shaped 2.0.1__py3-none-any.whl → 2.0.4__py3-none-any.whl

shaped/autogen/models/{redshift_dataset_config.py → redshift_table_config.py}

@@ -3,9 +3,9 @@
 """
     Shaped API
 
-    Welcome to Shaped's API reference docs. These provide a detailed view of the endpoints and CLI commands that Shaped provides and brief explanations of how they should be used.   Shaped's API is composed of 3 components:   1. **Dataset** - used to provision and manage 'Shaped Datasets', which are persisted     data views of external data. Shaped Datasets can be created from any of our     'Shaped connectors' (e.g. S3, Segment, Snowflake, etc.) and support both batch     ingestion (up to a 15min delay) and stream ingestion (up to a 30 second     delay) depending on the specific connector used. Shaped datasets can also be     created from local files, which is particularly useful for getting started     with a snapshot of data.    2. **Model Management** - used to provision and manage 'Shaped Models', which     represent a system of data pipelines, training and serving infrastructure for     your ranking use-case.    3. **Model Inference** - a high performance API that's used to make     user-understanding requests or ranking inferences to your 'Shaped Models'. For     example, the 'rank' endpoint can be used to determine for a given user id     query, what is the content that is most engaging to that user.    The recommended workflow to interact with the Shaped API is as follows:   1. First create 'Shaped Datasets' to sync over data that your Shaped     understanding models will need. The models at the minimum need interaction     data to understand behavior of your users, so start with that and add your item     and user catalog data later.   2. Then create 'Shaped Models' that use your created 'Shaped Datasets' as     input. Your Shaped Model will will start streaming, processing and training     from your connected data immediately. After a few hours your model will have     tuned all parameters based on your data and will deploy an active model.   3. You can now use the 'Model Inference' endpoints to make real-time     inferences to your model based on your use-case. 
+    Welcome to Shaped's API reference docs. These provide a  detailed view of the endpoints and CLI commands that Shaped provides and brief  explanations of how they should be used.  The Shaped API has four main endpoints:  **Tables** - Provision and manage batch and real-time data connectors.   **Views** - Configure SQL transformations and AI enrichment on your input data. Use SQL to combine multiple data sources or use an LLM to add new categories, extract specific attributes from descriptions, etc.  **Engines** - Deploy and manage your relevance engines. The Engine API exposes configuration for indexing logic, input datasets, externam embeddings, and more.  **Query** - Execute queries against your engines, to return data based on an input query or rerank an existing list. The Query API exposes the retrieve, filter, score, and ranking steps of the 4-stage ranking architecture.  The base URL for each endpoint is: `https://api.shaped.ai/v2`
 
-    The version of the OpenAPI document: 1.0.1
+    The version of the OpenAPI document: 2.0.4
     Generated by OpenAPI Generator (https://openapi-generator.tech)
 
     Do not edit the class manually.
@@ -17,34 +17,39 @@ import pprint
 import re  # noqa: F401
 import json
 
-from datetime import datetime
-from pydantic import BaseModel, ConfigDict, StrictInt, StrictStr, field_validator
+from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr, field_validator
 from typing import Any, ClassVar, Dict, List, Optional
 from typing import Optional, Set
 from typing_extensions import Self
 
