orca-sdk 0.0.86__tar.gz → 0.0.88__tar.gz

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: orca_sdk
-Version: 0.0.86
+Version: 0.0.88
 Summary: SDK for interacting with Orca Services
 License: Apache-2.0
 Author: Orca DB Inc.
@@ -15,9 +15,11 @@ Requires-Dist: attrs (>=22.2.0)
 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: networkx (>=3.4.2,<4.0.0)
 Requires-Dist: pandas (>=2.2.3,<3.0.0)
 Requires-Dist: pyarrow (>=18.0.0,<19.0.0)
 Requires-Dist: python-dateutil (>=2.8.0,<3.0.0)
+Requires-Dist: python-dotenv (>=1.1.0,<2.0.0)
 Requires-Dist: torch (>=2.5.1,<3.0.0)
 Description-Content-Type: text/markdown
 

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/_generated_api_client/api/__init__.py

@@ -100,6 +100,9 @@ from .memoryset.list_memorysets_memoryset_get import sync as list_memorysets
 from .memoryset.memoryset_lookup_gpu_memoryset_name_or_id_lookup_post import (
     sync as memoryset_lookup_gpu,
 )
+from .memoryset.potential_duplicate_groups_memoryset_name_or_id_potential_duplicate_groups_get import (
+    sync as potential_duplicate_groups,
+)
 from .memoryset.query_memoryset_memoryset_name_or_id_memories_post import (
     sync as query_memoryset,
 )
@@ -208,6 +211,7 @@ __all__ = [
     "list_pretrained_embedding_models",
     "list_tasks",
     "memoryset_lookup_gpu",
+    "potential_duplicate_groups",
     "predict_gpu",
     "query_memoryset",
     "record_prediction_feedback",

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/_generated_api_client/api/memoryset/insert_memories_gpu_memoryset_name_or_id_memory_post.py

@@ -11,7 +11,7 @@ The main changes are:
 """
 
 from http import HTTPStatus
-from typing import Any, Dict, List
+from typing import Any, Dict, List, cast
 
 import httpx
 
@@ -45,9 +45,10 @@ def _get_kwargs(
     return _kwargs
 
 
-def _parse_response(*, response: httpx.Response) -> None:
+def _parse_response(*, response: httpx.Response) -> List[str]:
     if response.status_code == 201:
-        response_201 = response.json()
+        response_201 = cast(List[str], response.json())
+
         return response_201
     if response.status_code == 401:
         raise get_error_for_response(response)
@@ -61,7 +62,7 @@ def _parse_response(*, response: httpx.Response) -> None:
         raise get_error_for_response(response)
 
 
-def _build_response(*, response: httpx.Response) -> Response[None]:
+def _build_response(*, response: httpx.Response) -> Response[List[str]]:
     return Response(
         status_code=HTTPStatus(response.status_code),
         content=response.content,
@@ -74,7 +75,7 @@ def sync_detailed(
     name_or_id: str,
     *,
     body: List["LabeledMemoryInsert"],
-) -> Response[None]:
+) -> Response[List[str]]:
     """Insert Memories
 
     Args:
@@ -86,7 +87,7 @@ def sync_detailed(
         httpx.TimeoutException: If the request takes longer than Client.timeout.
 
     Returns:
-        Response[None]
+        Response[List[str]]
     """
 
     kwargs = _get_kwargs(
@@ -106,7 +107,7 @@ def sync(
     name_or_id: str,
     *,
     body: List["LabeledMemoryInsert"],
-) -> None:
+) -> List[str]:
     """Insert Memories
 
     Args:
@@ -118,7 +119,7 @@ def sync(
         httpx.TimeoutException: If the request takes longer than Client.timeout.
 
     Returns:
-        None
+        List[str]
     """
 
     return sync_detailed(
@@ -131,7 +132,7 @@ async def asyncio_detailed(
     name_or_id: str,
     *,
     body: List["LabeledMemoryInsert"],
-) -> Response[None]:
+) -> Response[List[str]]:
     """Insert Memories
 
     Args:
@@ -143,7 +144,7 @@ async def asyncio_detailed(
         httpx.TimeoutException: If the request takes longer than Client.timeout.
 
     Returns:
-        Response[None]
+        Response[List[str]]
     """
 
     kwargs = _get_kwargs(
@@ -161,7 +162,7 @@ async def asyncio(
     name_or_id: str,
     *,
     body: List["LabeledMemoryInsert"],
-) -> None:
+) -> List[str]:
     """Insert Memories
 
     Args:
@@ -173,7 +174,7 @@ async def asyncio(
         httpx.TimeoutException: If the request takes longer than Client.timeout.
 
