mirror of
https://github.com/microsoft/semantic-kernel.git
synced 2026-10-12 11:19:56 +00:00
main
10
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Dmytro Struk
|
2a47ba9b7d |
Python: Removed usage of DefaultAzureCredential (#12964)
### 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 usage of `DefaultAzureCredential` by default is unsafe and raises security issues. Instead, users should provide their own credential types such as `AzureCliCredential`, `ManagedIdentityCredential` and so on. More information here: https://learn.microsoft.com/en-us/python/api/azure-identity/azure.identity.aio?view=azure-python In this PR: 1. Removed the usage of `DefaultAzureCredential` from authentication logic. 2. Replaced `DefaultAzureCredential` with `AzureCliCredential` in all examples. **Note**: this is breaking change for Azure users, who relies on `DefaultAzureCredential`. Users will need to update the code and pass the credential type of their choice by using `credential` parameter when initializing one of the Azure clients. Before: ```python chat_completion = AzureChatCompletion() ``` After: ```python chat_completion = AzureChatCompletion(credential=AzureCliCredential()) ``` ### 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 😄 |
||
|
Eduard van Valkenburg
|
003cc4c010 |
Python: Feature python vector stores preb (#12271)
### 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. --> Overhaul of the VectorStores to get it matching with dotnet and the latest development there. Closes: - #11938 - #11598 - #11597 - #11517 - #10561 - #10391 - #9911 - #9892 - #10867 ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Many changes, some highlights: - Moved from different vector fields types, to a single with a enum first VectorStoreField() - Renamed several items - Made embeddinggenerrator a part of the vector field spec and do automatic vectorization from there or from the same param on a collection - Adds hybrid search using the same setup - Removed the intermediate TextSeachVectorSearch object need, by allowing `create_search_function` directly on a collection Will write out full changes in a migration guide in the docs. ### 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 😄 |
||
|
Eduard van Valkenburg
|
12851923bc |
Python: allow settings to be created directly (#11468)
### 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. --> I've always hated having to add the .create to a settings object, this removes that, you can just use the regular init, added benefit is that it has the proper fields in the docstrings for each implemented settings object! ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Adds a __new__ method to the base settings class, which takes the prefix and if supplied the env_file and encoding, then calls model_rebuild and then the init. ### 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
|
8381e50e8b |
Python: Introduce the new function calling abstraction, FunctionChoiceBehavior (#6910)
### Motivation and Context The current `FunctionCallBehavior` has allowed us to utilize auto function calling for OpenAI type models. As we proceed to support more AI connectors, that differ from OpenAI models, we need to be able to handle functions for all models that support 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 In this PR: - We introduce a new function calling abstraction called `FunctionChoiceBehavior` which has three types: Auto, Required, and None. - One is able to configure the `function_choice_behavior` along with fully qualified function names (e.g., plugin1.function1), `maximum_auto_invoke_attempts` or `auto_invoke_kernel_functions` in yaml and JSON prompts. We have a new concept example showing how to do this for for yaml and JSON prompts. - If the fully qualified names are specified in the config file, they take precedence over the filters, if specified at a later point. - To make sure this isn't a breaking change, we still handle the previous `FunctionCallBehavior`, but so we can make decisions on the new `FunctionChoiceBehavior` we map the `FunctionCallBehavior` to `FunctionChoiceBehavior`. Each time `FunctionCallBehavior` is updated, `FunctionChoiceBehavior` will be updated, too. - The `_process_tool_call()` method in the `open_ai_chat_completion_base` needs to maintain the argument name as `function_call_behavior` as we cannot introduce a breaking change. - All concept samples have been converted to use `FunctionChoiceBehavior`. - New unit tests have been added for `FunctionChoiceBehavior` and we still currently support `FunctionCallBehavior` tests to make sure we haven't broken the backwards compatibility. - Added `deprecated` typing decorators to classes/methods to alert users that it would be best to transition to `FunctionChoiceBehavior` even though `FunctionCallBehavior` is still supported. - The `FunctionCallingStepwisePlanner` was updated to use the new `FunctionChoiceBehavior`. - Closes #6496, #6458 - Addresses #6626 <!-- 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
|
a2720a605d |
Python: Fix broken concept samples. Run concept examples as tests. (#6660)
### Motivation and Context We had many broken concept examples. These samples are also not covered by tests so it's hard to know when things are out of sync. <!-- 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 Fix the Python concept samples, and also cover them with tests so we aren't checking in code that is going to break them. <!-- 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 😄 |
||
|
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 😄 |
||
|
|
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
|
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 😄 |