microsoft/semantic-kernel
1
0
Fork 0
mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 02:19:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,197 Commits 63 Branches 1,077 Tags
ffeb099658d71fbee83e255e85574cdf106a5a09
Commit Graph
360 Commits
Author SHA1 Message Date
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 😄
 2024-07-23 04:38:55 +00:00
Tao Chen 5c8f4fd622 Python: Add application ID for Azure AI Inference (#7341) 
### 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.
-->
All Microsoft tools/SDKs that internally use the Azure AI Inference SDK
are required to set a unique application ID, which will be part of the
"use-agent" HTTP request header. This will allow teams to track usage
from that tool/SDK, using service-side telemetry dashboards.

Semantic Kernel's application ID is registered as
"semantic-kernel-python/{version}" according to this
[list](https://microsoft.sharepoint.com/❌/t/AzureMLExperiences-AgentsandCommonInferenceSDKteam/EUVgsgpFtdRLnkhxrdtJ1MIBDMl3wVfoza4c13MI_K6ywg?e=MEpwyo&ovuser=72f988bf-86f1-41af-91ab-2d7cd011db47%2Ctaochen%40microsoft.com&clickparams=eyJBcHBOYW1lIjoiVGVhbXMtRGVza3RvcCIsIkFwcFZlcnNpb24iOiI0OS8yNDA2MjcyNDgwNyJ9).

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Add "semantic-kernel-python/{version}" as the application ID where we
use the Azure AI Inference 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 😄
 2024-07-18 18:53:42 +00:00
Evan Mattson 6b01468efb Python: fix for kernel function type_object when not using Annotations. Add more unit tests. (#7338) 
### Motivation and Context

The current kernel function decorator class parses function params, but
had a miss related to how the underlying param's type is parsed if not
using Annotations.

<!-- 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 properly handles the type_object for params that don't using
typing.Annotations.
- Adds unit tests to exercise the code.
- Adds more kernel.py unit tests for near 100% test coverage.
- Adds some planner tests to improve the test coverage.
- Closes #7300 

<!-- 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 😄
 2024-07-18 05:12:08 +00:00
Tao Chen 79207ffbbc Python: Migrate to Ollama Python SDK (#7165) 
### 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

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Currently, the Ollama AI connector uses `aiohttp` sessions to interface
with the local Ollama LLM service. However, we have made the decision to
transition to the official Ollama Python SDK.

Related to: https://github.com/microsoft/semantic-kernel/issues/6841,
https://github.com/microsoft/semantic-kernel/issues/7134

Test coverage report:

![image](https://github.com/microsoft/semantic-kernel/assets/12570346/8d414f71-fc1b-4870-b038-0f7d2985b985)

MyPy warnings: all cleared
### 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 😄
 2024-07-16 22:38:21 +00:00
Tao Chen 7bbdd46b56 Python: Azure AI Inference connector code quality improvement (#7217) 
### 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.
-->
We have been working on improving code quality and increasing the test
coverage. This PR focuses on the Azure AI Inference connector.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Improve test coverage.

![image](https://github.com/user-attachments/assets/2d47318c-3fa5-4884-abe1-128eb3668c98)
2. Cleared all Mypy warnings.

### 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 😄
 2024-07-15 08:11:01 +00:00
Eduard van Valkenburg e02770d83e Python: added tests for singular and small fix to code coverage (#7223) 
### 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 fix for the text streaming singular method
tests for both
small fix for test coverage

### 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 😄
 2024-07-12 17:58:44 +00:00
Nico MöllerNico MöllerEvan Mattson
 		6944914017 Python : CQ MyPy Fix for MistralAI Connector (#7182) 
### Motivation and Context
1. I saw that you are having spikes regarding enabling MyPy
2. On ##7049  i had the Liskov Principle commented
3. In #7144 is saw how you plan to solve this so i decided to adjust the
mistral connector to this

### Description

The PR contains changes to be compliant to MyPy in Mistral AI Connector.
Changes input Parameter for MistralAIChatCompletion from
MistralAIPromptExecutionSettings to PromptExecutionSettings.
Adding Test Cases for MistralAIPromptExecutionSettings and
PromptExecutionSettings.


