mirror of
https://github.com/microsoft/semantic-kernel.git
synced 2026-10-12 11:19:56 +00:00
8828b86fd88d24208ce93fa3625adeec5dcf992e
104
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
8828b86fd8 |
Python: Refactoring and fix bug. AuthorRole instead of string literals. (#6391)
### 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. --> There's an enum called `AuthorRole`. I replaced string literals with the enum values. PyCharm highlights this in some cases: Expected type 'AuthorRole', got 'str' instead I also fixed a bug in _function_invocation_filters_stream.py_ where the argument name was wrong. `author="assistant"` instead of `role="assistant"` ### Description <!-- 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: --> - [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 - [x] I didn't break anyone 😄 --------- Co-authored-by: Evan Mattson <[email protected]> Co-authored-by: Eduard van Valkenburg <[email protected]> |
||
|
Evan Mattson
|
eab0e67ba0 |
Python: Bump Python version to 1.0.4 for a release. (#6488)
### Motivation and Context Bump Python version to 1.0.4 for a release. <!-- 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 Bump Python version to 1.0.4 for a release. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
fb8edbef94 |
Python: updates to cicd and notebooks (#6485)
### 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. --> Small update to test coverage workflow, to retrigger based on workflow run. Small updates to samples notebooks, to use GLOBAL_LLM_SERVICE allowing control of where they run through env. ### Description <!-- 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: --> - [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 - [x] I didn't break anyone 😄 |
||
|
Evan Mattson
|
9e46e52c97 |
Python: Fix learn resource planner sample (#6478)
### Motivation and Context The learn resource planner sample was not always passing as the plan created was non-deterministic. <!-- 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 Update the planner sample to run properly by introducing the Function Calling Stepwise Planner. Also introduce a small Pydantic Settings class to remove the dependency on the dotenv library. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
bf42feda6d |
Python: Fix function calling concept example. (#6477)
### Motivation and Context A function calling plugin example is failing due to an incorrect chat completion base method. Additionally, if one specifies to enable function calling with auto invoke set to False, and they don't provide a kernel, then there is no error thrown. <!-- 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: - Fixes the concept example that shows three different ways to handle function calling. - Fixes #6453 - Adjusts the error checks for the kernel and arguments in the open_ai_chat_completion_base: manual function calling doesn't require arguments, so don't throw if they aren't provided; however, it does require a kernel, which is used to configure the tools for the settings, so this check has to be by itself. - Add a unit test to exercise slightly different behavior. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
fbb26b5cf6 |
Python: further improvements to checks and docs in dev_setup (#6445)
### 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. --> Added a section on documentation to the DEV_SETUP Added a check for the copyright row to pre-commit Closes #5629 ### Description <!-- 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: --> - [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 - [x] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
7ce352b9e3 |
Python: Pydantic settings config (#6392)
### 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 initial implementation of Pydantic Settings was not optimal yet, more optimized now. ### Description Added a KernelBaseSettings class in kernel_pydantic Rebased all settings off that Added single create method to KernelBaseSettings: - sets model_config.env_prefix to cls.end_prefix allowing us to set the env_prefix as a classvar on each subclass and it works - if env_file_path is set, set that in model_config - strip all None values out of inputted values, then instantiate This also allows us to pass the settings that are supplied to the settings class, for overriding env settings. <!-- 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: --> - [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 - [x] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
e03b3fa168 |
Python: Run notebooks as tests (#6430)
### 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. --> Run notebooks as tests, working for all gettings started notebooks. Also updated learn resources samples test, this can now easily be extended with other sample scripts. Closes: #4637 Partially closes: #4638 ### Description <!-- 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: --> - [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 - [x] I didn't break anyone 😄 |
||
|
Evan Mattson
