Feature/embeddings

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "pyfusion"
-version = "2.0.6"
+version = "2.0.7-dev0"
 edition = "2021"
 
 

py_src/fusion/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = """Fusion Devs"""
 __email__ = "[email protected]"
-__version__ = "2.0.6"
+__version__ = "2.0.7-dev0"
 
 from fusion._fusion import FusionCredentials
 from fusion.fs_sync import fsync

py_src/fusion/attributes.py

@@ -155,7 +155,7 @@ def _use_client(self, client: Fusion | None) -> Fusion:
         if res is None:
             raise ValueError("A Fusion client object is required.")
         return res
-        
+
     @classmethod
     def _from_series(
         cls: type[Attribute],
@@ -436,7 +436,7 @@ def delete(
         resp = client.session.delete(url)
         requests_raise_for_status(resp)
         return resp if return_resp_obj else None
-    
+
     def set_lineage(
         self,
         attributes: list[Attribute],
@@ -479,22 +479,18 @@ def set_lineage(
             if attribute.application_id is None:
                 raise ValueError(f"The 'application_id' attribute is required for setting lineage.")
             attr_dict = {
-                    "catalog": catalog,
-                    "attribute": attribute.identifier,
-                    "applicationId": attribute.application_id
-                }
+                "catalog": catalog,
+                "attribute": attribute.identifier,
+                "applicationId": attribute.application_id,
+            }
             target_attributes.append(attr_dict)
 
         url = f"{client.root_url}catalogs/{catalog}/attributes/lineage"
         data = [
             {
-                "source": {
-                    "catalog": catalog,
-                    "attribute": self.identifier,
-                    "applicationId": self.application_id
-            },
-            "targets": target_attributes
-        }
+                "source": {"catalog": catalog, "attribute": self.identifier, "applicationId": self.application_id},
+                "targets": target_attributes,
+            }
         ]
         resp = client.session.post(url, json=data)
         requests_raise_for_status(resp)

py_src/fusion/dataflow.py

@@ -25,6 +25,7 @@ class DataFlow(Dataset):
         type_ (str | None): The type of dataset. Defaults to "Flow".
 
     """
+
     producer_application_id: dict[str, str] | None = None
     consumer_application_id: list[dict[str, str]] | dict[str, str] | None = None
     flow_details: dict[str, str] | None = None
@@ -77,6 +78,7 @@ def add_registered_attribute(
 @dataclass
 class InputDataFlow(DataFlow):
     """InputDataFlow class for maintaining input data flow metadata."""
+
     flow_details: dict[str, str] | None = field(default_factory=lambda: {"flowDirection": "Input"})
 
     def __repr__(self: InputDataFlow) -> str:
@@ -93,6 +95,7 @@ def __repr__(self: InputDataFlow) -> str:
 @dataclass
 class OutputDataFlow(DataFlow):
     """OutputDataFlow class for maintaining output data flow metadata."""
+
     flow_details: dict[str, str] | None = field(default_factory=lambda: {"flowDirection": "Output"})
 
     def __repr__(self: OutputDataFlow) -> str:

py_src/fusion/dataset.py

@@ -67,7 +67,7 @@ class Dataset(metaclass=CamelCaseMeta):
         is_highly_confidential (bool | None, optional): is_highly_confidential. Defaults to None.
         is_active (bool | None, optional): is_active. Defaults to None.
         owners (list[str] | None, optional): The owners of the dataset. Defaults to None.
-        application_id (str | dict[str, str] | None, optional): The application (most commonly seal ID) that the 
+        application_id (str | dict[str, str] | None, optional): The application (most commonly seal ID) that the
             dataset/report/flow is owned by. Accepts string format for seal IDs, or a dictionary containing 'id' and
             'type' as keys. Defaults to None.
         _client (Any, optional): A Fusion client object. Defaults to None.
@@ -585,7 +585,6 @@ def create(
         if data.get("report", None) and data["report"]["tier"] == "":
             raise ValueError("Tier cannot be blank for reports.")
 
-
         url = f"{client.root_url}catalogs/{catalog}/datasets/{self.identifier}"
         resp: requests.Response = client.session.post(url, json=data)
         requests_raise_for_status(resp)