![image](https://github.com/microsoft/semantic-kernel/assets/23048106/5822896e-17d1-4d68-9348-da6765ac3527)


### Tasks

- [x] Changes input Parameter for Liskov
- [x] Settings conversion
- [x] Adjust TestCases to 100%

### 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: Nico Möller <[email protected]>
Co-authored-by: Evan Mattson <[email protected]>
 2024-07-11 22:27:28 +00:00
Eduard van ValkenburgandTao Chen 6a0077c5d3 Python: added singular get methods (#7202) 
### 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.
-->
Adds singular get_..._content methods to all services, initially
implemented by calling the multi version and passing back the first
result, it therefore does not check on the number of responses
parameter, just provides the interface.

Also add `generate_raw_embeddings` to Embedding Base to allow models to
return different types, while keeping generate_embeddings to return a
numpy array.

Fixes #6926 


### 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: Tao Chen <[email protected]>
 2024-07-11 20:46:27 +00:00
Evan MattsonandGil LaHaye 904d1f514f Python: Increase unit test coverage (#7211) 
### Motivation and Context

We've been working on increasing the test coverage. These tests aren't
specific to the CQ spike, but I noticed that there was covering lacking
for them, and they were "low hanging fruit."

<!-- 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

Increasing the test coverage for some classes that have current test
coverage but were missing some line coverage here and there. At this
point in time, the test coverage report is showing 95% covered now.

<!-- 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: Gil LaHaye <[email protected]>
 2024-07-11 20:05:06 +00:00
Evan Mattson 240280a37b Python: Introduce the single, non-group chat completion agent (#7116) 
### Motivation and Context

Following in the steps of dotnet, we're beginning to add agent support
to Python. For an initial implementation the focus is on non-grouped,
chat completion agents. The first pass is covering a ChatCompletionAgent
that allows the user to define a ChatCompletion Service as part of the
SK Kernel, and then reference that service in an agent implementation.

<!-- 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:
- Adds support for a standard chat completion agent
- Adds the required abstractions to allow the single chat completion
agent to work
- Introduces a new agent concept sample showing how to invoke the agent
for a streaming and non-streaming context.
- Adds unit tests to cover the new code
- Closes #7079 


![image](https://github.com/microsoft/semantic-kernel/assets/35585003/8fa1f248-52b2-41b9-85ac-38ac80a05a68)

<!-- 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 😄
 2024-07-11 19:57:28 +00:00
Eduard van Valkenburg 8a23c2656f Python: add experimental unit tests for python 3.13 (#7204) 
### 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.
-->
Adds unit test run only for ubuntu for python 3.13, should not fail full
job when it does fail.
Slight improvement of filename handling for the coverage.

### 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 😄
 2024-07-11 16:30:28 +00:00
Eduard van Valkenburg bdf30a617a Python: allow more options for FunctionCallContent constructor (#7105) 
### 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 #6932
Added ability to supply function_name and plugin_name as well as name
(name keeps precedence)
Added ability to supply arguments as a dict, instead of string.
Also ups the test coverage for the contents folder.

### 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 😄
 2024-07-11 11:52:49 +00:00
Eduard van Valkenburg ea9276759b Python: mypy and tests for OpenAI (#7144) 
### 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.
-->
Up until this point, we had not had full test coverage for all openai
classes, and mypy type checking was disabled.
These have now both been solved, lots of small fixes for the typing and
a set of new tests for the different parts of the openai suite of
classes have been added.

fixes #7131
fixes #6930

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
The unit tests for OpenAI all now have multiple ways of creating checked
and tested.
Also actual responses from the openai package are created and used to
test the parsing of those into our classes.

### 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 😄
 2024-07-11 11:51:18 +00:00
qowlsdn8007andEvan Mattson 90e2237296 Python: Small docstring fix (#7187) 
Docstring in add_plugin_from_openai method explain that it's a plugin
from the openapi manifest, not open ai.


https://github.com/microsoft/semantic-kernel/blob/ed463329e7463b068a6669ecf3b7d03d040d1699/python/semantic_kernel/functions/kernel_function_extension.py#L211

### Motivation and Context
I found the add_plugin_from_openapi method because I needed a function
related to the semantic function for calling the API. While reading the
docstring, I saw an open AI description that had nothing to do with the
method, so I am reporting this.