|
246b84357f |
Python: Bump Python version to 1.0.3 for a release. (#6432)
### Motivation and Context Bump Python version to 1.0.3 for a release. <!-- 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 Bump Python version to 1.0.3 for a release. <!-- 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 😄 |
||
|
Eduard van ValkenburgandEvan Mattson
|
172e93113e |
Python: updated samples (#6411)
### 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. --> Updated samples for MS Learn, with tags. ### Description <!-- 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: --> - [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 - [x] I didn't break anyone 😄 --------- Co-authored-by: Evan Mattson <[email protected]> |
||
|
Eduard van Valkenburg
|
9e99933a27 |
Python: new pre-commit actions and pre-commit as GHA (#6376)
### 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. --> - Added static code checking to pre-commit (check-ast and nbqa-check-ast) - Added Bandit security checking to pre-commit - Added pre-commit step to python-lint workflow, if it works, can delete seperate mypy, ruff and black tests ### Description <!-- 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: --> - [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 - [x] I didn't break anyone 😄 |
||
|
Sin-Woo BangandEduard van Valkenburg
|
63f1f8bac9 |
Python: Fix typo (#6409)
### 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. --> Fix typo ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Fix typo ### 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 - [x] I didn't break anyone 😄 Co-authored-by: Eduard van Valkenburg <[email protected]> |
||
|
StefanandEvan Mattson
|
a9d7d5d90f |
Python: Refactoring. Use get_function and get_plugin. (#6382)
### 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. --> Refactoring some of the code following [this advice](https://github.com/microsoft/semantic-kernel/pull/6371#discussion_r1611138252) from the maintainers. ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Look up kernel functions and plugins with the `get_function` and `get_plugin` method. Removed the unused `DEFAULT_CHAT_SYSTEM_PROMPT` ### 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 - [x] I didn't break anyone 😄 --------- Co-authored-by: Evan Mattson <[email protected]> |
||
|
Evan Mattson
|
43b7d40d8b |
Python: Bump Python version to 1.0.2 for a release (#6380)
### Motivation and Context Bump Python version to 1.0.2 for a release <!-- 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 Bump Python version to 1.0.2 for a release <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
f304114060 |
Python: Bump Python version to 1.0.1 for a release. (#6368)
### Motivation and Context Bump Python version to 1.0.1 for a release. <!-- 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 Bump Python version to 1.0.1 for a release. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
d66fdcfe5c |
Python: Add cross language tests (#6318)
### Motivation and Context As we move towards v1 and beyond it's essential that we have a way to make sure we are staying in line with the other SK SDKs. Previous to this we didn't have a way to capture request bodies and payloads and make sure they confirm to the proper SK standards. <!-- 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 a number of integration tests that exercise various aspects of the SK SDK like prompts, prompt templates, functions, and the kernel. *TODO*: update the OpenAPI tests with a more JSON specific response that we can check against. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
6158c5b432 |
Python: Fix FC stepwise planner. (#6357)
### Motivation and Context The FC stepwise planner was breaking when trying to process the function call result because if a filter is not configured, then the context will be None. We need to only try to extract the FC result if the context is not none, otherwise it will already be present in the chat history. <!-- 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 Check that the FC result context is not None, if so, then extract the FC result, otherwise proceed as the FC result is in the chat history. Fixes #6350. - Removes some extranous logging from json schema addition. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
81cdde24fc |
Python: upgraded all files to 310 plus format and removed from future (#6353)
### 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. --> Now that we only support 310 and up, we could unify all files, to use the new style typing and annotations. ### Description <!-- 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: --> - [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 - [x] I didn't break anyone 😄 |
||
|
Evan Mattson
|
2b96abfb2f |
Python: Bump Python version to v1.0.0 (#6345)
### Motivation and Context Bump Python version to v1.0.0 <!-- 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 Bump Python version to v1.0.0 <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
517a0f8ed2 |
