orca-sdk 0.0.102__py3-none-any.whl → 0.0.104__py3-none-any.whl

orca_sdk/regression_model.py

@@ -281,6 +281,7 @@ class RegressionModel:
         save_telemetry: TelemetryMode = "on",
         prompt: str | None = None,
         use_lookup_cache: bool = True,
+        timeout_seconds: int = 10,
     ) -> RegressionPrediction: ...
 
     @overload
@@ -292,6 +293,7 @@ class RegressionModel:
         save_telemetry: TelemetryMode = "on",
         prompt: str | None = None,
         use_lookup_cache: bool = True,
+        timeout_seconds: int = 10,
     ) -> list[RegressionPrediction]: ...
 
     # TODO: add filter support
@@ -303,6 +305,7 @@ class RegressionModel:
         save_telemetry: TelemetryMode = "on",
         prompt: str | None = None,
         use_lookup_cache: bool = True,
+        timeout_seconds: int = 10,
     ) -> RegressionPrediction | list[RegressionPrediction]:
         """
         Make predictions using the regression model.
@@ -316,13 +319,20 @@ class RegressionModel:
                 environment variable is set to `"1"`. You can also pass `"sync"` or `"async"` to
                 explicitly set the save mode.
             prompt: Optional prompt for instruction-tuned embedding models
+            use_lookup_cache: Whether to use cached lookup results for faster predictions
+            timeout_seconds: Timeout in seconds for the request, defaults to 10 seconds
 
         Returns:
             Single RegressionPrediction or list of RegressionPrediction objects
 
         Raises:
             ValueError: If expected_scores length doesn't match value length for batch predictions
+            ValueError: If timeout_seconds is not a positive integer
+            TimeoutError: If the request times out after the specified duration
         """
+        if timeout_seconds <= 0:
+            raise ValueError("timeout_seconds must be a positive integer")
+
         telemetry_on, telemetry_sync = _get_telemetry_config(save_telemetry)
         response = orca_api.POST(
             "/gpu/regression_model/{name_or_id}/prediction",
@@ -341,6 +351,7 @@ class RegressionModel:
                 "prompt": prompt,
                 "use_lookup_cache": use_lookup_cache,
             },
+            timeout=timeout_seconds,
         )
 
         if telemetry_on and any(p["prediction_id"] is None for p in response):
@@ -454,7 +465,18 @@ class RegressionModel:
                 params={"model_name_or_id": self.id, "task_id": response["task_id"]},
             )
             assert res["result"] is not None
-            return RegressionMetrics(**res["result"])
+            return RegressionMetrics(
+                coverage=res["result"].get("coverage"),
+                mse=res["result"].get("mse"),
+                rmse=res["result"].get("rmse"),
+                mae=res["result"].get("mae"),
+                r2=res["result"].get("r2"),
+                explained_variance=res["result"].get("explained_variance"),
+                loss=res["result"].get("loss"),
+                anomaly_score_mean=res["result"].get("anomaly_score_mean"),
+                anomaly_score_median=res["result"].get("anomaly_score_median"),
+                anomaly_score_variance=res["result"].get("anomaly_score_variance"),
+            )
 
         job = Job(response["task_id"], get_value)
         return job if background else job.result()
@@ -469,6 +491,12 @@ class RegressionModel:
         batch_size: int,
         prompt: str | None = None,
     ) -> RegressionMetrics:
+        if len(dataset) == 0:
+            raise ValueError("Evaluation dataset cannot be empty")
+
+        if any(x is None for x in dataset[score_column]):
+            raise ValueError("Evaluation dataset cannot contain None values in the score column")
+
         predictions = [
             prediction
             for i in range(0, len(dataset), batch_size)

orca_sdk/regression_model_test.py

@@ -165,6 +165,16 @@ def test_evaluate(
     assert -1.0 <= result.anomaly_score_variance <= 1.0
 