<!-- 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
See changes, it's a one-liner 😁

<!-- 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: Evan Mattson <[email protected]>
 2024-07-10 16:33:56 +00:00
Evan Mattson 469092f35c Python: Enable mypy for the HuggingFace connectors. Increase unit test code coverage. (#7176) 
### Motivation and Context

We have mypy enabled on parts of the code base, but not all. The goal is
to enable it across the entire SK python code. As part of this, we've
broken up the work to tackle different sections. Additionally, we're
working to improve the unit test code coverage for these sections of
code.

<!-- 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:
- turns on mypy for the HuggingFace connector
- adds more unit test coverage for the text completion and embeddings
connector to achieve >95% code coverage.
- closes #7133

<!-- 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 😄
 2024-07-09 18:32:06 +00:00
Tao Chen 0ad7f54bdd Python: Azure AI Inference Function Calling (#7035) 
### 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 the Function Choice abstraction has been implemented in Python,
it is time to extend this feature to other connectors. The first (OAI
and AOAI are not included) connector to be granted this honor is the
Azure AI Inference connector.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Add function calling to Azure AI Inference.

### 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 😄
 2024-07-09 16:25:57 +00:00
Evan Mattson 4e99b76834 Python: Turn on mypy for function choice behavior. Improve test coverage. (#7154) 
### Motivation and Context

We have mypy enabled on parts of the code base, but not all. The goal is
to enable it across the entire SK python code. As part of this, we've
broken up the work to tackle different sections. Additionally, we're
working to improve the code coverage for these sections of code.

<!-- 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:
- turns on mypy for the function choice behavior code. Code adjustments
were made per mypy, with the exclusion of one place that contain a
`type: ignore` as mypy claimed the function mapping couldn't execute
properly, when it indeed can.
- adds more unit test coverage for the function choice behavior and
class and classmethods. There is 100% code coverage.
- fixes a bug related to mapping the function call behavior required
behavior to the new required behavior.
- closes #7137

<!-- 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 😄
 2024-07-09 15:32:21 +00:00
Evan Mattson 44d47ac382 Python: Enable mypy for connector utils and search connectors. Improve code quality. (#7163) 
### Motivation and Context

We have mypy enabled on parts of the code base, but not all. The goal is
to enable it across the entire SK python code. As part of this, we've
broken up the work to tackle different sections. Additionally, we're
working to improve the code coverage for these sections of code.

<!-- 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:
- turns on mypy for the connector utils and the search connectors (Bing
and Google). Small Code adjustments were made per mypy.
- other refactoring to make the code cleaner like using https
AsyncClient, and better error handling around the API call.
- introduces Google Search settings for the connector.
- adds more unit test coverage for the document loader util and the
Bing/Google search connectors. There is 100% code coverage.
- closes #7136

<!-- 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 😄
 2024-07-09 15:03:08 +00:00
Evan Mattson 44f5db1136 Python: Turn on mypy for OpenAPI plugins. Increase code coverage. (#7153) 
### Motivation and Context

We have mypy enabled on parts of the code base, but not all. The goal is
to enable it across the entire SK python code. As part of this, we've
broken up the work to tackle different sections. Additionally, we're
working to improve the code coverage for these sections of code.

<!-- 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:
- turns on mypy for the openapi connector (plugin). Code adjustments
were made per mypy, with the exclusion of two places that contain a
`type: ignore` as the type was already valid, but mypy still complained.
- adds more unit test coverage for the OpenAPI models and classes. All
OpenAPI classes are now >95% covered.
- closes #7135 

<!-- 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 😄
 2024-07-08 20:40:13 +00:00
Tao Chen 5779b7d3be Python: Verify local models in Ollama and LM Studio are compatible with the OpenAI connector (#6973) 
### 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.
-->
Related to https://github.com/microsoft/semantic-kernel/issues/6498

The use of local models presents a twofold benefit for developers:
increased flexibility and reduced costs. Ollama and LM Studio are two
well-known platforms that facilitate the hosting of models locally, both
of which offer compatibility with OpenAI endpoints. As such, it is
imperative that our OpenAI connector functions correctly when users are
operating models on these platforms.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Verify that our OpenAI connector works as expected with models hosted
locally using Ollama and LM Studio.
2. Create three new samples (Ollama/chat, LM Studio/chat, LM
Studio/Embedding) under `/concepts/local_models` to show how to using
local models with the OpenAI connector.
3. Fix a bug in `test_sample_utils.py` where if a test case is retried
and input was never reset.

