Python: Updated plugins

[eavanvalkenburg]

Motivation and Context

The loading of plugins and functions into Kernel was not fully consistent and clear, this is now simplified.

Adding a plugin can now be done in two ways:

• multiple: kernel.add_plugins[plugin1, plugin2]
• single plugin: kernel.add_plugin(plugin)
  • if the plugin here is a class, with methods that have the kernel_function decorator then that is parsed into a plugin

Adding a function can now be done in three ways:

• multiple: kernel.add_functions([func1, func2] or kernel.add_function({'func1': func1})
• single: kernel.add_function('plugin_name', func1)
• from a prompt: kernel.add_function(function_name='func1', prompt='test prompt', ...)

In other words, all the different methods that were available have been simplified, these methods also return the created plugin (or updated plugin for the add_functions method. The add_function (singular) method has a parameter return_plugin to control whether you get the created or updated plugin, instead of the created function.

An important callout:

One big internal change that this introduces is that a function that gets added to a plugin (new or existing) is automatically copied, the metadata is deep-copied and the plugin_name in the metadata is updated, so this sequence is valid now:

@kernel_function(name='test')
def f(...):
   etc

func = KernelFunctionFromMethod(method=f)
func2 = kernel.add_function('plugin', func)
assert func != func2

Also closes: #5855

Description

Removed KernelPluginCollection
Updated KernelPlugin
added from_... method to load from different sources
Updated KernelFunctionFromPrompt
added from_yaml and from_directory methods.

Added and updated tests to 99% coverage of KernelPlugin and KernelFunctionFromPrompt

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
• All unit tests pass, and I have added new tests where possible
• I didn't break anyone 😄

[moonbox3]

This is really exciting work. It's going to make working with functions/plugins so much better! Thank you for doing the work.

[markwallace-microsoft]

Python 3.8 Test Coverage Report •

File	Stmts	Miss	Cover	Missing
semantic_kernel
kernel.py	261	28	89%	122, 124, 182–185, 187–191, 193–196, 203, 210–219, 254–257, 267–272, 277, 281–284, 466–467
semantic_kernel/connectors/ai/open_ai
utils.py	46	21	54%	27–28, 51–55, 62–63, 104, 142, 144, 146, 148, 150, 155–162
semantic_kernel/connectors/openai_plugin
openai_utils.py	18	10	44%	20–31
semantic_kernel/connectors/openapi_plugin
openapi_manager.py	141	15	89%	13, 61–74, 104, 145, 150, 280, 348–361
semantic_kernel/core_plugins
conversation_summary_plugin.py	20	9	55%	6, 47–48, 75–84
semantic_kernel/functions
kernel_function.py	72	2	97%	141, 160
kernel_function_from_prompt.py	162	4	98%	170, 198, 299, 369
semantic_kernel/planners
basic_planner.py	64	48	25%	19–21, 24, 135, 143–167, 179–202, 211–241
planner_extensions.py	32	32	0%	3–70
semantic_kernel/planners/action_planner
action_planner.py	116	22	81%	11, 105, 114, 127, 131–132, 142–149, 162, 187, 245–246, 263, 280–291
semantic_kernel/planners/function_calling_stepwise_planner
function_calling_stepwise_planner.py	102	38	63%	122–185, 219–224
semantic_kernel/planners/sequential_planner
sequential_planner.py	65	6	91%	71, 75, 106, 122, 131–132
sequential_planner_extensions.py	51	9	82%	28–29, 50, 101–115
sequential_planner_parser.py	77	12	84%	63–72, 92, 115–118
semantic_kernel/planners/stepwise_planner
stepwise_planner.py	224	139	38%	12, 109–127, 136–206, 227–230, 238–249, 252, 260–275, 278–314, 317–345, 348–353, 356–368, 371–374, 388–400
semantic_kernel/prompt_template
jinja2_prompt_template.py	43	3	93%	61–63
kernel_prompt_template.py	85	3	96%	119–121
semantic_kernel/template_engine/blocks
code_block.py	70	1	99%	130
TOTAL	5545	1010	82%

Python 3.8 Unit Test Overview

Tests	Skipped	Failures	Errors	Time
1211	11 💤	0 ❌	0 🔥	22.188s ⏱️

[moonbox3]

Awesome

[juliomenendez]

Clean! LGTM