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

shaped/autogen/models/{snowflake_dataset_config.py → snowflake_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.
@@ -17,33 +17,39 @@ import pprint
 import re  # noqa: F401
 import json
 
-from pydantic import BaseModel, ConfigDict, 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 SnowflakeDatasetConfig(BaseModel):
+class SnowflakeTableConfig(BaseModel):
     """
-    SnowflakeDatasetConfig
+    SnowflakeTableConfig
     """ # noqa: E501
-    name: StrictStr
-    replication_key: StrictStr
-    account: StrictStr
-    user: StrictStr
-    password: StrictStr
-    table: StrictStr
+    schema_type: Optional[StrictStr] = Field(default='SNOWFLAKE', description="Schema type discriminator for Snowflake datasets.")
+    name: StrictStr = Field(description="Unique identifier for the Snowflake dataset.")
+    description: Optional[StrictStr] = None
+    replication_key: StrictStr = Field(description="Column name used for incremental replication.")
+    account: StrictStr = Field(description="Snowflake account identifier.")
+    user: StrictStr = Field(description="Snowflake username.")
+    password: StrictStr = Field(description="Snowflake password.")
+    table: StrictStr = Field(description="Snowflake table name to sync.")
+    schedule_interval: Optional[StrictStr] = None
     columns: Optional[List[StrictStr]] = None
     database: Optional[StrictStr] = None
     database_schema: Optional[StrictStr] = None
     warehouse: Optional[StrictStr] = None
     role: Optional[StrictStr] = None
-    schedule_interval: Optional[StrictStr] = '@hourly'
-    schema_type: StrictStr
-    __properties: ClassVar[List[str]] = ["name", "replication_key", "account", "user", "password", "table", "columns", "database", "database_schema", "warehouse", "role", "schedule_interval", "schema_type"]
+    batch_size: Optional[StrictInt] = None
+    unique_keys: Optional[List[StrictStr]] = None
+    __properties: ClassVar[List[str]] = ["schema_type", "name", "description", "replication_key", "account", "user", "password", "table", "schedule_interval", "columns", "database", "database_schema", "warehouse", "role", "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(['SNOWFLAKE']):
             raise ValueError("must be one of enum values ('SNOWFLAKE')")
         return value
@@ -66,7 +72,7 @@ class SnowflakeDatasetConfig(BaseModel):
 
     @classmethod
     def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of SnowflakeDatasetConfig from a JSON string"""
+        """Create an instance of SnowflakeTableConfig from a JSON string"""
         return cls.from_dict(json.loads(json_str))
 
     def to_dict(self) -> Dict[str, Any]:
@@ -87,6 +93,16 @@ class SnowflakeDatasetConfig(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:
@@ -112,11 +128,21 @@ class SnowflakeDatasetConfig(BaseModel):
         if self.role is None and "role" in self.model_fields_set:
             _dict['role'] = None
 
+        # set to None if batch_size (nullable) is None
+        # and model_fields_set contains the field
+        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 SnowflakeDatasetConfig from a dict"""
+        """Create an instance of SnowflakeTableConfig from a dict"""
         if obj is None:
             return None
 
@@ -124,19 +150,22 @@ class SnowflakeDatasetConfig(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 'SNOWFLAKE',
             "name": obj.get("name"),
+            "description": obj.get("description"),
             "replication_key": obj.get("replication_key"),
             "account": obj.get("account"),
             "user": obj.get("user"),
             "password": obj.get("password"),
             "table": obj.get("table"),
+            "schedule_interval": obj.get("schedule_interval"),
             "columns": obj.get("columns"),
             "database": obj.get("database"),
             "database_schema": obj.get("database_schema"),
             "warehouse": obj.get("warehouse"),
             "role": obj.get("role"),
-            "schedule_interval": obj.get("schedule_interval") if obj.get("schedule_interval") is not None else '@hourly',
-            "schema_type": obj.get("schema_type")
+            "batch_size": obj.get("batch_size"),
+            "unique_keys": obj.get("unique_keys")
         })
         return _obj
 

shaped/autogen/models/sql_transform_type.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 SQLTransformType(str, Enum):
+    """
+    SQLTransformType
+    """
+
+    """
+    allowed enum values
+    """
+    VIEW = 'VIEW'
+    MATERIALIZED_VIEW = 'MATERIALIZED_VIEW'
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Self:
+        """Create an instance of SQLTransformType from a JSON string"""
+        return cls(json.loads(json_str))
+
+

shaped/autogen/models/sql_view_config.py

@@ -0,0 +1,111 @@
+# 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.sql_transform_type import SQLTransformType
+from typing import Optional, Set
+from typing_extensions import Self
+
+class SQLViewConfig(BaseModel):
+    """
+    Configuration for SQL-based data views.
+    """ # noqa: E501
+    name: StrictStr = Field(description="Unique identifier for the SQL transform.")
+    transform_type: Optional[StrictStr] = Field(default='SQL', description="Transform type discriminator for SQL transforms.")
+    description: Optional[StrictStr] = None
+    sql_query: StrictStr = Field(description="SQL query to execute for the transform.")
+    sql_transform_type: SQLTransformType = Field(description="Type of SQL transform (VIEW or MATERIALIZED_VIEW).")
+    __properties: ClassVar[List[str]] = ["name", "transform_type", "description", "sql_query", "sql_transform_type"]
+
+    @field_validator('transform_type')
+    def transform_type_validate_enum(cls, value):
+        """Validates the enum"""
+        if value is None:
+            return value
+
+        if value not in set(['SQL']):
+            raise ValueError("must be one of enum values ('SQL')")
+        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 SQLViewConfig 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 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
+
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of SQLViewConfig 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"),
+            "transform_type": obj.get("transform_type") if obj.get("transform_type") is not None else 'SQL',
+            "description": obj.get("description"),
+            "sql_query": obj.get("sql_query"),
+            "sql_transform_type": obj.get("sql_transform_type")
+        })
+        return _obj
+
+