### 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 😄
 2024-07-05 22:26:09 +00:00
Nico MöllerandNico Möller ca7a58ed28 Python: #6499 Mistral AI Chat Completion (#7049) 
### 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.
-->

 1. Why is this changed required ?
To enable Mistral Models with Semantic Kernel, there was the issue #6499
in the Backlog to add a MistralAI Connector
2. What problem does it solve ?
It solves the problem, that semantic kernel is not yet integrated with
MistralAI
3. What scenario does it contribute to?
The scenario is to use different connector than HF,OpenAI or
AzureOpenAI. When User's want to use Mistral they can easliy integrate
it now
4. If it fixes an open issue, please link to the issue here.
#6499 

### Description

The changes made are designed by the open_ai connector, i tried to stay
as close as possible to the structure.
For the integration i installed the mistral python package in the
repository.

I added the following Classes :
- MistrealAIChatPromptExcecutionSettings --> Responsible to administrate
the Prompt Execution against MistralAI
- MistralAIChatCompletion --> Responsible to coordinate the Classes and
for Content parsing
- MistralAISettings --> Basic Settings to work with the MistralAIClient

**To test the changes with the tests please add MISTRALAI_API_KEY and
MISTRALAI_CHAT_MODEL_ID as Enviorment Variable**

From a design decision i moved the processing of Functions from
Connectors to the ChatCompletionClientBaseClass

What is integrated yet :

- [X] Integrate Mistral AI ChatCompletion Models without Streaming
- [X] Integrate Mistral AI Chat Completion Models with Streaming
- [X] Simple Integration Test to test Streaming and non Streaming
- [x] Extended Testing including Unit Testing & More Integration Tests

### 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: Nico Möller <[email protected]>
 2024-07-04 12:39:49 +00:00
Evan Mattson 007e3dab8b Python: Update sessions python plugin to work with the correct endpoints (#7070) 
### Motivation and Context

The Sessions Python Plugin was working properly, but some users reported
that the endpoints needed updating. We had made previous updates to the
plugin, but they didn't account for the update API endpoints and request
body changes shown
[here](https://learn.microsoft.com/en-us/azure/container-apps/sessions-code-interpreter).

<!-- 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 updates the plugin tool to work with the documented endpoints
and request bodies. The unit tests were also updated. The concept sample
for the Azure Python sessions plugin was tested with all methods to:
execute code, upload multiple files, list files, and download them.
- Additionally, improve error handling for each of the function calls so
the proper error message is surfaced to the user via SK exceptions.
- Fix path building and making sure the sessions endpoint is converted
to a string from the Pydantic https type.
- Closes #6934 

<!-- 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 😄
 2024-07-04 11:43:47 +00:00
Eduard van Valkenburg ed24889b7d Python: removed google palm (#7051) 
### 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.
-->
Since Google Palm will be deprecated soon, removing Google Palm from SK.

Closes #6362 

### 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 😄
 2024-07-02 13:58:23 +00:00
Eduard van Valkenburg fe38a5f5d6 Python: slight improvements in kernel and function result content, sample of local function calling with Nexus Raven (#6982) 
### 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 introduces a sample that uses function calling with a local model,
Nexus Raven V2, in this case using the API, but the same model can be
loaded using the Hugging Face Connection, the class here is highly
adapted and specific to Nexus including parsing the returned function
call value, into FunctionCallContent and then running that.
It then returns one or more ChatMessageContents with the function call
content and function result content which can then be shared with a
OpenAI call.

