Add CI checks for formatting + clean up CI

.github/workflows/code-formatting.yml

@@ -0,0 +1,41 @@
+name: Code Formatting
+
+on:
+  workflow_call:
+  push:
+    branches:
+      - main
+
+jobs:
+  formatting-check:
+    name: Code Formatting Check
+    runs-on: ubuntu-latest
+    if: github.event.pull_request.draft == false
+    env:
+      ZENML_DEBUG: 1
+      ZENML_ANALYTICS_OPT_IN: false
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.9'
+
+      - name: Install latest ruff
+        run: pip install --upgrade ruff
+
+      - name: Run formatting script
+        run: bash scripts/format.sh
+
+      - name: Check for changes
+        id: git-check
+        run: |
+          git diff --exit-code || echo "changes=true" >> $GITHUB_OUTPUT
+
+      - name: Fail if changes were made
+        if: steps.git-check.outputs.changes == 'true'
+        run: |
+          echo "::error::Formatting check failed. Please run 'scripts/format.sh' locally and commit the changes."
+          exit 1

.github/workflows/pull_request.yml

@@ -1,4 +1,4 @@
-name: Spell Checking
+name: Pull Request Checks
 
 on:
   pull_request:
@@ -25,3 +25,11 @@ jobs:
   markdown-link-check:
     uses: ./.github/workflows/markdown-link-check.yml
     if: github.event.pull_request.draft == false
+
+  code-formatting-check:
+    uses: ./.github/workflows/code-formatting.yml
+    if: github.event.pull_request.draft == false
+
+  readme-projects-check:
+    uses: ./.github/workflows/readme-projects-check.yml
+    if: github.event.pull_request.draft == false

.github/workflows/readme-projects-check.yml

@@ -0,0 +1,21 @@
+name: README Projects Check
+
+on:
+  workflow_call:
+
+jobs:
+  readme-projects-check:
+    name: Check Projects in README
+    runs-on: ubuntu-latest
+    if: github.event.pull_request.draft == false
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.9'
+
+      - name: Run README projects check
+        run: python3 scripts/check_readme_projects.py

.gitignore

@@ -167,3 +167,6 @@ finetuned-snowflake-arctic-embed-m-v1.5/
 
 # ollama ignores
 nohup.out
+
+# Claude
+.claude/

CONTRIBUTING.md

@@ -99,10 +99,23 @@ the ["fork-and-pull" Git workflow](https://github.com/susam/gitpr)
 4. Checkout the **main** branch <- `git checkout main`.
 5. Create a branch locally off the **main** branch with a succinct but descriptive name.
 6. Commit changes to the branch.
-7. Push changes to your fork.
-8. Open a PR in our repository to the `main` branch and
+7. Format your code by running `bash scripts/format.sh` before committing.
+8. Push changes to your fork.
+9. Open a PR in our repository to the `main` branch and
    follow the PR template so that we can efficiently review the changes.
 
+#### Code Formatting
+
+All code must pass our formatting checks before it can be merged. We use [ruff](https://github.com/astral-sh/ruff) for code formatting and linting.
+
+To format your code locally:
+```bash
+# Run from the project root
+bash scripts/format.sh
+```
+
+Our CI pipeline automatically checks if your code is properly formatted. If the check fails, you'll need to run the formatting script locally and commit the changes before your PR can be merged.
+
 ### 🚨 Reporting a Vulnerability
 
 If you think you have found a vulnerability, and even if you are not sure about it,

README.md

@@ -88,6 +88,15 @@ installation details.
 We welcome contributions from anyone to showcase your project built using ZenML.
 See our [contributing guide](./CONTRIBUTING.md) to start.
 
+## Code Quality
+
+All code contributions must pass our automated code quality checks:
+- **Code Formatting**: We use [ruff](https://github.com/astral-sh/ruff) for code formatting and linting
+- **Spelling**: We check for typos and spelling errors
+- **Markdown Links**: We verify that all links in documentation work properly
+
+Our CI pipeline will automatically check your PR for these issues. Remember to run `bash scripts/format.sh` locally before submitting your PR to ensure it passes the formatting checks.
+
 # 🆘 Getting Help
 
 By far the easiest and fastest way to get help is to:

databricks-production-qa-demo/steps/deployment/deployment_deploy.py

@@ -31,14 +31,10 @@
 
 
 @step(enable_cache=False)
-def deployment_deploy() -> (
-    Annotated[
-        Optional[DatabricksDeploymentService],
-        ArtifactConfig(
-            name="databricks_deployment", is_deployment_artifact=True
-        ),
-    ]
-):
+def deployment_deploy() -> Annotated[
+    Optional[DatabricksDeploymentService],
+    ArtifactConfig(name="databricks_deployment", is_deployment_artifact=True),
+]:
     """Predictions step.
 
     This is an example of a predictions step that takes the data in and returns

gamesense/steps/log_metadata.py

@@ -15,7 +15,6 @@
 # limitations under the License.
 #
 
-from typing import Any, Dict
 
 from zenml import get_step_context, log_metadata, step
 
@@ -33,9 +32,8 @@ def log_metadata_from_step_artifact(
     """
 
     context = get_step_context()
-    metadata_dict: Dict[str, Any] = context.pipeline_run.steps[
-        step_name
-    ].outputs[artifact_name]
+    # Access the artifact metadata but don't store the unused variable
+    _ = context.pipeline_run.steps[step_name].outputs[artifact_name]
 
     log_metadata(
         artifact_name=artifact_name,

huggingface-sagemaker/steps/deploying/huggingface_deployment.py

@@ -47,7 +47,9 @@ def deploy_to_huggingface(
     save_model_to_deploy.entrypoint()
 
     logger.info("Model saved locally. Pushing to HuggingFace...")
-    assert secret, "No secret found with name 'huggingface_creds'. Please create one with your `token`."
+    assert secret, (
+        "No secret found with name 'huggingface_creds'. Please create one with your `token`."
+    )
 
     token = secret.secret_values["token"]
     api = HfApi(token=token)

huggingface-sagemaker/steps/promotion/promote_get_metrics.py

@@ -27,12 +27,10 @@
 
 
 @step
-def promote_get_metrics() -> (
-    Tuple[
-        Annotated[Dict[str, Any], "latest_metrics"],
-        Annotated[Dict[str, Any], "current_metrics"],
-    ]
-):
+def promote_get_metrics() -> Tuple[
+    Annotated[Dict[str, Any], "latest_metrics"],
+    Annotated[Dict[str, Any], "current_metrics"],
+]:
     """Get metrics for comparison for promoting a model.
 
     This is an example of a metric retrieval step. It is used to retrieve

llm-complete-guide/steps/eval_retrieval.py

@@ -275,9 +275,9 @@ def perform_small_retrieval_evaluation(use_reranking: bool) -> float:
 
 
 @step
-def retrieval_evaluation_small() -> (
-    Annotated[float, "small_failure_rate_retrieval"]
-):
+def retrieval_evaluation_small() -> Annotated[
+    float, "small_failure_rate_retrieval"
+]:
     """Executes the retrieval evaluation step without reranking.
 
     Returns:
@@ -287,9 +287,9 @@ def retrieval_evaluation_small() -> (
 
 
 @step
-def retrieval_evaluation_small_with_reranking() -> (
-    Annotated[float, "small_failure_rate_retrieval_reranking"]
-):
+def retrieval_evaluation_small_with_reranking() -> Annotated[
+    float, "small_failure_rate_retrieval_reranking"
+]:
     """Executes the retrieval evaluation step with reranking.
 
     Returns: