orca-sdk 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl

orca_sdk/memoryset_test.py

@@ -46,16 +46,98 @@ def test_create_memoryset(readonly_memoryset: LabeledMemoryset, hf_dataset: Data
     assert readonly_memoryset.index_params == {"n_lists": 100}
 
 
+def test_create_empty_labeled_memoryset():
+    name = f"test_empty_labeled_{uuid4()}"
+    label_names = ["negative", "positive"]
+    try:
+        memoryset = LabeledMemoryset.create(name, label_names=label_names, description="empty labeled test")
+        assert memoryset is not None
+        assert memoryset.name == name
+        assert memoryset.length == 0
+        assert memoryset.label_names == label_names
+        assert memoryset.insertion_status is None
+
+        # inserting should work on an empty memoryset
+        memoryset.insert(dict(value="i love soup", label=1, key="k1"))
+        memoryset.refresh()
+        assert memoryset.length == 1
+        m = memoryset[0]
+        assert isinstance(m, LabeledMemory)
+        assert m.value == "i love soup"
+        assert m.label == 1
+        assert m.label_name == "positive"
+        assert m.metadata.get("key") == "k1"
+
+        # if_exists="open" should re-open the same memoryset
+        reopened = LabeledMemoryset.create(name, label_names=label_names, if_exists="open")
+        assert reopened.id == memoryset.id
+        assert len(reopened) == 1
+
+        # if_exists="open" should raise if label_names mismatch
+        with pytest.raises(ValueError, match=r"label names|requested"):
+            LabeledMemoryset.create(name, label_names=["turtles", "frogs"], if_exists="open")
+
+        # if_exists="open" should raise if embedding_model mismatch
+        with pytest.raises(ValueError, match=r"embedding_model|requested"):
+            LabeledMemoryset.create(
+                name,
+                label_names=label_names,
+                embedding_model=PretrainedEmbeddingModel.DISTILBERT,
+                if_exists="open",
+            )
+
+        # if_exists="error" should raise when it already exists
+        with pytest.raises(ValueError, match="already exists"):
+            LabeledMemoryset.create(name, label_names=label_names, if_exists="error")
+    finally:
+        LabeledMemoryset.drop(name, if_not_exists="ignore")
+
+
+def test_create_empty_scored_memoryset():
+    name = f"test_empty_scored_{uuid4()}"
+    try:
+        memoryset = ScoredMemoryset.create(name, description="empty scored test")
+        assert memoryset is not None
+        assert memoryset.name == name
+        assert memoryset.length == 0
+        assert memoryset.insertion_status is None
+
+        # inserting should work on an empty memoryset
+        memoryset.insert(dict(value="i love soup", score=0.25, key="k1", label=0))
+        memoryset.refresh()
+        assert memoryset.length == 1
+        m = memoryset[0]
+        assert isinstance(m, ScoredMemory)
+        assert m.value == "i love soup"
+        assert m.score == 0.25
+        assert m.metadata.get("key") == "k1"
+        assert m.metadata.get("label") == 0
+
+        # if_exists="open" should re-open the same memoryset
+        reopened = ScoredMemoryset.create(name, if_exists="open")
+        assert reopened.id == memoryset.id
+
+        # if_exists="open" should raise if embedding_model mismatch
+        with pytest.raises(ValueError, match=r"embedding_model|requested"):
+            ScoredMemoryset.create(name, embedding_model=PretrainedEmbeddingModel.DISTILBERT, if_exists="open")
+
+        # if_exists="error" should raise when it already exists
+        with pytest.raises(ValueError, match="already exists"):
+            ScoredMemoryset.create(name, if_exists="error")
+    finally:
+        ScoredMemoryset.drop(name, if_not_exists="ignore")
+
+
 def test_create_memoryset_unauthenticated(unauthenticated_client, datasource):
     with unauthenticated_client.use():
         with pytest.raises(ValueError, match="Invalid API key"):
-            LabeledMemoryset.create("test_memoryset", datasource)
+            LabeledMemoryset.create("test_memoryset", datasource=datasource)
 
 
 def test_create_memoryset_invalid_input(datasource):
     # invalid name
     with pytest.raises(ValueError, match=r"Invalid input:.*"):
-        LabeledMemoryset.create("test memoryset", datasource)
+        LabeledMemoryset.create("test memoryset", datasource=datasource)
 
 
 def test_create_memoryset_already_exists_error(hf_dataset, label_names, readonly_memoryset):
@@ -849,6 +931,31 @@ def test_clone_memoryset(readonly_memoryset: LabeledMemoryset):
     assert cloned_memoryset.insertion_status == Status.COMPLETED
 
