Clnt-61: Fix missing permissions in GitHub actions workflows, fix dataset-optimization to data-qa API renaming & fix package vulnerabilities

.github/workflows/lint.yaml

@@ -10,6 +10,8 @@ concurrency:
 jobs:
   ruff:
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     strategy:
       matrix:
         python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
@@ -31,6 +33,8 @@ jobs:
 
   pyright:
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     strategy:
       matrix:
         python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]

.github/workflows/pytest-full.yaml

@@ -8,22 +8,24 @@ on:
 jobs:
   pytest_full:
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     strategy:
       max-parallel: 2
       matrix:
-        optimization-test:
+        data-qa-test:
           - test: classification/classification_aws_test.py
-            env: RUN_CLASSIFICATION_AWS_OPTIMIZATION
+            env: RUN_CLASSIFICATION_AWS_DATA_QA
           - test: classification/classification_gcp_test.py
-            env: RUN_CLASSIFICATION_GCP_OPTIMIZATION
+            env: RUN_CLASSIFICATION_GCP_DATA_QA
           - test: classification/sanity_gcp_test.py
-            env: RUN_CLASSIFICATION_GCP_SANITY_OPTIMIZATION
+            env: RUN_CLASSIFICATION_GCP_SANITY_DATA_QA
           - test: object-detection/od_aws_test.py
-            env: RUN_AWS_OD_OPTIMIZATION
+            env: RUN_AWS_OD_DATA_QA
           - test: object-detection/od_git_test.py
-            env: RUN_OD_GIT_OPTIMIZATION
+            env: RUN_OD_GIT_DATA_QA
           - test: tests/object-detection/sama_coco_test.py
-            env: RUN_COCO_OD_GCP_SANITY_OPTIMIZATION
+            env: RUN_COCO_OD_GCP_SANITY_DATA_QA
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python
@@ -38,7 +40,7 @@ jobs:
           source .venv/bin/activate
           pip install -r requirements/dev.txt -r requirements/polars.txt
       - name: Run PyTest
-        run: .venv/bin/pytest tests/${{ matrix.optimization-test['test'] }}
+        run: .venv/bin/pytest tests/${{ matrix.data-qa-test['test'] }}
         env:
           API_HOST: ${{ secrets.API_HOST }}
           API_KEY: ${{ secrets.API_KEY }}
@@ -47,4 +49,4 @@ jobs:
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           HUGGINGFACE_ACCESS_TOKEN: ${{ secrets.HUGGINGFACE_ACCESS_TOKEN }}
           UNIQUE_ID: ${{ github.ref }}-${{ github.run_number }}
-          ${{ matrix.optimization-test['env'] }}: true
+          ${{ matrix.data-qa-test['env'] }}: true

.github/workflows/pytest-sanity.yaml

@@ -14,6 +14,8 @@ concurrency:
 jobs:
   pytest_sanity:
     runs-on: ${{ matrix.os }}
+    permissions:
+      contents: read
     strategy:
       max-parallel: 4
       matrix:

.github/workflows/safety-scan.yml

@@ -15,6 +15,8 @@ concurrency:
 jobs:
     safety-scan:
       runs-on: ubuntu-latest
+      permissions:
+        contents: read
       steps:
         - name: Checkout hirundo-client
           uses: actions/checkout@v4

README.md

@@ -1,8 +1,8 @@
 # Hirundo
 
-This package exposes access to Hirundo APIs for dataset optimization for Machine Learning.
+This package exposes access to Hirundo APIs for dataset QA for Machine Learning.
 
-Dataset optimization is currently available for datasets labelled for classification and object detection.
+Dataset QA is currently available for datasets labelled for classification and object detection.
 
 Support dataset storage configs include:
 
@@ -73,7 +73,7 @@ Classification example:
 from hirundo import (
     HirundoCSV,
     LabelingType,
-    OptimizationDataset,
+    QADataset,
     StorageGCP,
     StorageConfig,
     StorageTypes,
@@ -84,7 +84,7 @@ gcp_bucket = StorageGCP(
     project="Hirundo-global",
     credentials_json=json.loads(os.environ["GCP_CREDENTIALS"]),
 )
-test_dataset = OptimizationDataset(
+test_dataset = QADataset(
     name="TEST-GCP cifar 100 classification dataset",
     labeling_type=LabelingType.SINGLE_LABEL_CLASSIFICATION,
     storage_config=StorageConfig(
@@ -99,7 +99,7 @@ test_dataset = OptimizationDataset(
     classes=cifar100_classes,
 )
 