     Returns:
-        None
+        List[str]
     """
 
     return (

orca_sdk-0.0.88/orca_sdk/_generated_api_client/api/memoryset/potential_duplicate_groups_memoryset_name_or_id_potential_duplicate_groups_get.py

@@ -0,0 +1,166 @@
+"""
+This file is generated by the openapi-python-client tool via the generate_api_client.py script
+
+It is a customized template from the openapi-python-client tool's default template:
+https://github.com/openapi-generators/openapi-python-client/blob/861ef5622f10fc96d240dc9becb0edf94e61446c/openapi_python_client/templates/endpoint_module.py.jinja
+
+The main changes are:
+- Update the API call responses to either return the successful response type or raise an error by:
+    - Updating the _parse_response function to raise an error if the response status code is not in the 2xx range
+- Inject a client into every method via a context manager
+"""
+
+from http import HTTPStatus
+from typing import Any, List
+
+import httpx
+
+from ...client import _client_context
+from ...errors import get_error_for_response
+from ...models.labeled_memory import LabeledMemory
+from ...types import Response
+
+
+def _get_kwargs(
+    name_or_id: str,
+) -> dict[str, Any]:
+    _kwargs: dict[str, Any] = {
+        "method": "get",
+        "url": f"/memoryset/{name_or_id}/potential_duplicate_groups",
+    }
+
+    return _kwargs
+
+
+def _parse_response(*, response: httpx.Response) -> List[List["LabeledMemory"]]:
+    if response.status_code == 200:
+        response_200 = []
+        _response_200 = response.json()
+        for response_200_item_data in _response_200:
+            response_200_item = []
+            _response_200_item = response_200_item_data
+            for response_200_item_item_data in _response_200_item:
+                response_200_item_item = LabeledMemory.from_dict(response_200_item_item_data)
+
+                response_200_item.append(response_200_item_item)
+
+            response_200.append(response_200_item)
+
+        return response_200
+    if response.status_code == 401:
+        raise get_error_for_response(response)
+    if response.status_code == 500:
+        raise get_error_for_response(response)
+    if response.status_code == 503:
+        raise get_error_for_response(response)
+    if response.status_code == 404:
+        raise get_error_for_response(response)
+    else:
+        raise get_error_for_response(response)
+
+
+def _build_response(*, response: httpx.Response) -> Response[List[List["LabeledMemory"]]]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(response=response),
+    )
+
+
+def sync_detailed(
+    name_or_id: str,
+) -> Response[List[List["LabeledMemory"]]]:
+    """Potential Duplicate Groups
+
+    Args:
+        name_or_id (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[List[List['LabeledMemory']]]
+    """
+
+    kwargs = _get_kwargs(
+        name_or_id=name_or_id,
+    )
+
+    with _client_context() as client:
+        response = client.get_httpx_client().request(
+            **kwargs,
+        )
+
+        return _build_response(response=response)
+
+
+def sync(
+    name_or_id: str,
+) -> List[List["LabeledMemory"]]:
+    """Potential Duplicate Groups
+
+    Args:
+        name_or_id (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        List[List['LabeledMemory']]
+    """
+
+    return sync_detailed(
+        name_or_id=name_or_id,
+    ).parsed
+
+
+async def asyncio_detailed(
+    name_or_id: str,
+) -> Response[List[List["LabeledMemory"]]]:
+    """Potential Duplicate Groups
+
+    Args:
+        name_or_id (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[List[List['LabeledMemory']]]
+    """
+
+    kwargs = _get_kwargs(
+        name_or_id=name_or_id,
+    )
+
+    with _client_context() as client:
+        response = await client.get_async_httpx_client().request(**kwargs)
+
+    return _build_response(response=response)
+
+
+async def asyncio(
+    name_or_id: str,
+) -> List[List["LabeledMemory"]]:
+    """Potential Duplicate Groups
+
+    Args:
+        name_or_id (str):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        List[List['LabeledMemory']]
+    """
+
+    return (
+        await asyncio_detailed(
+            name_or_id=name_or_id,
+        )
+    ).parsed

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/_generated_api_client/models/label_prediction_with_memories_and_feedback.py

@@ -47,6 +47,7 @@ class LabelPredictionWithMemoriesAndFeedback:
         updated_at (datetime.datetime):
         tags (List[str]):
         explanation (Union[None, str]):
+        memory_id (Union[None, str]):
         feedbacks (List['PredictionFeedback']):
     """
 
@@ -68,6 +69,7 @@ class LabelPredictionWithMemoriesAndFeedback:
     updated_at: datetime.datetime
     tags: List[str]
     explanation: Union[None, str]
+    memory_id: Union[None, str]
     feedbacks: List["PredictionFeedback"]
     additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
 
