            "types-aiobotocore",
+            "types-protobuf==4.24.0.4",
+            "types-redis",
+            "types-requests",
+            "types-setuptools",
+            "types-click",
+          ]
+        args:
+          [
+            --disallow-untyped-defs,
+            --ignore-missing-imports,
+            --python-version=3.11,
+          ]
+        # exclude: ^(examples/|e2e_tests/|tests/message_queues/test_aws.py)
+
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        additional_dependencies: [tomli]
+
+  - repo: https://github.com/pappasam/toml-sort
+    rev: v0.23.1
+    hooks:
+      - id: toml-sort-fix

pyproject.toml

@@ -2,19 +2,24 @@
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 
+[dependency-groups]
+dev = [
+  "pre-commit>=4.2.0",
+  "pytest>=8.4.0",
+  "pytest-asyncio>=1.0.0",
+  "pytest-cov>=6.1.1"
+]
+
 [project]
 name = "llama-index-workflows"
 version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"
 dependencies = [
-    "llama-index-instrumentation>=0.1.0",
-    "pydantic>=2.11.5",
+  "llama-index-instrumentation>=0.1.0",
+  "pydantic>=2.11.5"
 ]
 
-[dependency-groups]
-dev = ["pytest>=8.4.0", "pytest-asyncio>=1.0.0", "pytest-cov>=6.1.1"]
-
 [tool.hatch.build.targets.wheel]
 packages = ["src/workflows"]

src/workflows/service.py

@@ -23,7 +23,7 @@ def __init__(self) -> None:
     def get(self, name: str, default: Optional["Workflow"] = None) -> "Workflow":
         try:
             return self._services[name]
-        except KeyError as e:
+        except KeyError:
             if default:
                 return default
 

src/workflows/utils.py

@@ -171,7 +171,7 @@ def get_steps_from_class(_class: object) -> Dict[str, Callable]:
         Dict[str, Callable]: A dictionary mapping step names to their corresponding methods.
 
     """
-    step_methods = {}
+    step_methods: dict[str, Callable] = {}
     all_methods = inspect.getmembers(_class, predicate=inspect.isfunction)
 
     for name, method in all_methods:
@@ -192,7 +192,7 @@ def get_steps_from_instance(workflow: object) -> Dict[str, Callable]:
         Dict[str, Callable]: A dictionary mapping step names to their corresponding methods.
 
     """
-    step_methods = {}
+    step_methods: dict[str, Callable] = {}
     all_methods = inspect.getmembers(workflow, predicate=inspect.ismethod)
 
     for name, method in all_methods:
@@ -315,8 +315,8 @@ def import_module_from_qualified_name(qualified_name: str) -> Any:
     if not qualified_name or "." not in qualified_name:
         raise ValueError("Qualified name must be in format 'module.attribute'")
 
+    module_path = qualified_name.rsplit(".", 1)
     try:
-        module_path = qualified_name.rsplit(".", 1)
         module = import_module(module_path[0])
         return getattr(module, module_path[1])
     except ImportError as e:

tests/conftest.py

@@ -34,15 +34,15 @@ async def end_step(self, ev: LastEvent) -> StopEvent:
 
 
 @pytest.fixture()
-def workflow():
+def workflow() -> Workflow:
     return DummyWorkflow()
 
 
 @pytest.fixture()
-def events():
+def events() -> list:
     return [OneTestEvent, AnotherTestEvent]
 
 
 @pytest.fixture()
-def ctx():
+def ctx() -> Context:
     return Context(workflow=DummyWorkflow())

tests/test_checkpointer.py

@@ -16,12 +16,12 @@
 
 
 @pytest.fixture()
-def workflow_checkpointer(workflow: DummyWorkflow):
+def workflow_checkpointer(workflow: DummyWorkflow) -> WorkflowCheckpointer:
     return WorkflowCheckpointer(workflow=workflow)
 
 
 @pytest.mark.asyncio
-async def test_create_checkpoint(workflow_checkpointer: WorkflowCheckpointer):
+async def test_create_checkpoint(workflow_checkpointer: WorkflowCheckpointer) -> None:
     incoming_ev = StartEvent()
     output_ev = OneTestEvent()
     ctx = Context(workflow=workflow_checkpointer.workflow)
@@ -48,7 +48,7 @@ async def test_create_checkpoint(workflow_checkpointer: WorkflowCheckpointer):
 @pytest.mark.asyncio
 async def test_checkpoints_after_successive_runs(
     workflow_checkpointer: WorkflowCheckpointer,
-):
+) -> None:
     num_steps = len(workflow_checkpointer.workflow._get_steps())
     num_runs = 2
 
@@ -67,7 +67,7 @@ async def test_checkpoints_after_successive_runs(
 
 
 @pytest.mark.asyncio
-async def test_filter_checkpoints(workflow_checkpointer: WorkflowCheckpointer):
+async def test_filter_checkpoints(workflow_checkpointer: WorkflowCheckpointer) -> None:
     num_runs = 2
     for _ in range(num_runs):
         handler: WorkflowHandler = workflow_checkpointer.run()
@@ -106,11 +106,11 @@ async def test_filter_checkpoints(workflow_checkpointer: WorkflowCheckpointer):
 @pytest.mark.asyncio
 async def test_checkpoints_works_with_new_instances_concurrently(
     workflow_checkpointer: WorkflowCheckpointer,
-):
+) -> None:
     num_instances = 3
     tasks = []
 
-    async def add_random_startup(coro: WorkflowHandler):
+    async def add_random_startup(coro: WorkflowHandler) -> None:
         """To randomly mix up the processing of the 3 runs."""
         startup = random.random()
         await asyncio.sleep(startup)
@@ -134,7 +134,7 @@ async def add_random_startup(coro: WorkflowHandler):
 
 
 @pytest.mark.asyncio
-async def test_run_from_checkpoint(workflow_checkpointer: WorkflowCheckpointer):
+async def test_run_from_checkpoint(workflow_checkpointer: WorkflowCheckpointer) -> None:
     num_steps = len(workflow_checkpointer.workflow._get_steps())
     num_ckpts_in_single_run = num_steps - 1
     handler: WorkflowHandler = workflow_checkpointer.run()
@@ -146,7 +146,7 @@ async def test_run_from_checkpoint(workflow_checkpointer: WorkflowCheckpointer):
     ckpt = workflow_checkpointer.filter_checkpoints(last_completed_step="middle_step")[
         0
     ]
-    handler: WorkflowHandler = workflow_checkpointer.run_from(checkpoint=ckpt)
+    handler = workflow_checkpointer.run_from(checkpoint=ckpt)
     await handler
 
     assert len(workflow_checkpointer.checkpoints) == 2
@@ -164,7 +164,7 @@ async def test_run_from_checkpoint(workflow_checkpointer: WorkflowCheckpointer):
 async def test_checkpointer_with_stepwise(
     mock_uuid: MagicMock,
     workflow_checkpointer: WorkflowCheckpointer,
-):
+) -> None:
     # -------------------------------
     # Stepwise run with checkpointing
     stepwise_run_id = "stepwise_run"
@@ -219,7 +219,7 @@ async def test_checkpointer_with_stepwise(
 async def test_disable_and_enable_checkpoints(
     mock_uuid: MagicMock,
     workflow_checkpointer: WorkflowCheckpointer,
-):
+) -> None:
     run_ids = ["42", "84"]
     mock_uuid.uuid4.side_effect = run_ids