-test_dataset.run_optimization()
+test_dataset.run_qa()
 results = test_dataset.check_run()
 print(results)
 ```
@@ -111,7 +111,7 @@ from hirundo import (
     GitRepo,
     HirundoCSV,
     LabelingType,
-    OptimizationDataset,
+    QADataset,
     StorageGit,
     StorageConfig,
     StorageTypes,
@@ -124,7 +124,7 @@ git_storage = StorageGit(
     ),
     branch="main",
 )
-test_dataset = OptimizationDataset(
+test_dataset = QADataset(
     name="TEST-HuggingFace-BDD-100k-validation-OD-validation-dataset",
     labeling_type=LabelingType.OBJECT_DETECTION,
     storage_config=StorageConfig(
@@ -140,7 +140,7 @@ test_dataset = OptimizationDataset(
     ),
 )
 
-test_dataset.run_optimization()
+test_dataset.run_qa()
 results = test_dataset.check_run()
 print(results)
 ```

docs/hirundo.dataset_optimization.rst

@@ -1,10 +1,10 @@
 .. meta::
    :http-equiv=Content-Security-Policy: default-src 'self', frame-ancestors 'none'
 
-hirundo.dataset\_optimization module
+hirundo.dataset\_qa module
 ====================================
 
-.. automodule:: hirundo.dataset_optimization
+.. automodule:: hirundo.dataset_qa
    :members:
    :undoc-members:
    :show-inheritance:

docs/hirundo.rst

@@ -11,7 +11,7 @@ Submodules
    :maxdepth: 4
 
    hirundo.cli
-   hirundo.dataset_optimization
+   hirundo.dataset_qa
    hirundo.enum
    hirundo.git
    hirundo.storage

hirundo/__init__.py

@@ -3,13 +3,15 @@
     LabelingType,
     StorageTypes,
 )
-from .dataset_optimization import (
+from .dataset_qa import (
+    ClassificationRunArgs,
+    Domain,
     HirundoError,
-    OptimizationDataset,
+    ObjectDetectionRunArgs,
+    QADataset,
     RunArgs,
-    VisionRunArgs,
 )
-from .dataset_optimization_results import DatasetOptimizationResults
+from .dataset_qa_results import DatasetQAResults
 from .git import GitPlainAuth, GitRepo, GitSSHAuth
 from .labeling import (
     COCO,
@@ -40,9 +42,11 @@
     "KeylabsObjDetVideo",
     "KeylabsObjSegImages",
     "KeylabsObjSegVideo",
-    "OptimizationDataset",
+    "QADataset",
+    "Domain",
     "RunArgs",
-    "VisionRunArgs",
+    "ClassificationRunArgs",
+    "ObjectDetectionRunArgs",
     "DatasetMetadataType",
     "LabelingType",
     "GitPlainAuth",
@@ -54,7 +58,7 @@
     # "StorageAzure",  TODO: Azure storage is coming soon
     "StorageGit",
     "StorageConfig",
-    "DatasetOptimizationResults",
+    "DatasetQAResults",
     "load_df",
     "load_from_zip",
 ]

hirundo/_constraints.py

@@ -11,7 +11,7 @@
 
 if TYPE_CHECKING:
     from hirundo._urls import HirundoUrl
-    from hirundo.dataset_optimization import LabelingInfo
+    from hirundo.dataset_qa import LabelingInfo
     from hirundo.storage import (
         ResponseStorageConfig,
         StorageConfig,

hirundo/cli.py

@@ -198,9 +198,9 @@ def check_run(
     """
     Check the status of a run.
     """
-    from hirundo.dataset_optimization import OptimizationDataset
+    from hirundo.dataset_qa import QADataset
 
-    results = OptimizationDataset.check_run_by_id(run_id)
+    results = QADataset.check_run_by_id(run_id)
     print(f"Run results saved to {results.cached_zip_path}")
 
 
@@ -209,9 +209,9 @@ def list_runs():
     """
     List all runs available.
     """
-    from hirundo.dataset_optimization import OptimizationDataset
+    from hirundo.dataset_qa import QADataset
 
-    runs = OptimizationDataset.list_runs()
+    runs = QADataset.list_runs()
 
     console = Console()
     table = Table(