@@ -117,6 +119,9 @@ class LabelPredictionWithMemoriesAndFeedback:
         explanation: Union[None, str]
         explanation = self.explanation
 
+        memory_id: Union[None, str]
+        memory_id = self.memory_id
+
         feedbacks = []
         for feedbacks_item_data in self.feedbacks:
             feedbacks_item = feedbacks_item_data.to_dict()
@@ -144,6 +149,7 @@ class LabelPredictionWithMemoriesAndFeedback:
                 "updated_at": updated_at,
                 "tags": tags,
                 "explanation": explanation,
+                "memory_id": memory_id,
                 "feedbacks": feedbacks,
             }
         )
@@ -225,6 +231,13 @@ class LabelPredictionWithMemoriesAndFeedback:
 
         explanation = _parse_explanation(d.pop("explanation"))
 
+        def _parse_memory_id(data: object) -> Union[None, str]:
+            if data is None:
+                return data
+            return cast(Union[None, str], data)
+
+        memory_id = _parse_memory_id(d.pop("memory_id"))
+
         feedbacks = []
         _feedbacks = d.pop("feedbacks")
         for feedbacks_item_data in _feedbacks:
@@ -251,6 +264,7 @@ class LabelPredictionWithMemoriesAndFeedback:
             updated_at=updated_at,
             tags=tags,
             explanation=explanation,
+            memory_id=memory_id,
             feedbacks=feedbacks,
         )
 

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/_generated_api_client/models/update_prediction_request.py

@@ -26,10 +26,12 @@ class UpdatePredictionRequest:
     Attributes:
         expected_label (Union[None, Unset, int]):
         tags (Union[Unset, List[str]]):
+        memory_id (Union[None, Unset, str]):
     """
 
     expected_label: Union[None, Unset, int] = UNSET
     tags: Union[Unset, List[str]] = UNSET
+    memory_id: Union[None, Unset, str] = UNSET
     additional_properties: dict[str, Any] = _attrs_field(init=False, factory=dict)
 
     def to_dict(self) -> dict[str, Any]:
@@ -43,6 +45,12 @@ class UpdatePredictionRequest:
         if not isinstance(self.tags, Unset):
             tags = self.tags
 
+        memory_id: Union[None, Unset, str]
+        if isinstance(self.memory_id, Unset):
+            memory_id = UNSET
+        else:
+            memory_id = self.memory_id
+
         field_dict: dict[str, Any] = {}
         field_dict.update(self.additional_properties)
         field_dict.update({})
@@ -50,6 +58,8 @@ class UpdatePredictionRequest:
             field_dict["expected_label"] = expected_label
         if tags is not UNSET:
             field_dict["tags"] = tags
+        if memory_id is not UNSET:
+            field_dict["memory_id"] = memory_id
 
         return field_dict
 
@@ -68,9 +78,19 @@ class UpdatePredictionRequest:
 
         tags = cast(List[str], d.pop("tags", UNSET))
 
+        def _parse_memory_id(data: object) -> Union[None, Unset, str]:
+            if data is None:
+                return data
+            if isinstance(data, Unset):
+                return data
+            return cast(Union[None, Unset, str], data)
+
+        memory_id = _parse_memory_id(d.pop("memory_id", UNSET))
+
         update_prediction_request = cls(
             expected_label=expected_label,
             tags=tags,
+            memory_id=memory_id,
         )
 
         update_prediction_request.additional_properties = d

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/_utils/auth.py

@@ -22,7 +22,10 @@ from .._generated_api_client.models.api_key_metadata import ApiKeyMetadata
 from .common import DropMode
 
 load_dotenv()  # this needs to be here to ensure env is populated before accessing it
+
+# the defaults here must match nautilus and lighthouse config defaults
 _ORCA_ROOT_ACCESS_API_KEY = os.environ.get("ORCA_ROOT_ACCESS_API_KEY", "00000000-0000-0000-0000-000000000000")
+_DEFAULT_ORG_ID = os.environ.get("DEFAULT_ORG_ID", "10e50000-0000-4000-a000-a78dca14af3a")
 
 
 def _create_api_key(org_id: str, name: str, scopes: list[str] = ["ADMINISTER"]) -> str:
@@ -56,7 +59,7 @@ def _delete_org(org_id: str) -> None:
         delete_org()
 
 
-def _authenticate_local_api(org_id: str = "10e50000-0000-4000-a000-a78dca14af3a", api_key_name: str = "local") -> None:
+def _authenticate_local_api(org_id: str = _DEFAULT_ORG_ID, api_key_name: str = "local") -> None:
     """Connect to the local API at http://localhost:1584/ and authenticate with a new API key"""
     set_base_url("http://localhost:1584/")
     _delete_api_key(org_id, api_key_name, if_not_exists="ignore")