 
+def test_evaluate_datasource_with_nones_raises_error(regression_model: RegressionModel, datasource: Datasource):
+    with pytest.raises(ValueError):
+        regression_model.evaluate(datasource, record_predictions=True, tags={"test"})
+
+
+def test_evaluate_dataset_with_nones_raises_error(regression_model: RegressionModel, hf_dataset: Dataset):
+    with pytest.raises(ValueError):
+        regression_model.evaluate(hf_dataset, record_predictions=True, tags={"test"})
+
+
 def test_evaluate_with_telemetry(regression_model, eval_dataset: Dataset):
     result = regression_model.evaluate(eval_dataset, record_predictions=True, tags={"test"})
     assert result is not None
@@ -187,6 +197,13 @@ def test_predict(regression_model: RegressionModel):
     assert 0 <= predictions[1].confidence <= 1
 
 
+def test_regression_prediction_has_no_score(regression_model: RegressionModel):
+    """Ensure optional score is None for regression predictions."""
+    prediction = regression_model.predict("This beach is amazing!")
+    assert isinstance(prediction, RegressionPrediction)
+    assert prediction.score is None
+
+
 def test_predict_unauthenticated(unauthenticated, regression_model: RegressionModel):
     with pytest.raises(ValueError, match="Invalid API key"):
         regression_model.predict(["This is excellent!", "This is terrible!"])
@@ -258,7 +275,7 @@ def test_predict_with_memoryset_override(regression_model: RegressionModel, hf_d
     # Create a memoryset with different scores
     inverted_scored_memoryset = ScoredMemoryset.from_hf_dataset(
         "test_memoryset_inverted_scores",
-        hf_dataset.map(lambda x: {"score": 2.0 - x["score"]}),  # Invert scores
+        hf_dataset.map(lambda x: {"score": (2.0 - x["score"]) if x["score"] is not None else None}),  # Invert scores
         embedding_model=PretrainedEmbeddingModel.GTE_BASE,
     )
     original_predictions = regression_model.predict(["This is excellent!", "This is terrible!"])

{orca_sdk-0.0.102.dist-info → orca_sdk-0.0.104.dist-info}/METADATA

@@ -1,24 +1,25 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: orca_sdk
-Version: 0.0.102
+Version: 0.0.104
 Summary: SDK for interacting with Orca Services
-License: Apache-2.0
+License-Expression: Apache-2.0
 Author: Orca DB Inc.
 Author-email: dev-rel@orcadb.ai
-Requires-Python: >=3.11,<4.0
-Classifier: License :: OSI Approved :: Apache Software License
+Requires-Python: >=3.11,<3.14
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: datasets (>=3.1.0,<4.0.0)
-Requires-Dist: gradio (==5.13.0)
-Requires-Dist: httpx (>=0.20.0,<0.29.0)
-Requires-Dist: pandas (>=2.2.3,<3.0.0)
-Requires-Dist: pyarrow (>=18.0.0,<19.0.0)
-Requires-Dist: python-dotenv (>=1.1.0,<2.0.0)
-Requires-Dist: scikit-learn (>=1.6.1,<2.0.0)
-Requires-Dist: torch (>=2.5.1,<3.0.0)
+Requires-Dist: datasets (>=3.1.0,<4)
+Requires-Dist: gradio (>=5.44.1,<6)
+Requires-Dist: httpx (>=0.28.1)
+Requires-Dist: httpx-retries (>=0.4.3,<0.5.0)
+Requires-Dist: numpy (>=2.1.0,<3)
+Requires-Dist: pandas (>=2.2.3,<3)
+Requires-Dist: pyarrow (>=18.0.0,<19)
+Requires-Dist: python-dotenv (>=1.1.0)
+Requires-Dist: scikit-learn (>=1.6.1,<2)
+Requires-Dist: torch (>=2.8.0,<3)
 Description-Content-Type: text/markdown
 
 <!--
@@ -45,7 +46,7 @@ You can find the documentation for all things Orca at [docs.orcadb.ai](https://d
 
 ## Installation
 
-Orca SDK is compatible with Python 3.10 or higher and is available on [PyPI](https://pypi.org/project/orca_sdk/). You can install it with your favorite python package manager:
+OrcaSDK is compatible with Python 3.10 or higher and is available on [PyPI](https://pypi.org/project/orca_sdk/). You can install it with your favorite python package manager:
 