-class RedshiftDatasetConfig(BaseModel):
+class RedshiftTableConfig(BaseModel):
     """
-    RedshiftDatasetConfig
+    RedshiftTableConfig
     """ # noqa: E501
-    name: StrictStr
-    host: StrictStr
-    port: StrictInt
-    user: StrictStr
-    password: StrictStr
-    table: StrictStr
-    database: StrictStr
-    replication_key: StrictStr
+    schema_type: Optional[StrictStr] = Field(default='REDSHIFT', description="Schema type discriminator for Redshift datasets.")
+    name: StrictStr = Field(description="Unique identifier for the Redshift dataset.")
+    description: Optional[StrictStr] = None
+    host: StrictStr = Field(description="Redshift cluster hostname or IP address.")
+    port: StrictInt = Field(description="Redshift cluster port number.")
+    user: StrictStr = Field(description="Redshift username.")
+    password: StrictStr = Field(description="Redshift password.")
+    table: StrictStr = Field(description="Redshift table name to sync.")
+    database: StrictStr = Field(description="Redshift database name.")
+    replication_key: StrictStr = Field(description="Column name used for incremental replication.")
+    schedule_interval: Optional[StrictStr] = None
     columns: Optional[List[StrictStr]] = None
     database_schema: Optional[StrictStr] = None
-    start_date: Optional[datetime] = None
-    schedule_interval: Optional[StrictStr] = None
-    schema_type: StrictStr
-    __properties: ClassVar[List[str]] = ["name", "host", "port", "user", "password", "table", "database", "replication_key", "columns", "database_schema", "start_date", "schedule_interval", "schema_type"]
+    start_date: Optional[StrictStr] = None
+    batch_size: Optional[StrictInt] = None
+    unique_keys: Optional[List[StrictStr]] = None
+    __properties: ClassVar[List[str]] = ["schema_type", "name", "description", "host", "port", "user", "password", "table", "database", "replication_key", "schedule_interval", "columns", "database_schema", "start_date", "batch_size", "unique_keys"]
 
     @field_validator('schema_type')
     def schema_type_validate_enum(cls, value):
         """Validates the enum"""
+        if value is None:
+            return value
+
         if value not in set(['REDSHIFT']):
             raise ValueError("must be one of enum values ('REDSHIFT')")
         return value
@@ -67,7 +72,7 @@ class RedshiftDatasetConfig(BaseModel):
 
     @classmethod
     def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of RedshiftDatasetConfig from a JSON string"""
+        """Create an instance of RedshiftTableConfig from a JSON string"""
         return cls.from_dict(json.loads(json_str))
 
     def to_dict(self) -> Dict[str, Any]:
@@ -88,6 +93,16 @@ class RedshiftDatasetConfig(BaseModel):
             exclude=excluded_fields,
             exclude_none=True,
         )
+        # set to None if description (nullable) is None
+        # and model_fields_set contains the field
+        if self.description is None and "description" in self.model_fields_set:
+            _dict['description'] = None
+
+        # set to None if schedule_interval (nullable) is None
+        # and model_fields_set contains the field
+        if self.schedule_interval is None and "schedule_interval" in self.model_fields_set:
+            _dict['schedule_interval'] = None
+
         # set to None if columns (nullable) is None
         # and model_fields_set contains the field
         if self.columns is None and "columns" in self.model_fields_set:
@@ -103,16 +118,21 @@ class RedshiftDatasetConfig(BaseModel):
         if self.start_date is None and "start_date" in self.model_fields_set:
             _dict['start_date'] = None
 
-        # set to None if schedule_interval (nullable) is None
+        # set to None if batch_size (nullable) is None
         # and model_fields_set contains the field
-        if self.schedule_interval is None and "schedule_interval" in self.model_fields_set:
-            _dict['schedule_interval'] = None
+        if self.batch_size is None and "batch_size" in self.model_fields_set:
+            _dict['batch_size'] = None
+
+        # set to None if unique_keys (nullable) is None
+        # and model_fields_set contains the field
+        if self.unique_keys is None and "unique_keys" in self.model_fields_set:
+            _dict['unique_keys'] = None
 
         return _dict
 
     @classmethod
     def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of RedshiftDatasetConfig from a dict"""
+        """Create an instance of RedshiftTableConfig from a dict"""
         if obj is None:
             return None
 
@@ -120,7 +140,9 @@ class RedshiftDatasetConfig(BaseModel):
             return cls.model_validate(obj)
 