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/classification_model.py

@@ -306,6 +306,7 @@ class ClassificationModel:
                 LabelPrediction({label: <negative: 0>, confidence: 0.05, anomaly_score: 0.1, input_value: 'I am sad'}),
             ]
         """
+
         response = predict_gpu(
             self.id,
             body=PredictionRequest(

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/memoryset.py

@@ -27,6 +27,7 @@ from ._generated_api_client.api import (
     list_memories_with_feedback,
     list_memorysets,
     memoryset_lookup_gpu,
+    potential_duplicate_groups,
     query_memoryset,
     update_memories_gpu,
     update_memory_gpu,
@@ -1276,6 +1277,11 @@ class LabeledMemoryset:
 
         display_suggested_memory_relabels(self)
 
+    def get_potential_duplicate_groups(self):
+        """Group potential duplicates in the memoryset"""
+        response = potential_duplicate_groups(self.name)
+        return response
+
     @staticmethod
     def run_embedding_evaluation(
         datasource: Datasource,

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/memoryset_test.py

@@ -334,3 +334,27 @@ def test_embedding_evaluation(hf_dataset):
     assert response["evaluation_results"][0]["embedding_model_name"] == "CDE_SMALL"
     assert response["evaluation_results"][0]["embedding_model_path"] == "OrcaDB/cde-small-v1"
     Datasource.drop("eval_datasource")
+
+
+@pytest.fixture(scope="function")
+async def test_group_potential_duplicates(memoryset: LabeledMemoryset):
+    memoryset.insert(
+        [
+            dict(value="raspberry soup Is my favorite", label=0),
+            dict(value="Raspberry soup is MY favorite", label=0),
+            dict(value="rAspberry soup is my favorite", label=0),
+            dict(value="raSpberry SOuP is my favorite", label=0),
+            dict(value="rasPberry SOuP is my favorite", label=0),
+            dict(value="bunny rabbit Is not my mom", label=1),
+            dict(value="bunny rabbit is not MY mom", label=1),
+            dict(value="bunny rabbit Is not my moM", label=1),
+            dict(value="bunny rabbit is not my mom", label=1),
+            dict(value="bunny rabbit is not my mom", label=1),
+            dict(value="bunny rabbit is not My mom", label=1),
+        ]
+    )
+
+    memoryset.analyze({"name": "duplicate", "possible_duplicate_threshold": 0.97})
+    response = memoryset.get_potential_duplicate_groups()
+    assert isinstance(response, list)
+    assert sorted([len(res) for res in response]) == [5, 6]  # 5 favorite, 6 mom

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/orca_sdk/telemetry.py

@@ -213,6 +213,8 @@ class LabelPrediction:
         url = f"/telemetry/prediction/{self.prediction_id}/explanation?refresh={refresh}"
         with httpx_client.stream("GET", url) as res:
             if res.status_code != 200:
+                # Read the response body before raising the error
+                res.read()
                 raise get_error_for_response(res)
             for chunk in res.iter_text():
                 yield chunk

{orca_sdk-0.0.86 → orca_sdk-0.0.88}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "orca_sdk"
-version = "0.0.86" # Will be set by CI before building the wheel from the git tag. Do not set manually.
+version = "0.0.88" # Will be set by CI before building the wheel from the git tag. Do not set manually.
 description = "SDK for interacting with Orca Services"
 authors = ["Orca DB Inc. <dev-rel@orcadb.ai>"]
 license = "Apache-2.0"
@@ -17,6 +17,8 @@ pandas = "^2.2.3"
 pyarrow = "^18.0.0"
 torch = "^2.5.1"
 gradio = "5.13.0"
+networkx = "^3.4.2"
+python-dotenv = "^1.1.0"
 
 [tool.poetry.group.dev]
 optional = true
@@ -30,7 +32,6 @@ pytest-asyncio = "^0.25.3"
 pytest-timeout = "^2.3.1"
 pytest-cov = "^6.0.0"
 poethepoet = "^0.31.1"
-python-dotenv = "^1.0.1"
 pyright = "^1.1.399"
 
 # TODO: Use this once poetry 2.0.0 is released https://github.com/python-poetry/poetry/issues/9448
@@ -53,6 +54,7 @@ log_cli_format = "%(asctime)s [%(levelname)s] %(message)s"
 log_cli_date_format = "%Y-%m-%d %H:%M:%S"
 addopts = "--color=yes -s"
 filterwarnings = ["ignore::DeprecationWarning"]
+asyncio_default_fixture_loop_scope = "session"
 
 [build-system]
 requires = ["poetry-core"]