KernelFunctionExtension Class

Kernel function extension.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Constructor

KernelFunctionExtension(*, plugins: dict[str, KernelPlugin] = None)

Keyword-Only Parameters

Name	Description
plugins Required

Methods

add_function	Adds a function to the specified plugin.
add_functions	Adds a list of functions to the specified plugin.
add_plugin	Adds a plugin to the kernel's collection of plugins. If a plugin is provided, it uses that instance instead of creating a new KernelPlugin. See KernelPlugin.from_directory for more details on how the directory is parsed.
add_plugin_from_openapi	Add a plugin from the OpenAPI manifest.
add_plugins	Adds a list of plugins to the kernel's collection of plugins.
get_full_list_of_function_metadata	Get a list of all function metadata in the plugins.
get_function	Get a function by plugin_name and function_name.
get_function_from_fully_qualified_function_name	Get a function by its fully qualified name (<plugin_name>-<function_name>).
get_list_of_function_metadata	Get a list of all function metadata in the plugin collection.
get_list_of_function_metadata_bool	Get a list of the function metadata in the plugin collection.
get_list_of_function_metadata_filters	Get a list of Kernel Function Metadata based on filters.
get_plugin	Get a plugin by name.
rewrite_plugins	Rewrite plugins to a dictionary.

add_function

Adds a function to the specified plugin.

add_function(plugin_name: str, function: KERNEL_FUNCTION_TYPE | None = None, function_name: str | None = None, description: str | None = None, prompt: str | None = None, prompt_template_config: PromptTemplateConfig | None = None, prompt_execution_settings: PromptExecutionSettings | Sequence[PromptExecutionSettings] | Mapping[str, PromptExecutionSettings] | None = None, template_format: Literal['semantic-kernel', 'handlebars', 'jinja2'] = 'semantic-kernel', prompt_template: PromptTemplateBase | None = None, return_plugin: bool = False, **kwargs: Any) -> KernelFunction | KernelPlugin

Parameters

Name	Description
plugin_name Required	str The name of the plugin to add the function to
function	<xref:KernelFunction \| Callable>[<xref:...>,<xref: Any>] The function to add Default value: None
function_name	str The name of the function Default value: None
plugin_name Required	The name of the plugin
description	<xref:<xref:semantic_kernel.functions.kernel_function_extension.str \| None>> The description of the function Default value: None
prompt	<xref:<xref:semantic_kernel.functions.kernel_function_extension.str \| None>> The prompt template. Default value: None
prompt_template_config	<xref:<xref:semantic_kernel.functions.kernel_function_extension.PromptTemplateConfig \| None>> The prompt template configuration Default value: None
prompt_execution_settings	The execution settings, will be parsed into a dict. Default value: None
template_format	<xref:<xref:semantic_kernel.functions.kernel_function_extension.str \| None>> The format of the prompt template Default value: semantic-kernel
prompt_template	<xref:<xref:semantic_kernel.functions.kernel_function_extension.PromptTemplateBase \| None>> The prompt template Default value: None
return_plugin	bool If True, the plugin is returned instead of the function Default value: False
kwargs Required	Any Additional arguments

Returns

Type	Description
KernelFunction \| KernelPlugin	The function that was added, or the plugin if return_plugin is True

add_functions

Adds a list of functions to the specified plugin.

add_functions(plugin_name: str, functions: list[KERNEL_FUNCTION_TYPE] | dict[str, KERNEL_FUNCTION_TYPE]) -> KernelPlugin

Parameters

Name	Description
plugin_name Required	str The name of the plugin to add the functions to
functions Required	list[<xref:KernelFunction>]<xref: \| dict>[str,<xref: KernelFunction>] The functions to add

Returns

Type	Description
KernelPlugin	The plugin that the functions were added to.

add_plugin

Adds a plugin to the kernel's collection of plugins.

If a plugin is provided, it uses that instance instead of creating a new KernelPlugin. See KernelPlugin.from_directory for more details on how the directory is parsed.

add_plugin(plugin: KernelPlugin | object | dict[str, Any] | None = None, plugin_name: str | None = None, parent_directory: str | None = None, description: str | None = None, class_init_arguments: dict[str, dict[str, Any]] | None = None) -> KernelPlugin

Parameters

Name	Description
plugin	The plugin to add. This can be a KernelPlugin, in which case it is added straightaway and other parameters are ignored, a custom class that contains methods with the kernel_function decorator or a dictionary of functions with the kernel_function decorator for one or several methods. Default value: None
plugin_name	The name of the plugin, used if the plugin is not a KernelPlugin, if the plugin is None and the parent_directory is set, KernelPlugin.from_directory is called with those parameters, see KernelPlugin.from_directory for details. Default value: None
parent_directory	The parent directory path where the plugin directory resides Default value: None
description	The description of the plugin, used if the plugin is not a KernelPlugin. Default value: None
class_init_arguments	The class initialization arguments Default value: None

Returns

Type	Description
KernelPlugin	The plugin that was added.