         _obj = cls.model_validate({
+            "schema_type": obj.get("schema_type") if obj.get("schema_type") is not None else 'REDSHIFT',
             "name": obj.get("name"),
+            "description": obj.get("description"),
             "host": obj.get("host"),
             "port": obj.get("port"),
             "user": obj.get("user"),
@@ -128,11 +150,12 @@ class RedshiftDatasetConfig(BaseModel):
             "table": obj.get("table"),
             "database": obj.get("database"),
             "replication_key": obj.get("replication_key"),
+            "schedule_interval": obj.get("schedule_interval"),
             "columns": obj.get("columns"),
             "database_schema": obj.get("database_schema"),
             "start_date": obj.get("start_date"),
-            "schedule_interval": obj.get("schedule_interval"),
-            "schema_type": obj.get("schema_type")
+            "batch_size": obj.get("batch_size"),
+            "unique_keys": obj.get("unique_keys")
         })
         return _obj
 

shaped/autogen/models/reference_table_config.py

@@ -0,0 +1,113 @@
+# coding: utf-8
+
+"""
+    Shaped API
+
+    Welcome to Shaped's API reference docs. These provide a  detailed view of the endpoints and CLI commands that Shaped provides and brief  explanations of how they should be used.  The Shaped API has four main endpoints:  **Tables** - Provision and manage batch and real-time data connectors.   **Views** - Configure SQL transformations and AI enrichment on your input data. Use SQL to combine multiple data sources or use an LLM to add new categories, extract specific attributes from descriptions, etc.  **Engines** - Deploy and manage your relevance engines. The Engine API exposes configuration for indexing logic, input datasets, externam embeddings, and more.  **Query** - Execute queries against your engines, to return data based on an input query or rerank an existing list. The Query API exposes the retrieve, filter, score, and ranking steps of the 4-stage ranking architecture.  The base URL for each endpoint is: `https://api.shaped.ai/v2`
+
+    The version of the OpenAPI document: 2.0.4
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+import pprint
+import re  # noqa: F401
+import json
+
+from pydantic import BaseModel, ConfigDict, Field, StrictStr, field_validator
+from typing import Any, ClassVar, Dict, List, Optional
+from typing import Optional, Set
+from typing_extensions import Self
+
+class ReferenceTableConfig(BaseModel):
+    """
+    Table config that references a table by name with column selection and optional where clause. Limited to single table queries (no joins).
+    """ # noqa: E501
+    type: Optional[StrictStr] = Field(default='table', description="Type discriminator for table reference config.")
+    name: StrictStr = Field(description="Name of the table to use.")
+    columns: Optional[List[StrictStr]] = None
+    where: Optional[StrictStr] = None
+    __properties: ClassVar[List[str]] = ["type", "name", "columns", "where"]
+
+    @field_validator('type')
+    def type_validate_enum(cls, value):
+        """Validates the enum"""
+        if value is None:
+            return value
+
+        if value not in set(['table']):
+            raise ValueError("must be one of enum values ('table')")
+        return value
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.model_dump(by_alias=True))
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the model using alias"""
+        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
+        return json.dumps(self.to_dict())
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Optional[Self]:
+        """Create an instance of ReferenceTableConfig from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Return the dictionary representation of the model using alias.
+
+        This has the following differences from calling pydantic's
+        `self.model_dump(by_alias=True)`:
+
+        * `None` is only added to the output dict for nullable fields that
+          were set at model initialization. Other fields with value `None`
+          are ignored.
+        """
+        excluded_fields: Set[str] = set([
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        # set to None if columns (nullable) is None
+        # and model_fields_set contains the field
+        if self.columns is None and "columns" in self.model_fields_set:
+            _dict['columns'] = None
+
+        # set to None if where (nullable) is None
+        # and model_fields_set contains the field
+        if self.where is None and "where" in self.model_fields_set:
+            _dict['where'] = None
+
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of ReferenceTableConfig from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "type": obj.get("type") if obj.get("type") is not None else 'table',
+            "name": obj.get("name"),
+            "columns": obj.get("columns"),
+            "where": obj.get("where")
+        })
+        return _obj
+
+