Python: Add json schema handling. Add experimental tag to OpenAPI and Memory Connectors. (#6335)
### Motivation and Context The Python code base could handle some primitive types for the schema for tool call objects and kernel parameter metadata. However, it couldn't properly handle the more complex JSON schemas for tool call objects. <!-- 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: - JSON schema handling for KernelParameterMetadata and tool call objects. - Updates to the tool call utils method to properly recurse on the KernelParameterMetadata's stucture. - Adds unit tests for this code. - Add experimental_class/experimental_functions to various parts of the code base like Memory Connectors and OpenAPI plugin. - Fixes #6310 - Fixes #6280 <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
49980638ed |
Python: Bump version to 1.0.0rc1. (#6321)
### Motivation and Context Python: Bump version to 1.0.0rc1. <!-- 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 Python: Bump version to 1.0.0rc1. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
a894aebaa9 |
Python: implement filters (#5681)
### 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. --> This pull request includes significant changes across multiple files, mainly related to the addition of hooks and the modification of function invocations in the `semantic_kernel` module. The changes also include the addition of a new sample and a YAML file, and modifications to the `__init__.py` files. Removals: * [`python/semantic_kernel/events`](diffhunk://#diff-ebda9504832b19ab83239a92c9a6d5f8c744deff9fef86071c13956ec92bb010L1-L11): Removed the previously used events. New Exceptions: * [`python/semantic_kernel/exceptions/kernel_exceptions.py`](diffhunk://#diff-450aaa5595a8b22cd6ee212eb79b7d6b0d4e9c1072063ef32018a3e7d3fdf21dR41-R48): Added new exception classes `OperationCancelledException` and `HookInvalidSignatureError`. [[1]](diffhunk://#diff-450aaa5595a8b22cd6ee212eb79b7d6b0d4e9c1072063ef32018a3e7d3fdf21dR41-R48) [[2]](diffhunk://#diff-450aaa5595a8b22cd6ee212eb79b7d6b0d4e9c1072063ef32018a3e7d3fdf21dR57-R58) Fixes: #3038 Fixes: #6276 ### 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 😄 |
||
|
Evan Mattson
|
33f278c477 |
Python: Bump python version to 0.9.9b1 for release. (#6299)
### Motivation and Context Bump python version to 0.9.9b1 for release. <!-- 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 Bump python version to 0.9.9b1 for release. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Eduard van ValkenburgandEvan Mattson
|
cc7f7d2f69 |
Python: renamed complete to get_ (#6288)
### 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. --> To get back in sync with dotnet, renamed: - complete to get_text_contents - complete_chat to get_chat_message_contents - complete_stream to get_streaming_text_contents - complete_chat_stream to get_streaming_chat_message_content ### Description <!-- 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: --> - [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 😄 Co-authored-by: Evan Mattson <[email protected]> |
||
|
Evan Mattson
|
46f5ea15a2 |
Python: Introduce Pydantic settings (#6193)
### Motivation and Context SK Python is tightly coupled to the use of a `.env` file to read all secrets, keys, endpoints, and more. This doesn't scale well for users who wish to be able to use environment variables with their SK Applications. By introducing Pydantic Settings, it is possible to use both environment variables as well as have a fall-back to a `.env` file (via a `env_file_path` parameter), if desired. By introducing Pydantic Settings, we are removing the requirement to have to create Text/Embedding/Chat completion objects with an `api_key` or other previously required information (in the case of AzureChatCompletion that means an `endpoint`, an `api_key`, a `deployment_name`, and an `api_version`). When the AI connector is created, the Pydantic settings are loaded either via env vars or the fall-back `.env` file, and that means the user can create a chat completion object like: ```python chat_completion = OpenAIChatCompletion(service_id="test") ``` or, to optionally override the `ai_model_id` env var: ```python chat_completion = OpenAIChatCompletion(service_id="test", ai_model_id="gpt-4-1106") ``` Note: we have left the ability to specific an `api_key`/`org_id` for `OpenAIChatCompletion` or a `deployment_name`, `endpoint`, `base_url`, and `api_version` for `AzureChatCompletion` as before, but if your settings are configured to use env vars/.env file then there is no need to pass this information. <!-- 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 The PR introduces the use of Pydantic settings and removes the use of the python-dotenv library. - Closes #1779 - Updates notebooks, samples, code and tests to remove the explicit config of api_key or other previous .env files values. - Adds new unit test config using monkeypatch to simulate env variables for testing - All unit and integration tests passing <!-- 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: --> - [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 😄 |
||
