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

shaped/autogen/models/passthrough_score.py

@@ -0,0 +1,104 @@
+# 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 PassthroughScore(BaseModel):
+    """
+    A simple step that uses the raw retrieval scores.
+    """ # noqa: E501
+    name: Optional[StrictStr] = None
+    type: Optional[StrictStr] = Field(default='passthrough', description="Score step type discriminator.")
+    __properties: ClassVar[List[str]] = ["name", "type"]
+
+    @field_validator('type')
+    def type_validate_enum(cls, value):
+        """Validates the enum"""
+        if value is None:
+            return value
+
+        if value not in set(['passthrough']):
+            raise ValueError("must be one of enum values ('passthrough')")
+        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 PassthroughScore 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 name (nullable) is None
+        # and model_fields_set contains the field
+        if self.name is None and "name" in self.model_fields_set:
+            _dict['name'] = None
+
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of PassthroughScore from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "name": obj.get("name"),
+            "type": obj.get("type") if obj.get("type") is not None else 'passthrough'
+        })
+        return _obj
+
+

shaped/autogen/models/personal_filter.py

@@ -0,0 +1,104 @@
+# 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 shaped.autogen.models.filter_index_type import FilterIndexType
+from typing import Optional, Set
+from typing_extensions import Self
+
+class PersonalFilter(BaseModel):
+    """
+    A user-specific filter. The source dataset must contain user and item identifiers.
+    """ # noqa: E501
+    user_id_column: Optional[StrictStr] = Field(default='user_id', description="Column name for user identifiers.")
+    item_id_column: Optional[StrictStr] = Field(default='item_id', description="Column name for item identifiers.")
+    index_type: Optional[FilterIndexType] = Field(default=None, description="Index type for fast filter lookups.")
+    type: Optional[StrictStr] = Field(default='personal', description="Filter type discriminator.")
+    __properties: ClassVar[List[str]] = ["user_id_column", "item_id_column", "index_type", "type"]
+
+    @field_validator('type')
+    def type_validate_enum(cls, value):
+        """Validates the enum"""
+        if value is None:
+            return value
+
+        if value not in set(['personal']):
+            raise ValueError("must be one of enum values ('personal')")
+        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 PersonalFilter 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,
+        )
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of PersonalFilter from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "user_id_column": obj.get("user_id_column") if obj.get("user_id_column") is not None else 'user_id',
+            "item_id_column": obj.get("item_id_column") if obj.get("item_id_column") is not None else 'item_id',
+            "index_type": obj.get("index_type"),
+            "type": obj.get("type") if obj.get("type") is not None else 'personal'
+        })
+        return _obj
+
+

shaped/autogen/models/pipeline_stage_explanation.py

@@ -0,0 +1,118 @@
+# 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, StrictFloat, StrictInt, StrictStr
+from typing import Any, ClassVar, Dict, List, Optional, Union
+from shaped.autogen.models.steps_inner import StepsInner
+from typing import Optional, Set
+from typing_extensions import Self
+
+class PipelineStageExplanation(BaseModel):
+    """
+    Explanation for an entire pipeline stage (e.g., all retrieval steps).
+    """ # noqa: E501
+    stage_name: StrictStr = Field(description="Name of the pipeline stage. One of 'retrieve', 'filter', 'score', or 'reorder'.")
+    total_execution_time_ms: Optional[Union[StrictFloat, StrictInt]] = None
+    input_count: Optional[StrictInt] = None
+    output_count: Optional[StrictInt] = None
+    steps: Optional[List[StepsInner]] = Field(default=None, description="List of step explanations for each step executed in this stage. Steps are ordered by execution order.")
+    __properties: ClassVar[List[str]] = ["stage_name", "total_execution_time_ms", "input_count", "output_count", "steps"]
+
+    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 PipelineStageExplanation 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,
+        )
+        # override the default output from pydantic by calling `to_dict()` of each item in steps (list)
+        _items = []
+        if self.steps:
+            for _item_steps in self.steps:
+                if _item_steps:
+                    _items.append(_item_steps.to_dict())
+            _dict['steps'] = _items
+        # set to None if total_execution_time_ms (nullable) is None
+        # and model_fields_set contains the field
+        if self.total_execution_time_ms is None and "total_execution_time_ms" in self.model_fields_set:
+            _dict['total_execution_time_ms'] = None
+
+        # set to None if input_count (nullable) is None
+        # and model_fields_set contains the field
+        if self.input_count is None and "input_count" in self.model_fields_set:
+            _dict['input_count'] = None
+
+        # set to None if output_count (nullable) is None
+        # and model_fields_set contains the field
+        if self.output_count is None and "output_count" in self.model_fields_set:
+            _dict['output_count'] = None
+
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of PipelineStageExplanation from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "stage_name": obj.get("stage_name"),
+            "total_execution_time_ms": obj.get("total_execution_time_ms"),
+            "input_count": obj.get("input_count"),
+            "output_count": obj.get("output_count"),
+            "steps": [StepsInner.from_dict(_item) for _item in obj["steps"]] if obj.get("steps") is not None else None
+        })
+        return _obj
+
+