shaped/autogen/models/regularization.py

@@ -0,0 +1,136 @@
+# coding: utf-8
+
+"""
+    Shaped API
+
+    Welcome to Shaped's API reference docs. These provide a  detailed view of the endpoints and CLI commands that Shaped provides and brief  explanations of how they should be used.  The Shaped API has four main endpoints:  **Tables** - Provision and manage batch and real-time data connectors.   **Views** - Configure SQL transformations and AI enrichment on your input data. Use SQL to combine multiple data sources or use an LLM to add new categories, extract specific attributes from descriptions, etc.  **Engines** - Deploy and manage your relevance engines. The Engine API exposes configuration for indexing logic, input datasets, externam embeddings, and more.  **Query** - Execute queries against your engines, to return data based on an input query or rerank an existing list. The Query API exposes the retrieve, filter, score, and ranking steps of the 4-stage ranking architecture.  The base URL for each endpoint is: `https://api.shaped.ai/v2`
+
+    The version of the OpenAPI document: 2.0.4
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+from inspect import getfullargspec
+import json
+import pprint
+import re  # noqa: F401
+from pydantic import BaseModel, ConfigDict, Field, StrictFloat, StrictInt, StrictStr, ValidationError, field_validator
+from typing import Optional, Union
+from shaped.autogen.models.tunable_float import TunableFloat
+from typing import Union, Any, List, Set, TYPE_CHECKING, Optional, Dict
+from typing_extensions import Literal, Self
+from pydantic import Field
+
+REGULARIZATION_ANY_OF_SCHEMAS = ["TunableFloat", "float"]
+
+class Regularization(BaseModel):
+    """
+    Regularization parameter to prevent overfitting.
+    """
+
+    # data type: float
+    anyof_schema_1_validator: Optional[Union[StrictFloat, StrictInt]] = None
+    # data type: TunableFloat
+    anyof_schema_2_validator: Optional[TunableFloat] = None
+    if TYPE_CHECKING:
+        actual_instance: Optional[Union[TunableFloat, float]] = None
+    else:
+        actual_instance: Any = None
+    any_of_schemas: Set[str] = { "TunableFloat", "float" }
+
+    model_config = {
+        "validate_assignment": True,
+        "protected_namespaces": (),
+    }
+
+    def __init__(self, *args, **kwargs) -> None:
+        if args:
+            if len(args) > 1:
+                raise ValueError("If a position argument is used, only 1 is allowed to set `actual_instance`")
+            if kwargs:
+                raise ValueError("If a position argument is used, keyword arguments cannot be used.")
+            super().__init__(actual_instance=args[0])
+        else:
+            super().__init__(**kwargs)
+
+    @field_validator('actual_instance')
+    def actual_instance_must_validate_anyof(cls, v):
+        instance = Regularization.model_construct()
+        error_messages = []
+        # validate data type: float
+        try:
+            instance.anyof_schema_1_validator = v
+            return v
+        except (ValidationError, ValueError) as e:
+            error_messages.append(str(e))
+        # validate data type: TunableFloat
+        if not isinstance(v, TunableFloat):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `TunableFloat`")
+        else:
+            return v
+
+        if error_messages:
+            # no match
+            raise ValueError("No match found when setting the actual_instance in Regularization with anyOf schemas: TunableFloat, float. Details: " + ", ".join(error_messages))
+        else:
+            return v
+
+    @classmethod
+    def from_dict(cls, obj: Dict[str, Any]) -> Self:
+        return cls.from_json(json.dumps(obj))
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Self:
+        """Returns the object represented by the json string"""
+        instance = cls.model_construct()
+        error_messages = []
+        # deserialize data into float
+        try:
+            # validation
+            instance.anyof_schema_1_validator = json.loads(json_str)
+            # assign value to actual_instance
+            instance.actual_instance = instance.anyof_schema_1_validator
+            return instance
+        except (ValidationError, ValueError) as e:
+            error_messages.append(str(e))
+        # anyof_schema_2_validator: Optional[TunableFloat] = None
+        try:
+            instance.actual_instance = TunableFloat.from_json(json_str)
+            return instance
+        except (ValidationError, ValueError) as e:
+             error_messages.append(str(e))
+
+        if error_messages:
+            # no match
+            raise ValueError("No match found when deserializing the JSON string into Regularization with anyOf schemas: TunableFloat, float. Details: " + ", ".join(error_messages))
+        else:
+            return instance
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the actual instance"""
+        if self.actual_instance is None:
+            return "null"
+
+        if hasattr(self.actual_instance, "to_json") and callable(self.actual_instance.to_json):
+            return self.actual_instance.to_json()
+        else:
+            return json.dumps(self.actual_instance)
+
+    def to_dict(self) -> Optional[Union[Dict[str, Any], TunableFloat, float]]:
+        """Returns the dict representation of the actual instance"""
+        if self.actual_instance is None:
+            return None
+
+        if hasattr(self.actual_instance, "to_dict") and callable(self.actual_instance.to_dict):
+            return self.actual_instance.to_dict()
+        else:
+            return self.actual_instance
+
+    def to_str(self) -> str:
+        """Returns the string representation of the actual instance"""
+        return pprint.pformat(self.model_dump())
+
+

