Share via

PromptExecutionSettings Class

  • Reference

Base class for prompt execution settings.

Can be used by itself or as a base class for other prompt execution settings. The methods are used to create specific prompt execution settings objects based on the keys in the extension_data field, this way you can create a generic PromptExecutionSettings object in your application, which gets mapped into the keys of the prompt execution settings that each services returns by using the service.get_prompt_execution_settings() method.

Initialize the prompt execution settings.

Inheritance
KernelBaseModel
PromptExecutionSettings

Constructor

PromptExecutionSettings(service_id: str | None = None, *, extension_data: dict[str, Any] = None, function_choice_behavior: FunctionChoiceBehavior | None = None)

Parameters

Name Description
service_id
str

The service ID to use for the request.

Default value: None
kwargs
Required
Any

Additional keyword arguments, these are attempted to parse into the keys of the specific prompt execution settings.

Keyword-Only Parameters

Name Description
extension_data
Required
function_choice_behavior
Required

Methods

from_prompt_execution_settings

Create a prompt execution settings from another prompt execution settings.
pack_extension_data

Update the extension data from the prompt execution settings.
parse_function_choice_behavior

Parse the function choice behavior data.
prepare_settings_dict

Prepares the settings as a dictionary for sending to the AI service.
unpack_extension_data

Update the prompt execution settings from extension data.

Does not overwrite existing values with None.
update_from_prompt_execution_settings

Update the keys from another prompt execution settings object.

from_prompt_execution_settings

Create a prompt execution settings from another prompt execution settings.

from_prompt_execution_settings()

Parameters

Name Description
config
Required

pack_extension_data

Update the extension data from the prompt execution settings.

pack_extension_data() -> None

parse_function_choice_behavior

Parse the function choice behavior data.

parse_function_choice_behavior(data: dict[str, Any]) -> dict[str, Any]

Parameters

Name Description
data
Required

prepare_settings_dict

Prepares the settings as a dictionary for sending to the AI service.

prepare_settings_dict()

unpack_extension_data

Update the prompt execution settings from extension data.

Does not overwrite existing values with None.

unpack_extension_data() -> None

update_from_prompt_execution_settings

Update the keys from another prompt execution settings object.

update_from_prompt_execution_settings()

Parameters

Name Description
config
Required

Attributes

keys

Get the keys of the prompt execution settings.

model_computed_fields

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

model_computed_fields: ClassVar[Dict[str, ComputedFieldInfo]] = {}

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True, 'populate_by_name': True, 'validate_assignment': True}

model_fields

Metadata about the fields defined on the model, mapping of field names to [FieldInfo][pydantic.fields.FieldInfo] objects.

This replaces Model.fields from Pydantic V1.

model_fields: ClassVar[Dict[str, FieldInfo]] = {'extension_data': FieldInfo(annotation=dict[str, Any], required=False, default_factory=dict), 'function_choice_behavior': FieldInfo(annotation=Union[FunctionChoiceBehavior, NoneType], required=False, default=None, exclude=True), 'service_id': FieldInfo(annotation=Union[str, NoneType], required=False, default=None, metadata=[MinLen(min_length=1)])}

service_id

The service ID to use for the request.

service_id: str | None

extension_data

Any additional data to send with the request.

extension_data: dict[str, Any]

function_choice_behavior

The function choice behavior settings.

function_choice_behavior: FunctionChoiceBehavior | None