hirundo 0.1.18__tar.gz → 0.1.21__tar.gz

{hirundo-0.1.18 → hirundo-0.1.21}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hirundo
-Version: 0.1.18
+Version: 0.1.21
 Summary: This package is used to interface with Hirundo's platform. It provides a simple API to optimize your ML datasets.
 Author-email: Hirundo <dev@hirundo.io>
 License: MIT License
@@ -13,7 +13,7 @@ License: MIT License
         
         THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
         
-Project-URL: Homepage, https://github.com/Hirundo-io/hirundo-client
+Project-URL: Homepage, https://github.com/Hirundo-io/hirundo-python-sdk
 Keywords: dataset,machine learning,data science,data engineering
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python
@@ -32,6 +32,10 @@ Requires-Dist: httpx>=0.27.0
 Requires-Dist: stamina>=24.2.0
 Requires-Dist: httpx-sse>=0.4.0
 Requires-Dist: tqdm>=4.66.5
+Requires-Dist: h11>=0.16.0
+Requires-Dist: requests>=2.32.4
+Requires-Dist: urllib3>=2.5.0
+Requires-Dist: setuptools>=78.1.1
 Provides-Extra: dev
 Requires-Dist: pyyaml>=6.0.1; extra == "dev"
 Requires-Dist: types-PyYAML>=6.0.12; extra == "dev"
@@ -46,13 +50,15 @@ Requires-Dist: stamina>=24.2.0; extra == "dev"
 Requires-Dist: httpx-sse>=0.4.0; extra == "dev"
 Requires-Dist: pytest>=8.2.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.23.6; extra == "dev"
-Requires-Dist: uv>=0.5.8; extra == "dev"
+Requires-Dist: uv>=0.8.6; extra == "dev"
 Requires-Dist: pre-commit>=3.7.1; extra == "dev"
 Requires-Dist: virtualenv>=20.6.6; extra == "dev"
-Requires-Dist: ruff>=0.11.6; extra == "dev"
+Requires-Dist: ruff>=0.12.0; extra == "dev"
 Requires-Dist: bumpver; extra == "dev"
 Requires-Dist: platformdirs>=4.3.6; extra == "dev"
 Requires-Dist: safety>=3.2.13; extra == "dev"
+Requires-Dist: cryptography>=44.0.1; extra == "dev"
+Requires-Dist: jinja2>=3.1.6; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: sphinx>=7.4.7; extra == "docs"
 Requires-Dist: sphinx-autobuild>=2024.9.3; extra == "docs"
@@ -61,8 +67,9 @@ Requires-Dist: autodoc_pydantic>=2.2.0; extra == "docs"
 Requires-Dist: furo; extra == "docs"
 Requires-Dist: sphinx-multiversion; extra == "docs"
 Requires-Dist: esbonio; extra == "docs"
-Requires-Dist: starlette>0.40.0; extra == "docs"
+Requires-Dist: starlette>=0.47.2; extra == "docs"
 Requires-Dist: markupsafe>=3.0.2; extra == "docs"
+Requires-Dist: jinja2>=3.1.6; extra == "docs"
 Provides-Extra: pandas
 Requires-Dist: pandas>=2.2.3; extra == "pandas"
 Provides-Extra: polars
@@ -71,9 +78,9 @@ Dynamic: license-file
 
 # 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:
 
@@ -144,7 +151,7 @@ Classification example:
 from hirundo import (
     HirundoCSV,
     LabelingType,
-    OptimizationDataset,
+    QADataset,
     StorageGCP,
     StorageConfig,
     StorageTypes,
@@ -155,7 +162,7 @@ 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(
@@ -170,7 +177,7 @@ test_dataset = OptimizationDataset(
     classes=cifar100_classes,
 )
 
-test_dataset.run_optimization()
+test_dataset.run_qa()
 results = test_dataset.check_run()
 print(results)
 ```
@@ -182,7 +189,7 @@ from hirundo import (
     GitRepo,
     HirundoCSV,
     LabelingType,
-    OptimizationDataset,
+    QADataset,
     StorageGit,
     StorageConfig,
     StorageTypes,
@@ -195,7 +202,7 @@ 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(
@@ -211,7 +218,7 @@ test_dataset = OptimizationDataset(
     ),
 )
 
-test_dataset.run_optimization()
+test_dataset.run_qa()
 results = test_dataset.check_run()
 print(results)
 ```
@@ -220,4 +227,4 @@ Note: Currently we only support the main CPython release 3.9, 3.10, 3.11, 3.12 &
 
 ## Further documentation
 
-To learn more about how to use this library, please visit the [http://docs.hirundo.io/](documentation) or see the [Google Colab examples](https://github.com/Hirundo-io/hirundo-client/tree/main/notebooks).
+To learn more about how to use this library, please visit the [http://docs.hirundo.io/](documentation) or see the [Google Colab examples](https://github.com/Hirundo-io/hirundo-python-sdk/tree/main/notebooks).