shaped/autogen/models/reorder_inner.py

@@ -0,0 +1,149 @@
+# coding: utf-8
+
+"""
+    Shaped API
+
+    Welcome to Shaped's API reference docs. These provide a  detailed view of the endpoints and CLI commands that Shaped provides and brief  explanations of how they should be used.  The Shaped API has four main endpoints:  **Tables** - Provision and manage batch and real-time data connectors.   **Views** - Configure SQL transformations and AI enrichment on your input data. Use SQL to combine multiple data sources or use an LLM to add new categories, extract specific attributes from descriptions, etc.  **Engines** - Deploy and manage your relevance engines. The Engine API exposes configuration for indexing logic, input datasets, externam embeddings, and more.  **Query** - Execute queries against your engines, to return data based on an input query or rerank an existing list. The Query API exposes the retrieve, filter, score, and ranking steps of the 4-stage ranking architecture.  The base URL for each endpoint is: `https://api.shaped.ai/v2`
+
+    The version of the OpenAPI document: 2.0.4
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+from inspect import getfullargspec
+import json
+import pprint
+import re  # noqa: F401
+from pydantic import BaseModel, ConfigDict, Field, StrictStr, ValidationError, field_validator
+from typing import Optional
+from shaped.autogen.models.boosted_reorder_step import BoostedReorderStep
+from shaped.autogen.models.diversity_reorder_step import DiversityReorderStep
+from shaped.autogen.models.exploration_reorder_step import ExplorationReorderStep
+from typing import Union, Any, List, Set, TYPE_CHECKING, Optional, Dict
+from typing_extensions import Literal, Self
+from pydantic import Field
+
+REORDERINNER_ANY_OF_SCHEMAS = ["BoostedReorderStep", "DiversityReorderStep", "ExplorationReorderStep"]
+
+class ReorderInner(BaseModel):
+    """
+    ReorderInner
+    """
+
+    # data type: ExplorationReorderStep
+    anyof_schema_1_validator: Optional[ExplorationReorderStep] = None
+    # data type: BoostedReorderStep
+    anyof_schema_2_validator: Optional[BoostedReorderStep] = None
+    # data type: DiversityReorderStep
+    anyof_schema_3_validator: Optional[DiversityReorderStep] = None
+    if TYPE_CHECKING:
+        actual_instance: Optional[Union[BoostedReorderStep, DiversityReorderStep, ExplorationReorderStep]] = None
+    else:
+        actual_instance: Any = None
+    any_of_schemas: Set[str] = { "BoostedReorderStep", "DiversityReorderStep", "ExplorationReorderStep" }
+
+    model_config = {
+        "validate_assignment": True,
+        "protected_namespaces": (),
+    }
+
+    def __init__(self, *args, **kwargs) -> None:
+        if args:
+            if len(args) > 1:
+                raise ValueError("If a position argument is used, only 1 is allowed to set `actual_instance`")
+            if kwargs:
+                raise ValueError("If a position argument is used, keyword arguments cannot be used.")
+            super().__init__(actual_instance=args[0])
+        else:
+            super().__init__(**kwargs)
+
+    @field_validator('actual_instance')
+    def actual_instance_must_validate_anyof(cls, v):
+        instance = ReorderInner.model_construct()
+        error_messages = []
+        # validate data type: ExplorationReorderStep
