Python: Introduce the function calling stepwise planner (#5350)
### Motivation and Context
To further align with the SK dotnet SDK and its functionality, the
Python SDK needs a function calling stepwise planner. Now that we have
auto tool calling available, it makes sense to introduce this planner.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
This PR:
- Introduces the function calling stepwise planner, its planner options,
and planner result. Closes #4642
- Introduces a kernel example `function_calling_stepwise_planner.py` to
exercise the planner and show how it works.
- Adds unit tests and an integration test.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-03-12 11:52:12 -04:00
|
|
|
# Copyright (c) Microsoft. All rights reserved.
|
|
|
|
|
|
|
|
|
|
|
2024-05-21 18:33:08 +02:00
|
|
|
from collections.abc import Callable
|
Python: Introduce the function calling stepwise planner (#5350)
### Motivation and Context
To further align with the SK dotnet SDK and its functionality, the
Python SDK needs a function calling stepwise planner. Now that we have
auto tool calling available, it makes sense to introduce this planner.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
This PR:
- Introduces the function calling stepwise planner, its planner options,
and planner result. Closes #4642
- Introduces a kernel example `function_calling_stepwise_planner.py` to
exercise the planner and show how it works.
- Adds unit tests and an integration test.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-03-12 11:52:12 -04:00
|
|
|
|
|
|
|
|
import pytest
|
|
|
|
|
from pydantic import ValidationError
|
|
|
|
|
|
|
|
|
|
from semantic_kernel import Kernel
|
Python: Updated plugins (#5827)
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
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:
```python
@kernel_function(name='test')
def f(...):
etc
func = KernelFunctionFromMethod(method=f)
func2 = kernel.add_function('plugin', func)
assert func != func2
```
Also closes: #5855
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
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
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-04-15 15:51:59 +02:00
|
|
|
from semantic_kernel.exceptions.function_exceptions import FunctionInitializationError
|
Python: Introduce the function calling stepwise planner (#5350)
### Motivation and Context
To further align with the SK dotnet SDK and its functionality, the
Python SDK needs a function calling stepwise planner. Now that we have
auto tool calling available, it makes sense to introduce this planner.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
This PR:
- Introduces the function calling stepwise planner, its planner options,
and planner result. Closes #4642
- Introduces a kernel example `function_calling_stepwise_planner.py` to
exercise the planner and show how it works.
- Adds unit tests and an integration test.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-03-12 11:52:12 -04:00
|
|
|
from semantic_kernel.functions.kernel_arguments import KernelArguments
|
|
|
|
|
from semantic_kernel.functions.kernel_function import KernelFunction
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def test_register_valid_native_function(kernel: Kernel, decorated_native_function: Callable):
|
2024-05-24 07:02:18 +01:00
|
|
|
kernel.add_function(plugin_name="TestPlugin", function=decorated_native_function)
|
|
|
|
|
registered_func = kernel.get_function(plugin_name="TestPlugin", function_name="getLightStatus")
|
Python: Introduce the function calling stepwise planner (#5350)
### Motivation and Context
To further align with the SK dotnet SDK and its functionality, the
Python SDK needs a function calling stepwise planner. Now that we have
auto tool calling available, it makes sense to introduce this planner.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
This PR:
- Introduces the function calling stepwise planner, its planner options,
and planner result. Closes #4642
- Introduces a kernel example `function_calling_stepwise_planner.py` to
exercise the planner and show how it works.
- Adds unit tests and an integration test.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-03-12 11:52:12 -04:00
|
|
|
|
|
|
|
|
assert isinstance(registered_func, KernelFunction)
|
2024-05-24 07:02:18 +01:00
|
|
|
assert kernel.get_function(plugin_name="TestPlugin", function_name="getLightStatus") == registered_func
|
Python: Introduce the function calling stepwise planner (#5350)
### Motivation and Context
To further align with the SK dotnet SDK and its functionality, the
Python SDK needs a function calling stepwise planner. Now that we have
auto tool calling available, it makes sense to introduce this planner.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
This PR:
- Introduces the function calling stepwise planner, its planner options,
and planner result. Closes #4642
- Introduces a kernel example `function_calling_stepwise_planner.py` to
exercise the planner and show how it works.
- Adds unit tests and an integration test.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-03-12 11:52:12 -04:00
|
|
|
func_result = await registered_func.invoke(kernel, KernelArguments(arg1="testtest"))
|
|
|
|
|
assert str(func_result) == "test"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_register_undecorated_native_function(kernel: Kernel, not_decorated_native_function: Callable):
|
|
|
|
|
with pytest.raises(FunctionInitializationError):
|
Python: Updated plugins (#5827)
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
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:
```python
@kernel_function(name='test')
def f(...):
etc
func = KernelFunctionFromMethod(method=f)
func2 = kernel.add_function('plugin', func)
assert func != func2
```
Also closes: #5855
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
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
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-04-15 15:51:59 +02:00
|
|
|
kernel.add_function("TestPlugin", not_decorated_native_function)
|
Python: Introduce the function calling stepwise planner (#5350)
### Motivation and Context
To further align with the SK dotnet SDK and its functionality, the
Python SDK needs a function calling stepwise planner. Now that we have
auto tool calling available, it makes sense to introduce this planner.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
This PR:
- Introduces the function calling stepwise planner, its planner options,
and planner result. Closes #4642
- Introduces a kernel example `function_calling_stepwise_planner.py` to
exercise the planner and show how it works.
- Adds unit tests and an integration test.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-03-12 11:52:12 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_register_with_none_plugin_name(kernel: Kernel, decorated_native_function: Callable):
|
|
|
|
|
with pytest.raises(ValidationError):
|
Python: Updated plugins (#5827)
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
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:
```python
@kernel_function(name='test')
def f(...):
etc
func = KernelFunctionFromMethod(method=f)
func2 = kernel.add_function('plugin', func)
assert func != func2
```
Also closes: #5855
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
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
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone :smile:
2024-04-15 15:51:59 +02:00
|
|
|
kernel.add_function(function=decorated_native_function, plugin_name=None)
|