|
Evan Mattson
|
142aef82b1 |
Python: OpenAPI plugin enhance (#6279)
### Motivation and Context Python's OpenAPI manager `run_openapi_operation` was hard-coded to use certain parameters that would ultimately be built up to make an API request. This didn't allow the model to know which parameters were actually defined as required in the OpenAPI spec and would cause errors during function calling. <!-- 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 does a quite major overhaul on the openapi manager, with the caveat that the code is going to be refactored / cleaned up in a next iteration (we're pressed for time right now). In the `_create_function_from_operation` method, the `rest_operation_params` are now built up from the operation which means we included the required parameters and will have them during function calling. This allows us to properly build up the url, headers, request body and paths to make the API call. - The concept samples were updated and are functioning with this latest code. - function calling was tested with the AzureKeyVault OpenAPI example and the model was able to automatically create a secret in a test key vault. - Old unit tests were removed. Note: in the next iteration new unit tests for all of the new functionality will be added. - In the next iteration, the entire `openapi_manager.py` file will be broken apart to separate files for classes/moels to clean it up. - Closes #6261 <!-- 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: --> - [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 😄 |
||
|
|
ecbc15b586 |
Python: fix class type (#6183)
### Motivation and Context It should be "ChatMessageContent" type instead of "FunctionCallContent" type. ### Description <!-- 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 😄 --------- Co-authored-by: Yan Zhang <[email protected]> Co-authored-by: Evan Mattson <[email protected]> Co-authored-by: Eduard van Valkenburg <[email protected]> |
||
|
Evan Mattson
|
1692207639 |
Python: allow openapi runner to use a custom client (#6226)
### Motivation and Context A custom client was used to get the openapi spec but it wasn't passed down into the openapi runner. <!-- 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 Pass the custom client into the open api runner if desired. Fix param parsing and samples. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
7b4aba4797 |
Python: Bump Python version to 0.9.8b1 for a release. (#6178)
### Motivation and Context Bump Python version to 0.9.8b1 for a release. <!-- 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 Bump Python version to 0.9.8b1 for a release. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
7e4faa3f72 |
Python: Add ACA Python Sessions (Code Interpreter) Core Plugin, samples, and tests (#6158)
### Motivation and Context Adding a new core plugin to Semantic Kernel Python that leverages the Azure Container Apps Python Sessions Container. This container allows one, with the proper resource, to run Python in a safe, managed environment. <!-- 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 Python Sessions (code interpreter) plugin to execute code, upload a file to the container, list files, and download files. - It includes a README.md with the steps to set up the ACA resource. - New samples to show use as a plugin and auto function calling - Unit tests <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Jordan Bean
|
e2f9deb975 |
Python: Fixes to Python getting_started notebooks (#6147)
### 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? - lots of changes in paths, namespaces, functions, etc have broken the getting_started samples 3. What problem does it solve? - fixes the getting_started notebooks 5. What scenario does it contribute to? - educating teams on use of Python Semantic Kernel SDK 7. If it fixes an open issue, please link to the issue here. --> ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Fixes to get all the Python getting_started notebooks to run with the latest version of the SDK ### 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 - [ x] I didn't break anyone 😄 |
||
|
|
96912812db |
Python: update ToolCallBehavior and rename to FunctionCallBehavior to match dotnet and extended capabilities (#5919)