 - Pip: `pip install orca_sdk`
 - Conda: `conda install orca_sdk`

orca_sdk-0.0.104.dist-info/RECORD

@@ -0,0 +1,40 @@
+orca_sdk/__init__.py,sha256=bNbT7BlBGo5ZWYHBiPUz77dIc344l7czz7AsuBrdzyM,1001
+orca_sdk/_shared/__init__.py,sha256=3Kt0Hu3QLI5FEp9nqGTxqAm3hAoBJKcagfaGQZ-lbJQ,223
+orca_sdk/_shared/metrics.py,sha256=LEZfAUWUtUWv_WWy9F_yjGLlUQHQpmR9WxG2fbKxa7U,14419
+orca_sdk/_shared/metrics_test.py,sha256=Rw1MaH37FppNsMnW8Ir9vMd8xxnZt3eo2Iypx1igtBI,9440
+orca_sdk/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+orca_sdk/_utils/analysis_ui.py,sha256=nT-M_YcNRCVPQzvuqYNFKnNHhYkADYBvq1GlIUePrWw,9232
+orca_sdk/_utils/analysis_ui_style.css,sha256=q_ba_-_KtgztepHg829zLzypaxKayl7ySC1-oYDzV3k,836
+orca_sdk/_utils/auth.py,sha256=Yf39jucuAkrM-TbTsLm_iRgLbLEcAIRzlHrCqgy8RiM,2483
+orca_sdk/_utils/auth_test.py,sha256=ygVWv1Ex53LaxIP7p2hzPHl8l9qYyBD5IGmEFJMps6s,1056
+orca_sdk/_utils/common.py,sha256=wUm2pNDWytEecC5WiDWd02-yCZw3Akx0bIutG4lHsFA,805
+orca_sdk/_utils/data_parsing.py,sha256=gkAwWEC8qRt3vRUObe7n7Pr0azOayNwc2yFY04WFp7E,5220
+orca_sdk/_utils/data_parsing_test.py,sha256=fNEYzPzE1jt3KWE2Kj91KqIeuv-L5REHFAa98zkNGSQ,8962
+orca_sdk/_utils/pagination.py,sha256=986z0QPZixrZeurJWorF6eMgnTRdDF84AagEA6qNbMw,4245
+orca_sdk/_utils/pagination_test.py,sha256=BUylCrcHnwoKEBmMUzVr0lwLpA35ivcCwdBK4rMw9y8,4887
+orca_sdk/_utils/prediction_result_ui.css,sha256=sqBlkRLnovb5X5EcUDdB6iGpH63nVRlTW4uAmXuD0WM,258
+orca_sdk/_utils/prediction_result_ui.py,sha256=Ur_FY7dz3oWNmtPiP3Wl3yRlEMgK8q9UfT-SDu9UPxA,4805
+orca_sdk/_utils/tqdm_file_reader.py,sha256=Lw7Cg1UgNuRUoN6jjqZb-IlV00H-kbRcrZLdudr1GxE,324
+orca_sdk/_utils/value_parser.py,sha256=c3qMABCCDQcIjn9N1orYYnlRwDW9JWdGwW_2TDZPLdI,1286
+orca_sdk/_utils/value_parser_test.py,sha256=OybsiC-Obi32RRi9NIuwrVBRAnlyPMV1xVAaevSrb7M,1079
+orca_sdk/classification_model.py,sha256=A_3efuBSYF3hUxu1VbSlZNpzBF9CwuGEEtvgSPyTl9M,32696
+orca_sdk/classification_model_test.py,sha256=fJx4s3fcKwQ1z-K0LsmbM9gVakWjejs595WeM2AlnR8,20405
+orca_sdk/client.py,sha256=8SJBt38AzmQNJQvkmO9tx1yqlkW8kBMcNNJgRD5ZtLk,123279
+orca_sdk/conftest.py,sha256=p5ae1XS0Ra9l-OuQzaUw3YyM0lfsA1GpK7grSqKnKPc,9589
+orca_sdk/credentials.py,sha256=YuWipb5r1R_uPRe0nrm8mbbrfrXKFimgFOxny9bzAbI,5063
+orca_sdk/credentials_test.py,sha256=ZIIZtfv507UyIIgLhnECWn6KS5NjbfHMdT31f8k0zJM,1623
+orca_sdk/datasource.py,sha256=BfjutQ12cuvjMSyPTTiJVopKgDwy8PxoRkbfDM7tHXw,20262
+orca_sdk/datasource_test.py,sha256=mVEYWZVpgpGo9RDXmcqlXEIZeGDPiLG4K87wS2-nJuc,11810
+orca_sdk/embedding_model.py,sha256=sgOEJE-U99qU3qkKAdtZbZqNXY48wjkHqwOQ9KZLd3Q,27285
+orca_sdk/embedding_model_test.py,sha256=1aELyCuIzxSxUg7Z4tYtNOd8-hV5hFb-gsZTNh712OQ,7765
+orca_sdk/job.py,sha256=yHmHgm5vf2DHJlvAGgA2o1mNbKs3yoJ5RMeUpPSwl7E,12858
+orca_sdk/job_test.py,sha256=nRSWxd_1UIfrj9oMVvrXjt6OBkBpddYAjb2y6P-DTUg,4327
+orca_sdk/memoryset.py,sha256=L6Y1Hw6D93XHYUdz0zPcTsgmJZWcODSTLOqXFLN-T3A,85854
+orca_sdk/memoryset_test.py,sha256=hmbRERbea7vEWlSLJeeZcH4FEKXIDoUyQci7KdatfiU,21400
+orca_sdk/regression_model.py,sha256=YNrpp9G-kT9YL2Dl5IAZMVzyS7N4NNESWWxxjhFQJ8c,25987
+orca_sdk/regression_model_test.py,sha256=J8u9xZ9Y1qmMcKRTB0wyPDABvr0C3lHHI_FaGwQOmPs,15386
+orca_sdk/telemetry.py,sha256=qTEPkOlqjxsPaS-HR5Jh5ZnIvuF58aIy5OpzA-wQkAE,25713
+orca_sdk/telemetry_test.py,sha256=eT66C5lFdNg-pQdo2I__BP7Tn5fTc9aTkVo9ZhWwhU0,5519
+orca_sdk-0.0.104.dist-info/METADATA,sha256=rDiw0iacZ8sG8ZON99Ovdyl4E8dRZzL9fYzUTJUEjwA,3661
+orca_sdk-0.0.104.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+orca_sdk-0.0.104.dist-info/RECORD,,