Error handling improvements:

*
[`python/semantic_kernel/contents/chat_history.py`](diffhunk://#diff-b57a30f97fec1a91bbf6f7d15584473a8f0cf409797bdcd90d8c80bedc670892L266-R267):
Improved error logging when parsing prompts as XML fails.
*
[`python/semantic_kernel/contents/function_result_content.py`](diffhunk://#diff-3b69e6aedf4c29038cdff0ac99602b70583ab6c85f7bd777b08ad96b7fa48d87L7-R10):
Removed field validator for `result` and allow result to be any value,
instead of casting everything to string.
[[1]](diffhunk://#diff-3b69e6aedf4c29038cdff0ac99602b70583ab6c85f7bd777b08ad96b7fa48d87L7-R10)
[[2]](diffhunk://#diff-3b69e6aedf4c29038cdff0ac99602b70583ab6c85f7bd777b08ad96b7fa48d87L50-R51)
[[3]](diffhunk://#diff-3b69e6aedf4c29038cdff0ac99602b70583ab6c85f7bd777b08ad96b7fa48d87L63-L69)
[[4]](diffhunk://#diff-3b69e6aedf4c29038cdff0ac99602b70583ab6c85f7bd777b08ad96b7fa48d87R92-R115)

Minor changes:

*
[`python/semantic_kernel/core_plugins/math_plugin.py`](diffhunk://#diff-632444474bd3ea991b4409dfd0ab194e0789c73617bef4a3dcae4db5c4b0b6c0L32-R38):
Removed some docstrings for clarity.
[[1]](diffhunk://#diff-632444474bd3ea991b4409dfd0ab194e0789c73617bef4a3dcae4db5c4b0b6c0L32-R38)
[[2]](diffhunk://#diff-632444474bd3ea991b4409dfd0ab194e0789c73617bef4a3dcae4db5c4b0b6c0L55-R47)
*
[`python/semantic_kernel/functions/kernel_function_from_prompt.py`](diffhunk://#diff-eabd53da2ec241cce6f92de85283065e7b478d62cefb52817c5b29ff07e28189L173-R174):
Changed the order of condition checks for better readability.
*
[`python/semantic_kernel/kernel.py`](diffhunk://#diff-3db6fe98818eda0b824788901c718d35eac8b13d0ff428d3dfd417866d922d3aR9-R10):
Added functionality to update kernel arguments in `invoke_stream` method
and made `function_name` and `plugin_name` optional in `invoke_prompt`
method.
[[1]](diffhunk://#diff-3db6fe98818eda0b824788901c718d35eac8b13d0ff428d3dfd417866d922d3aR9-R10)
[[2]](diffhunk://#diff-3db6fe98818eda0b824788901c718d35eac8b13d0ff428d3dfd417866d922d3aR29)
[[3]](diffhunk://#diff-3db6fe98818eda0b824788901c718d35eac8b13d0ff428d3dfd417866d922d3aR119-R120)
[[4]](diffhunk://#diff-3db6fe98818eda0b824788901c718d35eac8b13d0ff428d3dfd417866d922d3aL195-R202)
[[5]](diffhunk://#diff-3db6fe98818eda0b824788901c718d35eac8b13d0ff428d3dfd417866d922d3aL209-R216)

Closes #6804
Closes #6944

### 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 😄
 2024-06-28 20:17:05 +00:00
Mihir PatilandEvan Mattson ccc6ed0467 Python: Catch correct error for does_collection_exist (#6950) 
### Motivation and Context

Fixes #6949. 

### Description

Catches the correct error for does_collection_exist. 

### 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]>
 2024-06-28 13:35:04 +00:00
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 😄
 2024-06-27 20:34:59 +00:00
Tao ChenandEvan Mattson d22ee5af55 Python: Azure Model-as-a-Service Python connector (#6742) 
### 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.
-->
Related to: https://github.com/microsoft/semantic-kernel/pull/6693

Azure Model-as-a-Service allows users to deploy certain models from the
Azure AI Studio model catalog as an API. This option also provides
pay-as-you-go access to the models hosted. Below are some of the models
that are supported:
- Microsoft Phi-3 family
- Meta Llama family (Llama 2 chat & Llama 3 instruct)
- Mistral-Small & Mistral-Large
- and more

We'd like to provide an AI connector for users of SK to use Azure
Model-as-a-Service.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
A new AI connector named `azure_ai_inference` is added to support Azure
Model-as-a-Service. This connector takes a new dependency on the Python
`azure.ai.inference` 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 😄

