mirror of
https://github.com/microsoft/semantic-kernel.git
synced 2026-10-12 02:19:06 +00:00
copilot/bump-messagepack-version
7
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Tao Chen
|
481d16a749 |
Python: Bedrock connector (#9100)
### 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. --> Add Amazon Bedrock AI to Semantic Kernel. Amazon Bedrock is a platform on AWS that offers access to a wide range to LLMs, including proprietary Amazon Titan models. We are integrating it into Semantic Kernel as one of our AI connectors to provide more options to developers. ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> 1. All interfaces implemented: chat completion (streaming + non-streaming), text completion (streaming + non-streaming), and text embedding. 2. Supports for function calling. 3. Supports for image content. 4. Supports for all models available on Bedrock. ### 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 😄 |
||
|
Tao Chen
|
9529652d5d |
Python: More telemetry in AI services (#8641)
### 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. --> Add more telemetry to our built-in AI services, and update the telemetry sample app to show case the changes. ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> ### Contribution Checklist The following items are added: 1. Add tracing to all streaming APIs via the `trace_streaming_xxx` decorators. 2. Wrap auto function invocation, with span name set to `AutoFunctionInvocationLoop`. Available functions will be recorded by the attribute `sk.available_functions`. 3. Common completion usage interface. 4. Add a test to make all APIs are instrumented. 5. Record service address when possible. Updates made to the telemetry sample app: 1. Rename to `telemetry` from `telemetry_with_application_insights`. 2. Add sample code showing auto function calling. 3. Reorganize the sample by scenarios. 4. Add more output options: Aspire dashboard and console. 6. Update Readme. TODO: Add unit tests from the streaming decorators and improve code converage. <!-- 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
|
5f49880d52 |
Python: Json schema improvements for Union and Optional (#7367)
### Motivation and Context We have some gaps in how we build the JSON schema for function calling related to Union and Optional types. There is also some work to do related to handling `Optional` versus `param | None = None`. <!-- 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 improves the JSON schema building for the Union and Optional types. It adds additional tests and improves some existing tests. - Closes #7297 - Closes #7298 <!-- 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
|
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
|
148e8de701 |
Python: Updates to user agent. Add unit tests. (#6824)
### Motivation and Context Updates to the User-Agent are required so that we can align with all three SK languages. Examples: User agent - semantic-kernel-csharp/1.1.1 [existing user agent] - semantic-kernel-java/1.1.1 [existing user agent] - semantic-kernel-python/1.1.1 [existing user agent] semantic-kernel-version header - csharp/1.1.1 - java/1.1.1 - python/1.1.1 <!-- 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 Updates to the user agent to reflect the desired changes/standardization across all SK languages. Adding unit tests. - Closes #6827 - Moves the `USER_AGENT` const from its previous home in the openai const file to a more generic const file. - Updates unit tests to be able to run properly when a valid `.env` file exists in the current working directory. The unit tests patch the env vars and our current implementation of Pydantic Settings loads the `.env` file if not specified. <!-- 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
|
ba9af0e07b |
Python: mypy coverage enhancement (#6250)
### 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. --> extend mypy coverage for prompt_templates, template_engine and some other smaller folders. still todo: connectors, memory and planner folders. ### 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
|
08bcc803ef |
Python: Unsafe input handling (#6003)
### 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. --> Implements dealing with unsafe content, by doing HTML parsing on variables and function results. Closes: #5889 ### Description <!-- Describe your changes, the overall approach, the underlying design. These notes will help understanding how your code works. Thanks! --> Adds parameter `allow_dangerously_set_content` to: - InputVariable - PromptTemplateConfig - PromptTemplateBase The behavior is that if the flag is set to True on the template itself (KernelPromptTemplate, Jinja2PromptTemplate or HandlebarsPromptTemplate) the behavior is the same, no encoding is done on inputs. Otherwise: - variables are encoded by default, this can be switched off using the InputVariables class for that variable. - function output is encoded by default, this can be switched off using the flag in the PromptTemplateConfig, this is not yet possible to do on a per function basis. ### 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 😄 |