{orca_sdk-0.0.102.dist-info → orca_sdk-0.0.104.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.1
+Generator: poetry-core 2.2.1
 Root-Is-Purelib: true
 Tag: py3-none-any

orca_sdk-0.0.102.dist-info/RECORD

@@ -1,40 +0,0 @@
-orca_sdk/__init__.py,sha256=bNbT7BlBGo5ZWYHBiPUz77dIc344l7czz7AsuBrdzyM,1001
-orca_sdk/_shared/__init__.py,sha256=3Kt0Hu3QLI5FEp9nqGTxqAm3hAoBJKcagfaGQZ-lbJQ,223
-orca_sdk/_shared/metrics.py,sha256=S-0aC340vUCW0JB-x4IExo8Dt_-cPhmLs-goI0RPvEE,13490
-orca_sdk/_shared/metrics_test.py,sha256=3wD1e2WE_wGtWBQ0E2gML6J3LCcbQBMezxvhDM947a0,8478
-orca_sdk/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-orca_sdk/_utils/analysis_ui.py,sha256=nT-M_YcNRCVPQzvuqYNFKnNHhYkADYBvq1GlIUePrWw,9232
-orca_sdk/_utils/analysis_ui_style.css,sha256=q_ba_-_KtgztepHg829zLzypaxKayl7ySC1-oYDzV3k,836
-orca_sdk/_utils/auth.py,sha256=58Gaa4KA9iy7WP-hMZT4PI6x5lkpctFbbJ6Piwu1ZS4,2484
-orca_sdk/_utils/auth_test.py,sha256=ygVWv1Ex53LaxIP7p2hzPHl8l9qYyBD5IGmEFJMps6s,1056
-orca_sdk/_utils/common.py,sha256=wUm2pNDWytEecC5WiDWd02-yCZw3Akx0bIutG4lHsFA,805
-orca_sdk/_utils/data_parsing.py,sha256=gkAwWEC8qRt3vRUObe7n7Pr0azOayNwc2yFY04WFp7E,5220
-orca_sdk/_utils/data_parsing_test.py,sha256=fNEYzPzE1jt3KWE2Kj91KqIeuv-L5REHFAa98zkNGSQ,8962
-orca_sdk/_utils/pagination.py,sha256=986z0QPZixrZeurJWorF6eMgnTRdDF84AagEA6qNbMw,4245
-orca_sdk/_utils/pagination_test.py,sha256=BUylCrcHnwoKEBmMUzVr0lwLpA35ivcCwdBK4rMw9y8,4887
-orca_sdk/_utils/prediction_result_ui.css,sha256=sqBlkRLnovb5X5EcUDdB6iGpH63nVRlTW4uAmXuD0WM,258
-orca_sdk/_utils/prediction_result_ui.py,sha256=0xBXodbnh50IRoI4y4dWCWCm3YCuQddWSHYw3gwXcjQ,4633
-orca_sdk/_utils/tqdm_file_reader.py,sha256=Lw7Cg1UgNuRUoN6jjqZb-IlV00H-kbRcrZLdudr1GxE,324
-orca_sdk/_utils/value_parser.py,sha256=c3qMABCCDQcIjn9N1orYYnlRwDW9JWdGwW_2TDZPLdI,1286