---------

Co-authored-by: Evan Mattson <[email protected]>
 2024-06-24 22:00:57 +00:00
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 😄
 2024-06-20 15:02:01 +00:00
Eduard van Valkenburg 9f205c3245 Python: fix for Python: parameters mentioned in a SK prompt are not synced wi… (#6807) 
fixes #6806

### 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

<!-- 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 😄
 2024-06-19 06:35:05 +00:00
Evan Mattson e244dad208 Python: If no env_file is configured then default to relative .env file (#6754) 
### Motivation and Context

We'd like to improve the handling of the .env file related to Pydantic
Settings. If Environment variables aren't found, it's possible to fall
back on reading the values from a .env file.

<!-- 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

Previous to this PR, that is done by specifying the .env file path. Now,
if the env_file is not specified, we will default to reading from the
relative ".env" file in the cwd.

<!-- 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 😄
 2024-06-18 15:29:01 +00:00
Eduard van Valkenburg 1cc6464860 Python: Env sample (#6711) 
### 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.
-->
Clarify the names and uses of the environment variables and pydantic
settings.

### 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 😄
 2024-06-14 19:04:44 +00:00
Milad Mobarhan a9d361a82f Python: fix: Preserve class type in experimental_class decorator to avoid type inference issues (#6709) 
### 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.
-->

Closes https://github.com/microsoft/semantic-kernel/issues/6707 

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

- Introduce `TypeVar` `T` bounded to `type` to ensure the decorator
maintains the class type.
- Modify the `experimental_class` decorator to use the bounded `TypeVar`
for accurate type hinting.


### 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 😄
 2024-06-14 16:51:25 +00:00
Evan Mattson 68ffd1b1de Python: Azure AI Search api key should not be required. (#6698) 
### Motivation and Context

We have a regression that makes the AI Search Setting's API key
required.

<!-- 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

Make the AI Search setting a non-required attribute. Fixes #6697

<!-- 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 😄
 2024-06-13 15:12:27 +00:00
Eduard van Valkenburg 05dcb29dea Python: Support for image content and chat message content with image content (#6520) 
### 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.
-->
Introduces a ImageContent class
Allows that type to be part of ChatMessageContent
Adds a sample for both local and online images
Adds many tests with data uri edge cases, and binary parsing edge cases.

Closes #6536 

### 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 😄
 2024-06-13 15:09:25 +00:00
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 😄
 2024-06-11 15:28:12 +00:00
Eduard van Valkenburg 032fa2cfbb Python: import fix for azure ai search settings in chat (#6562) 
### 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 for an issue where Azure AI search packages where needed for core
behavior.

### 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 😄
 2024-06-05 15:06:01 +00:00
Evan Mattson b85bca1919 Python: Handle streaming tool call attempts. Fix func calling concept example. (#6560) 
### Motivation and Context

If auto_invoke was False and the function used streaming, the max func
attempts were being set to 0 which Python's range function doesn't like.
The chat gpt auto function calling example was also broken due to wrong
checks on the returned result for FunctionCallResult 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

Fixing handling streaming tool calls when auto invoke is false and
fixing the chat gpt auto function calling concept example.

<!-- 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 😄
 2024-06-05 14:35:01 +00:00
Stefan MuscaluEvan MattsonEduard van Valkenburg
 		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]>
 2024-06-04 07:09:00 +00:00
Evan Mattson 2a7763aa3b Python: Updates to fix changes made to ACA Sessions Plugin (#6507) 
### Motivation and Context

There were changes made to the ACA upload file API that weren't made in
the Python SDK. This caused the file upload to error out. The ACA team
also passed along their docs and advice to update to a certain API
version, and what changes that brings.