 
+def test_clone_empty_memoryset():
+    name = f"test_empty_to_clone_{uuid4()}"
+    cloned_name = f"test_empty_cloned_{uuid4()}"
+    label_names = ["negative", "positive"]
+    try:
+        # Create an empty memoryset
+        empty_memoryset = LabeledMemoryset.create(name, label_names=label_names, description="empty memoryset to clone")
+        assert empty_memoryset is not None
+        assert empty_memoryset.name == name
+        assert empty_memoryset.length == 0
+        assert empty_memoryset.insertion_status is None  # Empty memorysets have None status
+
+        # Clone the empty memoryset
+        cloned_memoryset = empty_memoryset.clone(cloned_name, embedding_model=PretrainedEmbeddingModel.DISTILBERT)
+        assert cloned_memoryset is not None
+        assert cloned_memoryset.name == cloned_name
+        assert cloned_memoryset.length == 0  # Clone should also be empty
+        assert cloned_memoryset.embedding_model == PretrainedEmbeddingModel.DISTILBERT
+        assert cloned_memoryset.insertion_status == Status.COMPLETED
+        assert cloned_memoryset.label_names == label_names
+    finally:
+        LabeledMemoryset.drop(name, if_not_exists="ignore")
+        LabeledMemoryset.drop(cloned_name, if_not_exists="ignore")
+
+
 @pytest.fixture(scope="function")
 async def test_group_potential_duplicates(writable_memoryset: LabeledMemoryset):
     writable_memoryset.insert(

orca_sdk/regression_model.py

@@ -11,10 +11,8 @@ from ._shared.metrics import RegressionMetrics, calculate_regression_metrics
 from ._utils.common import UNSET, CreateMode, DropMode
 from .client import (
     OrcaClient,
-    PostRegressionModelByModelNameOrIdEvaluationParams,
     PredictiveModelUpdate,
     RARHeadType,
-    RegressionEvaluationRequest,
     RegressionModelMetadata,
     RegressionPredictionRequest,
 )
@@ -85,12 +83,13 @@ class RegressionModel:
         return isinstance(other, RegressionModel) and self.id == other.id
 
     def __repr__(self):
+        memoryset_repr = self.memoryset.__repr__().replace("\n", "\n    ")
         return (
             "RegressionModel({\n"
             f"    name: '{self.name}',\n"
             f"    head_type: {self.head_type},\n"
             f"    memory_lookup_count: {self.memory_lookup_count},\n"
-            f"    memoryset: ScoredMemoryset.open('{self.memoryset.name}'),\n"
+            f"    memoryset: {memoryset_repr},\n"
             "})"
         )
 

{orca_sdk-0.1.6.dist-info → orca_sdk-0.1.8.dist-info}/METADATA

@@ -1,15 +1,16 @@
 Metadata-Version: 2.4
 Name: orca_sdk
-Version: 0.1.6
+Version: 0.1.8
 Summary: SDK for interacting with Orca Services
 License-Expression: Apache-2.0
 Author: Orca DB Inc.
 Author-email: dev-rel@orcadb.ai
-Requires-Python: >=3.11,<3.14
+Requires-Python: >=3.11,<3.15
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Requires-Dist: datasets (>=3.1.0,<4)
 Requires-Dist: gradio (>=5.44.1,<6)
 Requires-Dist: httpx (>=0.28.1)