{hirundo-0.1.18 → hirundo-0.1.21}/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)
 ```
@@ -149,4 +149,4 @@ Note: Currently we only support the main CPython release 3.9, 3.10, 3.11, 3.12 &
 
 ## Further documentation
 
-To learn more about how to use this library, please visit the [http://docs.hirundo.io/](documentation) or see the [Google Colab examples](https://github.com/Hirundo-io/hirundo-client/tree/main/notebooks).
+To learn more about how to use this library, please visit the [http://docs.hirundo.io/](documentation) or see the [Google Colab examples](https://github.com/Hirundo-io/hirundo-python-sdk/tree/main/notebooks).

{hirundo-0.1.18 → hirundo-0.1.21}/hirundo/__init__.py

@@ -3,13 +3,15 @@ from .dataset_enum import (
     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 @@ __all__ = [
     "KeylabsObjDetVideo",
     "KeylabsObjSegImages",
     "KeylabsObjSegVideo",
-    "OptimizationDataset",
+    "QADataset",
+    "Domain",
     "RunArgs",
-    "VisionRunArgs",
+    "ClassificationRunArgs",
+    "ObjectDetectionRunArgs",
     "DatasetMetadataType",
     "LabelingType",
     "GitPlainAuth",
@@ -54,9 +58,9 @@ __all__ = [
     # "StorageAzure",  TODO: Azure storage is coming soon
     "StorageGit",
     "StorageConfig",
-    "DatasetOptimizationResults",
+    "DatasetQAResults",
     "load_df",
     "load_from_zip",
 ]
 
-__version__ = "0.1.18"
+__version__ = "0.1.21"

{hirundo-0.1.18 → hirundo-0.1.21}/hirundo/_constraints.py

@@ -11,7 +11,7 @@ from hirundo.labeling import COCO, YOLO, HirundoCSV, Keylabs
 
 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-0.1.18 → hirundo-0.1.21}/hirundo/_headers.py

@@ -1,6 +1,6 @@
 from hirundo._env import API_KEY, check_api_key
 
-HIRUNDO_API_VERSION = "0.2"
+HIRUNDO_API_VERSION = "0.3"
 
 _json_headers = {
     "Content-Type": "application/json",

hirundo-0.1.21/hirundo/_http.py

@@ -0,0 +1,72 @@
+import requests as _requests
+from requests import Response
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
+
+import hirundo.logger
+
+logger = hirundo.logger.get_logger(__name__)
+
+MINIMUM_CLIENT_SERVER_ERROR_CODE = 400
+
+
+def _build_retrying_session() -> _requests.Session:
+    # No more than 10 tries total (including the initial attempt)
+    # urllib3 Retry.total counts retries, not total attempts, so use 9 retries
+    retries = Retry(
+        total=9,
+        backoff_factor=1.0,
+        status_forcelist=(429,),
+        allowed_methods=("HEAD", "GET", "PUT", "POST", "PATCH", "DELETE", "OPTIONS"),
+        respect_retry_after_header=True,
+        raise_on_status=False,
+    )
+    adapter = HTTPAdapter(max_retries=retries)
+    session = _requests.Session()
+    session.mount("http://", adapter)
+    session.mount("https://", adapter)
+    return session
+
+
+_SESSION = _build_retrying_session()
+
+
+class _RequestsShim:
+    """Shim exposing a subset of the requests API but backed by a retrying Session."""
+
+    HTTPError = _requests.HTTPError
+    Response = _requests.Response
+
+    def request(self, method: str, url: str, **kwargs) -> Response:
+        return _SESSION.request(method=method, url=url, **kwargs)
+
+    def get(self, url: str, **kwargs) -> Response:
+        return _SESSION.get(url, **kwargs)
+
+    def post(self, url: str, **kwargs) -> Response:
+        return _SESSION.post(url, **kwargs)
+
+    def delete(self, url: str, **kwargs) -> Response:
+        return _SESSION.delete(url, **kwargs)
+
+    def patch(self, url: str, **kwargs) -> Response:
+        return _SESSION.patch(url, **kwargs)
+
+    def put(self, url: str, **kwargs) -> Response:
+        return _SESSION.put(url, **kwargs)
+
+
+# Public shim to be imported by modules instead of the raw requests package
+requests = _RequestsShim()
+
+
+def raise_for_status_with_reason(response: Response):
+    try:
+        if response.status_code >= MINIMUM_CLIENT_SERVER_ERROR_CODE:
+            response.reason = response.json().get("reason", None)
+            if response.reason is None:
+                response.reason = response.json().get("detail", None)
+    except Exception as e:
+        logger.debug("Could not parse response as JSON: %s", e)
+
+    response.raise_for_status()

{hirundo-0.1.18 → hirundo-0.1.21}/hirundo/_iter_sse_retrying.py

@@ -5,11 +5,11 @@ import uuid
 from collections.abc import AsyncGenerator, Generator
 
 import httpx
-import requests
 import urllib3
 from httpx_sse import ServerSentEvent, SSEError, aconnect_sse, connect_sse
 from stamina import retry
 
+from hirundo._http import requests
 from hirundo._timeouts import READ_TIMEOUT
 from hirundo.logger import get_logger
 

{hirundo-0.1.18 → hirundo-0.1.21}/hirundo/cli.py

@@ -88,7 +88,7 @@ def setup_api_key(
     ],
 ):
     """
-    Setup the API key for the Hirundo client library.
+    Setup the API key for the Hirundo Python SDK.
     Values are saved to a .env file in the current directory for use by the library in requests.
     """
     saved_to = upsert_env("API_KEY", api_key)
@@ -115,7 +115,7 @@ def change_api_remote(
     ],
 ):
     """
-    Change the API server address for the Hirundo client library.
+    Change the API server address for the Hirundo Python SDK.
     This is the same address where you access the Hirundo web interface.
     """
     api_host = fix_api_host(api_host)
@@ -151,7 +151,7 @@ def setup(
     ],
 ):
     """
-    Setup the Hirundo client library.
+    Setup the Hirundo Python SDK.
     """
     api_host = fix_api_host(api_host)
     api_host_saved_to = upsert_env("API_HOST", api_host)
@@ -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(