### 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. --> Updated ToolCallBehavior to match the approach in dotnet Closes #5727 Closes #5447 Closes #5414 ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Extends ToolCallBehavior class with fields: - enable_kernel_functions - max_use_attempts - allow_any_request_kernel_function Added subclasses of TCB: - KernelFunctions, the configure_options set tools to all functions in the kernel and tool_choice to auto - EnabledFunctions, created with a filter dict, sets tool_choice to auto and tools to the filtered list - RequiredFunction, created with a function fully qualified name (plugin-function), sets tool_choice to that name and adds the definition of just that tool to tools. Methods: - configure_options(kernel, exection_settings) - This sets the execution settings depending on the field in toolcallbehavior - Does nothing in the default ToolCallBehavior class, so there you have to manually set tools and tool_choice ClassMethods: - AutoInvokeKernelFunctions, returns KernelFunctions class with max_auto_invoke_attempts set to 5 (default) - EnabelKernelFunctions, return KernelFunctions but with max_auto_invoke_attempts set to 0, disabling auto invoke, but it might return toolcalls from the model - EnableFunctions, takes the filter and a auto_invoke params and returns a EnabledFunctions class, if auto_invoke == True then it will auto invoke, otherwise it wont. - RequiredFunctions, returns RequiredFunction class with either max_invoke_attempts 0 or 1 depending on auto_invoke param Changed OpenAIChatPromptExecutionSettings to have a field called tool_call_behavior instead of max_invoke_attempts and auto_invoke_tool_calls fields. Some changes in openai_chat_completion_base to handle this. ### 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 😄 --------- Co-authored-by: Evan Mattson <[email protected]> Co-authored-by: Evan Mattson <[email protected]> |
||
|
Evan Mattson
|
db46d347f8 |
Python: Retire planners that are not supported in dotnet. (#6141)
### Motivation and Context In dotnet, there are no action, basic or stepwise planners. Since Python has the FunctionCallingStepwisePlanner, we will retire the legacy stepwise planner. We're leaving the Sequential planner for the meantime as it provides the developer with a way to show the plan steps. <!-- 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 The PR: - Removes the action, basic, and stepwise planners, along with their unit/integration tests. Closes #5585 - Removes one action planner kernel syntax example. - Updates the 05-planners Jupyter notebook to showcase the Sequential Planner along with the FunctionCallingStepwisePlanner - Fixes some sample paths that use the `prompt_template_samples` folder in the root of the repo. <!-- 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: --> - [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 😄 |
||
|
Evan Mattson
|
6ce7e1ef5e |
Python: Bump py version for release (#6123)
### Motivation and Context Bump py version for release from 0.9.6b1 -> 0.9.7b1. <!-- 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 Bump py version for release from 0.9.6b1 -> 0.9.7b1. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
ce2d9c9b5f |
Python: Add PF learn path resources (#6122)
### Motivation and Context Add files that weren't staged to PF resources. <!-- 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 Add files that weren't staged to PF resources. <!-- 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 😄 |
||
|
Evan Mattson
|
09508dc8ba |
Python: Restructure samples into new folders to make things more clear. (#6116)
### Motivation and Context All previous samples were either in kernel syntax or a separate notebooks folder. The goal is to make the samples easier to understand and have a better structure. <!-- 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 The PR restructures the kernel syntax examples into new folders: concepts (with subfolders for previous syntax examples), demos, getting_started, and learn_resources. - Closes #6119 - Adds a new concept/function example for understanding kernel arguments. - Updates the bookings plugin <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
9a44506220 |
Python: add new samples and fix streaming tool call FunctionCallContent formation (#5877)
### Motivation and Context We're working towards creating a core set of syntax examples (there are four total). The core examples will be available in all 3 SK languages. <!-- 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 two (of the four) new kernel syntax examples, which will align with the new kernel examples coming soon for both dotnet and Java. #5784 - Introduce a custom weather plugin that in conjunction with the core TimePlugin, make use of auto function calling. - Introduce a kernel syntax example that shows how to integrate with the Microsoft Graph API to create a "restaurant booking." Note: this doesn't actually place a real reservation, but shows how to interact with msgraph. - Also fixes an issue where the streaming tool call argument formation was broken. Closes #6106 <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
deb813bdca |
Python: Remove references to text-davinci-003 text models as it causes tests to hang. (#6089)
### Motivation and Context Python PR merges were failing due to integration tests. Local integration tests were hanging on running Azure text completions. It appears text-davinci-003 was deprecated, and needed to be replaced by gpt-35-turbo-instruct. <!-- 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 Remove references to text-davinci-003 text models as it causes tests to hang.to hang. Updated to gpt-35-turbo-instruct, which passes. Add EastUS AOAI deployment name var. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Chris
|