Exceptions

Type	Description
ValidationError	If a KernelPlugin needs to be created, but it is not valid.

add_plugin_from_openapi

Add a plugin from the OpenAPI manifest.

add_plugin_from_openapi(plugin_name: str, openapi_document_path: str | None = None, openapi_parsed_spec: dict[str, Any] | None = None, execution_settings: OpenAPIFunctionExecutionParameters | None = None, description: str | None = None) -> KernelPlugin

Parameters

Name	Description
plugin_name Required	The name of the plugin
openapi_document_path	The path to the OpenAPI document Default value: None
openapi_parsed_spec	The parsed OpenAPI spec Default value: None
execution_settings	The execution parameters Default value: None
description	The description of the plugin Default value: None

Returns

Type	Description
KernelPlugin	The imported plugin

Exceptions

Type	Description
PluginInitializationError	if the plugin URL or plugin JSON/YAML is not provided

add_plugins

Adds a list of plugins to the kernel's collection of plugins.

add_plugins(plugins: list[KernelPlugin] | dict[str, KernelPlugin | object]) -> None

Parameters

Name	Description
plugins Required	list[<xref:KernelPlugin>]<xref: \| dict>[str,<xref: KernelPlugin>] The plugins to add to the kernel

get_full_list_of_function_metadata

Get a list of all function metadata in the plugins.

get_full_list_of_function_metadata() -> list[KernelFunctionMetadata]

get_function

Get a function by plugin_name and function_name.

get_function(plugin_name: str | None, function_name: str) -> KernelFunction

Parameters

Name	Description
plugin_name Required	<xref:<xref:semantic_kernel.functions.kernel_function_extension.str \| None>> The name of the plugin
function_name Required	str The name of the function

Returns

Type	Description
KernelFunction	The function

Exceptions

Type	Description
KernelPluginNotFoundError	If the plugin is not found
KernelFunctionNotFoundError	If the function is not found

get_function_from_fully_qualified_function_name

Get a function by its fully qualified name (<plugin_name>-<function_name>).

get_function_from_fully_qualified_function_name(fully_qualified_function_name: str) -> KernelFunction

Parameters

Name	Description
fully_qualified_function_name Required	str The fully qualified name of the function, if there is no '-' in the name, it is assumed that it is only a function_name.

Returns

Type	Description
KernelFunction	The function

Exceptions

Type	Description
KernelPluginNotFoundError	If the plugin is not found
KernelFunctionNotFoundError	If the function is not found

get_list_of_function_metadata

Get a list of all function metadata in the plugin collection.

get_list_of_function_metadata(*args: Any, **kwargs: Any) -> list[KernelFunctionMetadata]

get_list_of_function_metadata_bool

Get a list of the function metadata in the plugin collection.

get_list_of_function_metadata_bool(include_prompt: bool = True, include_native: bool = True) -> list[KernelFunctionMetadata]

Parameters

Name	Description
include_prompt	bool Whether to include semantic functions in the list. Default value: True
include_native	bool Whether to include native functions in the list. Default value: True

Returns

Type	Description
	A list of KernelFunctionMetadata objects in the collection.

get_list_of_function_metadata_filters

Get a list of Kernel Function Metadata based on filters.

get_list_of_function_metadata_filters(filters: dict[Literal['excluded_plugins', 'included_plugins', 'excluded_functions', 'included_functions'], list[str]]) -> list[KernelFunctionMetadata]

Parameters

Name	Description
filters Required	dict[str,list[str]] The filters to apply to the function list. The keys are: included_plugins: A list of plugin names to include. excluded_plugins: A list of plugin names to exclude. included_functions: A list of function names to include. excluded_functions: A list of function names to exclude. The included and excluded parameters are mutually exclusive. The function names are checked against the fully qualified name of a function.

Name

Description

filters

Required

dict[str,list[str]]

The filters to apply to the function list. The keys are:

included_plugins: A list of plugin names to include.
excluded_plugins: A list of plugin names to exclude.
included_functions: A list of function names to include.
excluded_functions: A list of function names to exclude.

The included and excluded parameters are mutually exclusive. The function names are checked against the fully qualified name of a function.

Returns

Type	Description
list[KernelFunctionMetadata]	The list of Kernel Function Metadata that match the filters.

get_plugin

Get a plugin by name.

get_plugin(plugin_name: str) -> KernelPlugin

Parameters

Name	Description
plugin_name Required	str The name of the plugin

Returns

Type	Description
KernelPlugin	The plugin

Exceptions

Type	Description
KernelPluginNotFoundError	If the plugin is not found

rewrite_plugins

Rewrite plugins to a dictionary.

rewrite_plugins(plugins: KernelPlugin | list[KernelPlugin] | dict[str, KernelPlugin] | None = None) -> dict[str, KernelPlugin]

Parameters

Name	Description
plugins	Default value: None

Attributes

plugins

plugins: dict[str, KernelPlugin]

Share via

KernelFunctionExtension Class

Constructor

Keyword-Only Parameters

Methods

add_function

Parameters

Returns

add_functions

Parameters

Returns

add_plugin

Parameters

Returns

Exceptions

add_plugin_from_openapi

Parameters

Returns

Exceptions

add_plugins

Parameters

get_full_list_of_function_metadata

get_function

Parameters

Returns

Exceptions

get_function_from_fully_qualified_function_name

Parameters

Returns

Exceptions

get_list_of_function_metadata

get_list_of_function_metadata_bool

Parameters

Returns

get_list_of_function_metadata_filters

Parameters

Returns

get_plugin

Parameters

Returns

Exceptions

rewrite_plugins

Parameters

Attributes

plugins