### 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:
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 😄
### 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
<!-- 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 😄
### 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 😄
### 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 😄
### 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 😄
### 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 😄
### Motivation and Context
Fix sample plugin path for Windows. Re-enable samples CI tests.
<!-- 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 sample plugin path for Windows. Re-enable samples CI tests.
- Tests passing locally on both MacOS and Windows.
- Adds logic to each notebook to properly set up the correct path to
find imports. Notebooks should now run out of the box to close#6588
- Added retry logic for the samples tests to retry 3 times in the event
of a failure.
- Install notebook pip package at kernel level instead of shell level
- Updated all occurrences of `gpt-3.5-turbo-1106` to `gpt-3.5-turbo`
which is `gpt-3.5-turbo-0125`.
The GH Action code quality check was failing for this same code in
#6675, so this is superseding it. Now that the GH actions are fixed,
this also supersedes #6681.
<!-- 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 😄
### 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 😄
### 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 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Run notebooks as tests, working for all gettings started notebooks.
Also updated learn resources samples test, this can now easily be
extended with other sample scripts.
Closes: #4637
Partially closes: #4638
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
Updated samples for MS Learn, with tags.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
---------
Co-authored-by: Evan Mattson <[email protected]>
Tao Chen