<!-- 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

Fixes #6494
Closes #6509 
- Properly handle the file upload's response body as it now contains a
`$values` attribute and then a list of key-value pairs.
- Also properly construct the `remote_file_path` by checking if it
includes `/mnt/data/` and if not, appending it to the front of the
`remote_file_path`.
- Update to use ACA API version 2024-02-02. This means the API version
needs to be included with all requests. Adding API version to requests,
and adding session ID to all requests.
- Removed the ability to pass in a BufferedReader to the upload file
function since the LLM doesn't know how to handle that. As is done in
dotnet, allow the user to specify a local_file_path which the model can
handle, to upload a file.
- Update 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 😄
 2024-06-04 07:00:26 +00:00
Chris BoandEvan Mattson e9b140721b Python: Fix Bing Connector Setting Usage (#6493) 
### 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.
-->

[PR 6278](https://github.com/microsoft/semantic-kernel/pull/6278) added
support for Bing Custom Search, but had a bug introduced when merging a
change to how settings worked.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

This PR fixes the bug in how settings are referenced.

### 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]>
 2024-06-03 18:12:49 +00:00
Eduard van Valkenburg 780aa63e76 Python: implement async support for templates (#6486) 
### 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.
-->

Jinja2 templates now use async functions instead of nested ones!
With full testing

### 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 😄
 2024-06-03 17:12:57 +00:00
Eduard van Valkenburg e6ec0eff4a Python: added tests for core_plugins (#6470) 
### 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 tests to completely cover the core_plugins.

### 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 😄
 2024-06-03 15:41:56 +00:00
Chris BoandEvan Mattson 5f40f57897 Python: Support Bing Custom Search (#6278) 
### 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.
-->
Update BingConnector to add support for Bing Custom Search, which can be
used to specify domains and webpages to search and allows custom ranking
adjustments.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Note that API keys for Bing are separate from Bing Custom Search.

### 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]>
 2024-05-31 23:46:06 +00:00
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 😄
 2024-05-31 20:50:26 +00:00
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 😄
 2024-05-31 16:37:19 +00:00
Evan Mattson 4508e8d966 Python: properly handle types while building the schema (#6469) 
### Motivation and Context

While parsing the kernel function's arguments, we recurse to the type's
base origin and then set that as the `type_object`. For a type like
`list[MyCustomClass]` only setting the `type_object` as `list` has us
lose out on the other valuable information of the list's type, which is
`MyCustomClass` and what attributes it contains within. This then leads
us to build an incomplete schema when creating the kernel function
parameters and ultimately when we send the JSON schema to the model
during tool calls.

<!-- 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:
- Closes #6466 
- Refactors the kernel function decorator code to parse
arguments/parameters. We now grab the `type_object` of the
parameter/argument in question, which is used to build the JSON schema.
- Fixes the schema building for the types we build. We were missing
`required` parameters as well.
- Attempts to handle as many edge cases as possible, although there are
probably more that we aren't handling right now -- for example properly
handling all schemas for Unions is tricky.
- Adds unit tests to make sure we are building the JSON schema as
expected. All unit, integration and sample tests are passing.
- Handles a `TypeError` exception during auto function calling where the
model sends back an argument like `2`, which doesn't cause JSON parsing
to fail, but will fail when trying to update the argument dictionary.

<!-- 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 😄
 2024-05-31 16:04:08 +00:00
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 😄
 2024-05-31 13:06:41 +00:00
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 😄
 2024-05-30 09:38:28 +00:00
Eduard van ValkenburgandEvan Mattson 7cb651a809 Python: fix for add_function with conflicts (#6437) 
### 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 change in the logic and detection and log.warning for when the
prompt and template and template_format are not the same, when using
kernel.add_function

Fixes #6412 

### 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]>
 2024-05-29 18:21:14 +00:00
Daniele Antonio MaggioandEvan Mattson 5d25f6a8dd Python: fix: Remove wrong response_format override in AzureChatPromptExecutionSettings class (#6424) 
### Motivation and Context

This change is required to fix #5997 


### Description

The change is removing the wrong `response_format` override in
`AzureChatPromptExecutionSettings` class. The PR is also adding a unit
test covering the case where `response format` is defined.

The changes were successfully tested against an `Azure OpenAI` instance
with a `gpt-4o` deployment by specifying an
`AzureChatPromptExecutionSettings` like follows:

```python 
execution_settings =  AzureChatPromptExecutionSettings(
        service_id=service_id,
        ai_model_id=ai_model_id,
        max_tokens=1000,
        temperature=0.2,
        response_format={"type": "json_object"},
    )
```

### 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]>
 2024-05-29 15:52:50 +00:00