{orca_sdk-0.1.6.dist-info → orca_sdk-0.1.8.dist-info}/RECORD

@@ -1,7 +1,7 @@
 orca_sdk/__init__.py,sha256=xyjNwkLQXaX8A-UYgGwYDjv2btOXArT_yiMTfmW7KA8,1003
 orca_sdk/_shared/__init__.py,sha256=3Kt0Hu3QLI5FEp9nqGTxqAm3hAoBJKcagfaGQZ-lbJQ,223
-orca_sdk/_shared/metrics.py,sha256=a_FdsPGDjR3CMOEBaEhEBqMfWUg7sqz9Jeh26XzAeg0,19756
-orca_sdk/_shared/metrics_test.py,sha256=n7eEAT8e6RqbI94ftEDljTBzOuh-YkFpXfF3DOoZA10,12905
+orca_sdk/_shared/metrics.py,sha256=faeL1B1ftmns1ikfKrIlU3xOn6j0iAGLNUupxvAFza8,24968
+orca_sdk/_shared/metrics_test.py,sha256=vDIXoj8EuuLcdPJz_7EiVPgQ-FXiVT81JG30jxsg9HM,20752
 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
@@ -17,25 +17,25 @@ orca_sdk/_utils/prediction_result_ui.py,sha256=Ur_FY7dz3oWNmtPiP3Wl3yRlEMgK8q9Uf
 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/async_client.py,sha256=y2D3fPQZmbwmtYWAk5acJ45atSZen9MNfjP2tKjpP6Q,132737
-orca_sdk/classification_model.py,sha256=4AcQvAm0EN7w0qx0WpgEs7VUoIIPTqIVE86wtkaIAYs,46249
+orca_sdk/async_client.py,sha256=U7B8yLbeB5STPr3dkeTTwPkDHou2nBCJ9CLBPulrXVY,134893
+orca_sdk/classification_model.py,sha256=jy8h5Kb4cesFqm1sat4JuxAs9uH53rUvOrlqKID-mwA,46294
 orca_sdk/classification_model_test.py,sha256=vBn7KBb9-ACuJEdzW50n54Fn6Mh9iEYbn1197lE8-yI,36997
-orca_sdk/client.py,sha256=oQd8Lm0agetLyAdVRP8IZqe6S5mjxhFSnbVHqhT7dmI,131798
+orca_sdk/client.py,sha256=9AaEYrfK7HZEpsSSih8mRuTUiaQ4yk2n0jU92oLusGY,133942
 orca_sdk/conftest.py,sha256=0O1VY-SPKNAvi9fBLdY1RMnYVgZvMjP92y99bNAqqiw,12461
 orca_sdk/credentials.py,sha256=80_1r8n5jruEvN_E629SaRrRhKvF_NhWUEZyZzPXkqQ,6620
 orca_sdk/credentials_test.py,sha256=TLbXJMz3IlThvtSrHeLM7jRsKnrncA_ahOTpHg15Ei4,4089
 orca_sdk/datasource.py,sha256=6QaccghiyFEUSFcqnwjIJzpgIh9Id0snJk2EqViqPsU,22356
 orca_sdk/datasource_test.py,sha256=sCk3IcQJbDut5oN4Wf7PXhTxyMwalxMuCXJekSxy9wk,16665
-orca_sdk/embedding_model.py,sha256=4xxfo26b5X_YJtU8KyqoMmJQ6VgfHEcYftVSz-RfDng,27920
-orca_sdk/embedding_model_test.py,sha256=-NItbNb3tTVj5jAvSi3WjV3FP448q08lmT5iObg9vwA,8133
+orca_sdk/embedding_model.py,sha256=vLGnlO9I-cN1lklNBl_LxZ8m9oK3vkegFOpvYYw8u8g,28038
+orca_sdk/embedding_model_test.py,sha256=Lc6fZ0ifT0hh6ldkUfjwMPcP6OgN0Umlzu8XDLs7UO4,8144
 orca_sdk/job.py,sha256=wHwVt-s7i-v8udhLGybB-90Kp4dwOLrY806bE4Tam5Q,13092
 orca_sdk/job_test.py,sha256=nRSWxd_1UIfrj9oMVvrXjt6OBkBpddYAjb2y6P-DTUg,4327
-orca_sdk/memoryset.py,sha256=OtIZH14bN7tejevdsHJpBeje5Ovc58vtkw1inRMWdw4,117709
-orca_sdk/memoryset_test.py,sha256=YrMP_Z7BPhKAIZq1FKar83dNzR_2b56A89pnEiUbRrs,46509
-orca_sdk/regression_model.py,sha256=vXdY2Fbfc0MyECUR3fa_IR-nETPrDN7VFAdjvsgHPrs,31382
+orca_sdk/memoryset.py,sha256=-bTQJLzr8Fdt3LIaCEliO2jT_LxcaoaqxETY42vH0mA,156070
+orca_sdk/memoryset_test.py,sha256=X-gAOz-BA4ByXAitI19GQsktnL2xRGcLus8AHj5mL48,51218
+orca_sdk/regression_model.py,sha256=Ga0TZLm1Qe_bQXoP90BrMiyvZ8bsJ33Z9I6RgT86t2c,31339
 orca_sdk/regression_model_test.py,sha256=DfWLkqxB835jjwM-sj1uxQ6Yz_ZBMnt8EHjdfnHsRnU,25103
 orca_sdk/telemetry.py,sha256=ZyCMiyyo_SchjadWZH55TlLrC4Ucq5S316NbW26LL4Y,27834
 orca_sdk/telemetry_test.py,sha256=eT66C5lFdNg-pQdo2I__BP7Tn5fTc9aTkVo9ZhWwhU0,5519
-orca_sdk-0.1.6.dist-info/METADATA,sha256=85QDZDP9Uxda4oZ3BMPP_kI5T4GPy1mFMYtWh1-nI54,3659
-orca_sdk-0.1.6.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-orca_sdk-0.1.6.dist-info/RECORD,,
+orca_sdk-0.1.8.dist-info/METADATA,sha256=EIDzSzxtf7D5LEuAdakH5rIy1XHqeEC1HhqsrF_oT5c,3710
+orca_sdk-0.1.8.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+orca_sdk-0.1.8.dist-info/RECORD,,