shaped/autogen/models/stemmer_tokenizer.py

@@ -0,0 +1,105 @@
+# 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, StrictBool, StrictStr, field_validator
+from typing import Any, ClassVar, Dict, List, Optional
+from typing import Optional, Set
+from typing_extensions import Self
+
+class StemmerTokenizer(BaseModel):
+    """
+    A standard, language-aware tokenizer that supports stemming, folding, and stop words.
+    """ # noqa: E501
+    language: Optional[StrictStr] = Field(default='en', description="Language code (e.g., en, es, fr).")
+    stemming: Optional[StrictBool] = Field(default=True, description="Whether to apply word stemming.")
+    ascii_folding: Optional[StrictBool] = Field(default=True, description="Whether to fold accented characters to ASCII.")
+    remove_stop_words: Optional[StrictBool] = Field(default=True, description="Whether to remove common stop words.")
+    type: Optional[StrictStr] = Field(default='stemmer', description="Tokenizer type discriminator.")
+    __properties: ClassVar[List[str]] = ["language", "stemming", "ascii_folding", "remove_stop_words", "type"]
+
+    @field_validator('type')
+    def type_validate_enum(cls, value):
+        """Validates the enum"""
+        if value is None:
+            return value
+
+        if value not in set(['stemmer']):
+            raise ValueError("must be one of enum values ('stemmer')")
+        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 StemmerTokenizer 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 StemmerTokenizer from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "language": obj.get("language") if obj.get("language") is not None else 'en',
+            "stemming": obj.get("stemming") if obj.get("stemming") is not None else True,
+            "ascii_folding": obj.get("ascii_folding") if obj.get("ascii_folding") is not None else True,
+            "remove_stop_words": obj.get("remove_stop_words") if obj.get("remove_stop_words") is not None else True,
+            "type": obj.get("type") if obj.get("type") is not None else 'stemmer'
+        })
+        return _obj
+
+

shaped/autogen/models/step_explanation.py

@@ -0,0 +1,137 @@
+# 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 typing import Optional, Set
+from typing_extensions import Self
+
+class StepExplanation(BaseModel):
+    """
+    Explanation for a single pipeline step.
+    """ # noqa: E501
+    step_name: Optional[StrictStr] = None
+    step_type: Optional[StrictStr] = Field(default='', description="Type of step. Examples: 'column_order', 'similarity', 'text_search', 'prebuilt', 'expression', 'score_ensemble', 'diversity', etc.")
+    input_count: Optional[StrictInt] = None
+    output_count: Optional[StrictInt] = None
+    filtered_count: Optional[StrictInt] = None
+    execution_time_ms: Optional[Union[StrictFloat, StrictInt]] = None
+    metadata: Optional[Dict[str, Any]] = Field(default=None, description="Additional step-specific metadata. Contains implementation details specific to the step type.")
+    additional_properties: Dict[str, Any] = {}
+    __properties: ClassVar[List[str]] = ["step_name", "step_type", "input_count", "output_count", "filtered_count", "execution_time_ms", "metadata"]
+
+    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 StepExplanation 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.
+        * Fields in `self.additional_properties` are added to the output dict.
+        """
+        excluded_fields: Set[str] = set([
+            "additional_properties",
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        # puts key-value pairs in additional_properties in the top level
+        if self.additional_properties is not None:
+            for _key, _value in self.additional_properties.items():
+                _dict[_key] = _value
+
+        # set to None if step_name (nullable) is None
+        # and model_fields_set contains the field
+        if self.step_name is None and "step_name" in self.model_fields_set:
+            _dict['step_name'] = 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
+
+        # set to None if filtered_count (nullable) is None
+        # and model_fields_set contains the field
+        if self.filtered_count is None and "filtered_count" in self.model_fields_set:
+            _dict['filtered_count'] = None
+
+        # set to None if execution_time_ms (nullable) is None
+        # and model_fields_set contains the field
+        if self.execution_time_ms is None and "execution_time_ms" in self.model_fields_set:
+            _dict['execution_time_ms'] = None
+
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of StepExplanation from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "step_name": obj.get("step_name"),
+            "step_type": obj.get("step_type") if obj.get("step_type") is not None else '',
+            "input_count": obj.get("input_count"),
+            "output_count": obj.get("output_count"),
+            "filtered_count": obj.get("filtered_count"),
+            "execution_time_ms": obj.get("execution_time_ms"),
+            "metadata": obj.get("metadata")
+        })
+        # store additional fields in additional_properties
+        for _key in obj.keys():
+            if _key not in cls.__properties:
+                _obj.additional_properties[_key] = obj.get(_key)
+
+        return _obj
+
+