+        if not isinstance(v, ExplorationReorderStep):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `ExplorationReorderStep`")
+        else:
+            return v
+
+        # validate data type: BoostedReorderStep
+        if not isinstance(v, BoostedReorderStep):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `BoostedReorderStep`")
+        else:
+            return v
+
+        # validate data type: DiversityReorderStep
+        if not isinstance(v, DiversityReorderStep):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `DiversityReorderStep`")
+        else:
+            return v
+
+        if error_messages:
+            # no match
+            raise ValueError("No match found when setting the actual_instance in ReorderInner with anyOf schemas: BoostedReorderStep, DiversityReorderStep, ExplorationReorderStep. Details: " + ", ".join(error_messages))
+        else:
+            return v
+
+    @classmethod
+    def from_dict(cls, obj: Dict[str, Any]) -> Self:
+        return cls.from_json(json.dumps(obj))
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Self:
+        """Returns the object represented by the json string"""
+        instance = cls.model_construct()
+        error_messages = []
+        # anyof_schema_1_validator: Optional[ExplorationReorderStep] = None
+        try:
+            instance.actual_instance = ExplorationReorderStep.from_json(json_str)
+            return instance
+        except (ValidationError, ValueError) as e:
+             error_messages.append(str(e))
+        # anyof_schema_2_validator: Optional[BoostedReorderStep] = None
+        try:
+            instance.actual_instance = BoostedReorderStep.from_json(json_str)
+            return instance
+        except (ValidationError, ValueError) as e:
+             error_messages.append(str(e))
+        # anyof_schema_3_validator: Optional[DiversityReorderStep] = None
+        try:
+            instance.actual_instance = DiversityReorderStep.from_json(json_str)
+            return instance
+        except (ValidationError, ValueError) as e:
+             error_messages.append(str(e))
+
+        if error_messages:
+            # no match
+            raise ValueError("No match found when deserializing the JSON string into ReorderInner with anyOf schemas: BoostedReorderStep, DiversityReorderStep, ExplorationReorderStep. Details: " + ", ".join(error_messages))
+        else:
+            return instance
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the actual instance"""
+        if self.actual_instance is None:
+            return "null"
+
+        if hasattr(self.actual_instance, "to_json") and callable(self.actual_instance.to_json):
+            return self.actual_instance.to_json()
+        else:
+            return json.dumps(self.actual_instance)
+
+    def to_dict(self) -> Optional[Union[Dict[str, Any], BoostedReorderStep, DiversityReorderStep, ExplorationReorderStep]]:
+        """Returns the dict representation of the actual instance"""
+        if self.actual_instance is None:
+            return None
+
+        if hasattr(self.actual_instance, "to_dict") and callable(self.actual_instance.to_dict):
+            return self.actual_instance.to_dict()
+        else:
+            return self.actual_instance
+
+    def to_str(self) -> str:
+        """Returns the string representation of the actual instance"""
+        return pprint.pformat(self.model_dump())
+
+