ac6e03ba98 |
Java: Python: Docs: Fix broken link (#6092)
### 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. --> `https://openai.com/product` is failing `Check .md links` workflow. ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Revise links. https://github.com/microsoft/semantic-kernel/actions/workflows/markdown-link-check.yml Whitespace edits peformed by VS Code ### 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 - [X] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
65e94b3454 |
Python: updated Chat Message Content with Function Call and Result Content (#5946)
### 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. --> Introducing FunctionCallContent and FunctionResultContent Changed ChatRole to AuthorRole Adapting ChatMessageContent to have 1 or more other contents within (currently TextContent or one of the above) Closes #5890 ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Changed OpenAI classes, to remove OpenAIChatMessageContent and AzureChatMessageContent Changed OpenAI classes to create and parse FunctionCallContent and other new things. ### 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 😄 |
||
|
|
8b3203af52 |
Python: Refactor environment variable naming for clarity and consistency (#5686)
### Summary of Changes - Updated environment variable names to use single underscores for better readability and to avoid potential confusion. - Modified `service_configurator.py` to align with the updated environment variable naming convention. - Updated `.env.example` to reflect the new environment variable names, ensuring consistency across the project. - Added error handling and improved error messages in `service_configurator.py` for better debugging and maintainability. ### Motivation and Context The motivation for these changes is to address a bug where the `service_configurator.py` script is unable to read the `GLOBAL_LLM_SERVICE` environment variable due to inconsistent naming conventions. Additionally, the Azure service configuration variables were not being utilized, which could potentially lead to misconfigurations in certain deployment scenarios. - **Why is this change required?** To fix existing bugs related to environment variable handling and improve code maintainability and readability. - **What problem does it solve?** Ensures reliable loading of environment variables and correct configuration of AI services, thereby preventing runtime errors. - **What scenario does it contribute to?** Enhances the stability and reliability of the AI service configuration process within the semantic-kernel project. ### Description This PR addresses the issue where the environment variable `GLOBAL_LLM_SERVICE` was not consistently read due to a mismatch in the expected naming convention. The problem was identified in the `service_configurator.py` script where the variable was referenced with two underscores instead of one. Additionally, Azure service deployment names were not being used, leading to potential misconfigurations. - Modified the naming convention from double to single underscores for all environment variables in `service_configurator.py` and `.env.example`. - Ensured that Azure service deployment names are correctly utilized in the service configuration logic. - Improved error handling in the script to provide clearer and more actionable feedback. For more context, here's a link to the buggy code: [Link to the code](https://github.com/microsoft/semantic-kernel/blob/main/python/samples/documentation_examples/service_configurator.py#L27), [Link to the code](https://github.com/microsoft/semantic-kernel/blob/main/python/samples/documentation_examples/.env.example#L1)   ### Contribution Checklist - [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. - [x] I didn't break anyone 😄 --------- Co-authored-by: Evan Mattson <[email protected]> Co-authored-by: Chris <[email protected]> |
||
|
Eduard van Valkenburg
|
66a3b5bfea |
Python: init cleanup (#5872)
### 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. --> When the root init has to load a lot of stuff, loading the whole thing becomes slower, only one concept there Kernel, all other things must now be loaded from a sub package. The following is not the guidance: - imports within SK use the full path - init files are created as much as possible on the root+1 level (like semantic_kernel.functions) with the pieces that common developers need, except in connectors and utils, there a developer needs to go deeper - within the connectors folder this is further detailed first to ai, memory, search_engine, within ai it is further spread into the different connectors, for instance everything for openai and azure openai can be imported using `from semantic_kernel.connectors.ai.open_ai import ...`, the same within memory - imports in samples use the abbreviated path as much as possible. ### Description <!-- 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: --> - [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 😄 |
||