-orca_sdk/_utils/value_parser_test.py,sha256=OybsiC-Obi32RRi9NIuwrVBRAnlyPMV1xVAaevSrb7M,1079
-orca_sdk/classification_model.py,sha256=SUiUgv_o3UUngpz3Le_L6DsijhjXVEB3yo84hrD1MX4,31172
-orca_sdk/classification_model_test.py,sha256=WganVoP-0vw1cqiVWJ2vXyGi4lwYp_hbZHultpxvFqk,19536
-orca_sdk/client.py,sha256=Q2tjK-CeNnX0dgK-oZPzElgEK3wkxXC1q5YK85mZcqE,120338
-orca_sdk/conftest.py,sha256=LHA46gDU_D0T_ogS6XOVQvGDDMD01nVZFWVcBYDConc,8885
-orca_sdk/credentials.py,sha256=G_jdeC-1j6oL6VtHnRHL-LxvLXnL-KH2CDCB2iQ9POY,5084
-orca_sdk/credentials_test.py,sha256=whUweSJIEws6C8Bku-5V31Dv9hD1mFDDW7X2cCsB6g0,1629
-orca_sdk/datasource.py,sha256=6wARRq-eNDJVSBABdVzn41z7s69xasTsqbozaVAsf9U,20263
-orca_sdk/datasource_test.py,sha256=wENPourrJvQN-uJJPaJI9EDuof6wVw3GirOhbrY4sFI,11564
-orca_sdk/embedding_model.py,sha256=FBuMDYKS8x6iyhSHtNO8TI2pCi6yYDycirKw3hqaGAc,26043
-orca_sdk/embedding_model_test.py,sha256=1aELyCuIzxSxUg7Z4tYtNOd8-hV5hFb-gsZTNh712OQ,7765
-orca_sdk/job.py,sha256=wWJPkkQbkNu_ylBtZN4AscU00VwWTfqlSmysRBUlivw,12787
-orca_sdk/job_test.py,sha256=r4zCyCuJ8eVN-O6_IUSakmSBn64rY7oBmlNtb5RNsi0,3919
-orca_sdk/memoryset.py,sha256=aeceFH6WpIt3hVXnpjLGr7cdj5lPy_PeT3ZxR8fdhKA,85585
-orca_sdk/memoryset_test.py,sha256=14WG6u_adVmm6CSn2dM5lEfQYxybwh3s9Q7RBeTuoPE,20486
-orca_sdk/regression_model.py,sha256=je2g1BmoPCuouv5iWqDolja90F2w2vD6TooXA8KjL7c,24552
-orca_sdk/regression_model_test.py,sha256=8LDhtQeh52grZQ2Xd0ju1MQvb_hwosY_ORDDE3wS2LA,14570
-orca_sdk/telemetry.py,sha256=qTEPkOlqjxsPaS-HR5Jh5ZnIvuF58aIy5OpzA-wQkAE,25713
-orca_sdk/telemetry_test.py,sha256=eT66C5lFdNg-pQdo2I__BP7Tn5fTc9aTkVo9ZhWwhU0,5519
-orca_sdk-0.0.102.dist-info/METADATA,sha256=dfe9GFGNjzso6R73Y-uVqyRgvFxvJZRIOsCgVvPpnn8,3665
-orca_sdk-0.0.102.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-orca_sdk-0.0.102.dist-info/RECORD,,