Create Transform
API that transforms unstructured data into structured format based on your schema. You can specify classification, extraction and generation options on the data all in the transform_params
Represents a transformation request.
Attributes: proj_id (str): The id of the project. transform_name (Optional[str], optional): The name of the transformation. Defaults to None. transform_params (TransformParams): The parameters for the transformation.
The transform_name parameter is an optional parameter that provides a human-readable name or description for the transformation, which can be useful for identifying and referencing transformations. If provided, the transform_name parameter should be a string. If not provided, the value of transform_name will be None.
Applicable for table transform mode only. Optional parameter that specifies the table names to be included for table transforms.
Parameter that specifies the table names to be included for table transforms.
Using advanced reasoning when extracting rows from the tables. Transformation becomes slower and more computationally intensive
The model to be used for the transformation. Must be one of 'trellis-scale', 'trellis-premium', or 'trellis-vertix'
The mode to be used for the transformation. Must be one of 'document' or 'table'
Authorizations
Body
Represents a transformation request.
Attributes: proj_id (str): The id of the project. transform_name (Optional[str], optional): The name of the transformation. Defaults to None. transform_params (TransformParams): The parameters for the transformation.
The model to be used for the transformation. Must be one of 'trellis-scale', 'trellis-premium', or 'trellis-vertix'
Applicable for table transform mode only. Optional parameter that specifies the table names to be included for table transforms.
Parameter that specifies the table names to be included for table transforms.
Using advanced reasoning when extracting rows from the tables. Transformation becomes slower and more computationally intensive
The mode to be used for the transformation. Must be one of 'document' or 'table'
Name of the column to be transformed. Any alphanumeric characters are allowed. Must be unique.
TransformColumnType is an enumeration that defines various data types for transforming columns.
Attributes:
text (str): Represents a text data type.
integer (str): Represents an integer data type. (Deprecated in Jan 2025: Use number instead)
numeric (str): Represents a numeric data type. (Deprecated in Jan 2025: Use number instead)
boolean (str): Represents a boolean data type.
list (str): Represents a list data type.
object (str): Represents an object data type.
string (str): Represents a string data type. (Deprecated in Jan 2025: Use text instead)
number (str): Represents a number data type.
time (str): Represents a time data type.
date (str): Represents a date data type.
text[] (str): Represents an array of text data type. (Deprecated in Jan 2025)
jsonb (str): Represents a JSONB data type. (Deprecated in Jan 2025)
Note:
Because of upcoming changes, please use `list`, `object`, `text`, `date`, `time`, and `number` going forward.
text
, integer
, numeric
, boolean
, list
, object
, string
, number
, time
, date
, text[]
, jsonb
Type of transformation to be applied.
extraction
, classification
, generation
Description of the task to be performed
Required when column_type is object
or list
. Defines the structure of object or list operations. If column_type is list
, then operations should only be of length 1 since list
can only be of one type. If column_type is object
, then operations can be longer of length one (and optionally be nested.)
Name of the column to be transformed. Any alphanumeric characters are allowed. Must be unique.
TransformColumnType is an enumeration that defines various data types for transforming columns.
Attributes:
text (str): Represents a text data type.
integer (str): Represents an integer data type. (Deprecated in Jan 2025: Use number instead)
numeric (str): Represents a numeric data type. (Deprecated in Jan 2025: Use number instead)
boolean (str): Represents a boolean data type.
list (str): Represents a list data type.
object (str): Represents an object data type.
string (str): Represents a string data type. (Deprecated in Jan 2025: Use text instead)
number (str): Represents a number data type.
time (str): Represents a time data type.
date (str): Represents a date data type.
text[] (str): Represents an array of text data type. (Deprecated in Jan 2025)
jsonb (str): Represents a JSONB data type. (Deprecated in Jan 2025)
Note:
Because of upcoming changes, please use `list`, `object`, `text`, `date`, `time`, and `number` going forward.
text
, integer
, numeric
, boolean
, list
, object
, string
, number
, time
, date
, text[]
, jsonb
Type of transformation to be applied.
extraction
, classification
, generation
Description of the task to be performed
Required when column_type is object
or list
. Defines the structure of object or list operations. If column_type is list
, then operations should only be of length 1 since list
can only be of one type. If column_type is object
, then operations can be longer of length one (and optionally be nested.)
Name of the column to be transformed. Any alphanumeric characters are allowed. Must be unique.
TransformColumnType is an enumeration that defines various data types for transforming columns.
Attributes:
text (str): Represents a text data type.
integer (str): Represents an integer data type. (Deprecated in Jan 2025: Use number instead)
numeric (str): Represents a numeric data type. (Deprecated in Jan 2025: Use number instead)
boolean (str): Represents a boolean data type.
list (str): Represents a list data type.
object (str): Represents an object data type.
string (str): Represents a string data type. (Deprecated in Jan 2025: Use text instead)
number (str): Represents a number data type.
time (str): Represents a time data type.
date (str): Represents a date data type.
text[] (str): Represents an array of text data type. (Deprecated in Jan 2025)
jsonb (str): Represents a JSONB data type. (Deprecated in Jan 2025)
Note:
Because of upcoming changes, please use `list`, `object`, `text`, `date`, `time`, and `number` going forward.
text
, integer
, numeric
, boolean
, list
, object
, string
, number
, time
, date
, text[]
, jsonb
Type of transformation to be applied.
extraction
, classification
, generation
Description of the task to be performed
Required when column_type is object
or list
. Defines the structure of object or list operations. If column_type is list
, then operations should only be of length 1 since list
can only be of one type. If column_type is object
, then operations can be longer of length one (and optionally be nested.)
NOTE: only valid with classification tasks. Output values of the transformation operation.
The transform_name parameter is an optional parameter that provides a human-readable name or description for the transformation, which can be useful for identifying and referencing transformations. If provided, the transform_name parameter should be a string. If not provided, the value of transform_name will be None.