|
Evan Mattson
|
65275737d6 |
Python: Bump project version for release. Fix missing imports in notebooks. (#5871)
### Motivation and Context Bumping the pyproject.toml version and related notebook version references for a release. Some of the Jupyter notebooks were missing the imports to be able to run properly. <!-- 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 The PR - bumps the pyproject.toml version and related notebook version references for a release. - Fixes the missing notebook imports. - Fixes a service_id/request settings bug in one kernel syntax example. Closes #5148 <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
6751f9d819 |
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 😄
|
||
|
Evan Mattson
|
ed1770c40b |
Python: Allow args to pass to func calling stepwise planner (#5830)
### Motivation and Context A recent feature was added to dotnet to allow for a chat_history object to be passed into invoke. This only allows the user to affect the `chatHistoryForSteps`, but doesn't account for generating a plan with provided context (via the chat history). <!-- 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 allows the user to pass in optional kernel arguments or kwargs (that get turned into kernel arguments). If the user then overrides the prompt template/step prompt.txt, they can utilize any new arguments that are supplied. - Closes #5824 <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
3490e2afac |
Python: Add missing await to openapi client (#5759)
### Motivation and Context Add missing await to openapi client <!-- 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 Add missing await to openapi client <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
|
ca2ad19130 |
Python: Update to AOAI OYD 2024-02-15-preview API version (#5684)
### 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. --> ### Description * Updated models to support the new preview API version 2024-02-15-preview, with some backward compatibility with previous API shape through the use of aliases * Updated samples, unit tests and integration tests * Added experimental settings management using pydantic-settings -- not strictly required here, but I thought it was useful for testing to be able to set all values through the .env file, and validation comes for free using Pydantic. Looking forward to feedback on this. :) ### 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 😄 --------- Co-authored-by: Abby Hartman <[email protected]> Co-authored-by: Evan Mattson <[email protected]> |
||
|
Evan Mattson
|
e563920b70 |
Python: Honor the function calling options if configured. (#5701)
### Motivation and Context In the function calling stepwise planner, some settings like max_tokens (based on max_completion_tokens from the planner settings) and the max auto invoke attempts were not used. <!-- 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 fixes the issue where the prompt execution settings for chat completion wasn't using the function calling stepwise planner options, if configured. Closes #5661 <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Evan Mattson
|
c4c7464f07 |
Python: Introduce operations to handle OpenAI plugins, improve OpenAPI plugins, and allow for auth (#5695)
### Motivation and Context Python had the ability to handle operations for OpenAPI plugins, but at a basic level. It did not have the ability to handle OpenAI plugins, nor did it allow the user to configure an authentication callback. This PR brings in that functionality. <!-- 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: - Allows a user to handle OpenAI plugins with/without auth. Closes #5355 - Improves the functionality around handling OpenAPI specs. - Introduces an auth callback mechanism to allow for REST API calls to use auth - Introduces OpenAI/OpenAPI function execution settings. - Provides two new kernel examples that show how to handle a simple OpenAI plugin (Klarna) as well as a more complex plugin (Azure Key Vault) that requires auth. - Updates unit tests. <!-- 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: --> - [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 - [X] I didn't break anyone 😄 |
||
|
Eduard van Valkenburg
|
14a0881989 |
Python: mypy clears kernel.py (#5689)
### 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. --> Fixed all mypy errors for kernel.py In preparation of extending that to all files in semantic_kernel Also got the pre-commit hook working on a commit, with mypy checks fixes #5630 ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Moved pre-commit-config to base folder, can now be extended to have specific hooks for other languages fixed things in kernel.py to satisfy mypy used assert for some things, so that they can be skipped when running in -o mode. ### 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 - [x] I didn't break anyone 😄 |