shaped/autogen/models/policy.py

@@ -0,0 +1,134 @@
+# 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.latency_scaling_policy import LatencyScalingPolicy
+from shaped.autogen.models.requests_per_second_scaling_policy import RequestsPerSecondScalingPolicy
+from typing import Union, Any, List, Set, TYPE_CHECKING, Optional, Dict
+from typing_extensions import Literal, Self
+from pydantic import Field
+
+POLICY_ANY_OF_SCHEMAS = ["LatencyScalingPolicy", "RequestsPerSecondScalingPolicy"]
+
+class Policy(BaseModel):
+    """
+    Autoscaling policy configuration.
+    """
+
+    # data type: RequestsPerSecondScalingPolicy
+    anyof_schema_1_validator: Optional[RequestsPerSecondScalingPolicy] = None
+    # data type: LatencyScalingPolicy
+    anyof_schema_2_validator: Optional[LatencyScalingPolicy] = None
+    if TYPE_CHECKING:
+        actual_instance: Optional[Union[LatencyScalingPolicy, RequestsPerSecondScalingPolicy]] = None
+    else:
+        actual_instance: Any = None
+    any_of_schemas: Set[str] = { "LatencyScalingPolicy", "RequestsPerSecondScalingPolicy" }
+
+    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 = Policy.model_construct()
+        error_messages = []
+        # validate data type: RequestsPerSecondScalingPolicy
+        if not isinstance(v, RequestsPerSecondScalingPolicy):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `RequestsPerSecondScalingPolicy`")
+        else:
+            return v
+
+        # validate data type: LatencyScalingPolicy
+        if not isinstance(v, LatencyScalingPolicy):
+            error_messages.append(f"Error! Input type `{type(v)}` is not `LatencyScalingPolicy`")
+        else:
+            return v
+
+        if error_messages:
+            # no match
+            raise ValueError("No match found when setting the actual_instance in Policy with anyOf schemas: LatencyScalingPolicy, RequestsPerSecondScalingPolicy. 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[RequestsPerSecondScalingPolicy] = None
+        try:
+            instance.actual_instance = RequestsPerSecondScalingPolicy.from_json(json_str)
+            return instance
+        except (ValidationError, ValueError) as e:
+             error_messages.append(str(e))
+        # anyof_schema_2_validator: Optional[LatencyScalingPolicy] = None
+        try:
+            instance.actual_instance = LatencyScalingPolicy.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 Policy with anyOf schemas: LatencyScalingPolicy, RequestsPerSecondScalingPolicy. 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], LatencyScalingPolicy, RequestsPerSecondScalingPolicy]]:
+        """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/pool_fn.py

@@ -0,0 +1,152 @@
+# 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: 2.0.0
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+
+import json
+import pprint
+import re  # noqa: F401
+from typing import TYPE_CHECKING, Any, Dict, Optional, Set, Union
+
+from pydantic import BaseModel, ValidationError, field_validator
+from shaped.autogen.models.encoding_pooling_strategy import EncodingPoolingStrategy
+from shaped.autogen.models.tunable_string import TunableString
+from typing_extensions import Self
+
+POOLFN_ANY_OF_SCHEMAS = ["EncodingPoolingStrategy", "TunableString"]
+
+
+class PoolFn(BaseModel):
+    """
+    PoolFn
+    """
+
+    # data type: EncodingPoolingStrategy
+    anyof_schema_1_validator: Optional[EncodingPoolingStrategy] = None
+    # data type: TunableString
+    anyof_schema_2_validator: Optional[TunableString] = None
+    if TYPE_CHECKING:
+        actual_instance: Optional[Union[EncodingPoolingStrategy, TunableString]] = None
+    else:
+        actual_instance: Any = None
+    any_of_schemas: Set[str] = {"EncodingPoolingStrategy", "TunableString"}
+
+    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 = PoolFn.model_construct()
+        error_messages = []
+        # validate data type: EncodingPoolingStrategy
+        if not isinstance(v, EncodingPoolingStrategy):
+            error_messages.append(
+                f"Error! Input type `{type(v)}` is not `EncodingPoolingStrategy`"
+            )
+        else:
+            return v
+
+        # validate data type: TunableString
+        if not isinstance(v, TunableString):
+            error_messages.append(
+                f"Error! Input type `{type(v)}` is not `TunableString`"
+            )
+        else:
+            return v
+
+        if error_messages:
+            # no match
+            raise ValueError(
+                "No match found when setting the actual_instance in PoolFn with anyOf schemas: EncodingPoolingStrategy, TunableString. 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[EncodingPoolingStrategy] = None
+        try:
+            instance.actual_instance = EncodingPoolingStrategy.from_json(json_str)
+            return instance
+        except (ValidationError, ValueError) as e:
+            error_messages.append(str(e))
+        # anyof_schema_2_validator: Optional[TunableString] = None
+        try:
+            instance.actual_instance = TunableString.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 PoolFn with anyOf schemas: EncodingPoolingStrategy, TunableString. 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], EncodingPoolingStrategy, TunableString]]:
+        """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/pooling_function.py

@@ -0,0 +1,37 @@
+# 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 json
+from enum import Enum
+from typing_extensions import Self
+
+
+class PoolingFunction(str, Enum):
+    """
+    The function to use when pooling multiple embeddings into one.
+    """
+
+    """
+    allowed enum values
+    """
+    MAX = 'max'
+    MEAN = 'mean'
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Self:
+        """Create an instance of PoolingFunction from a JSON string"""
+        return cls(json.loads(json_str))
+
+