### 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?
When we try to create an index in AI Search where the encryption is
enabled we have this issue :
Code: OperationNotAllowed
Message: The creation of non-encrypted Indexes is not alowed when
encryption policy is enforced.
Which make the operation create_collection unusable
2. What problem does it solve?
Use create_collection function
3. What scenario does it contribute to?
If the customer uses the CMK for the encryption
4. If it fixes an open issue, please link to the issue here.
### Description
The Azure Search Documents supports the encryption key with the class
SearchResourceEncryptionKey, adding it (Free to the customer to use it
or not) resolve the issue.
Maybe it may be use it in save_information function as well ?
### 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]>
### 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.
-->
Fixes#4652
and reenabled integration tests for hugging face
found we never added the prompt execution settings class into the right
place in the HF class, fixed now.
### 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
Fixes#4869. On a created semantic function, the plugins weren't getting
set for use for the function.
<!-- 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
Set the default plugins for the registered function, and add a unit
test.
<!-- 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
Solves #4864
The KernelFunction was configured as a Python class without regards to
using Pydantic fields and its validations. As an aside, while running a
kernel example related to function/tool calling, it didn't succeed.
<!-- 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 cleans up the KernelFunction by creating Pydantic fields. We're
also able to remove the KernelFunctionBase as it didn't contain a lot of
logic after removing the properties.
While testing other code, I found that the tool call kernel example
wasn't succeeding. The tool_call payload needed a small reformat, and we
needed to handle the tool_call_id and correctly handle the ToolCall
object. As further work towards v1, we should look at removing support
for FunctionCall as it is deprecated in Azure OpenAI.
We now see:
```
User:> What is 3+3?
Mosscap:> Ah, the timeless question of arithmetic! The sum of 3 and 3 is undoubtedly a splendid number.
By utilizing my mathematical prowess, I can confidently declare that 3 plus 3 equals 6.
It is a harmonious union of two threes, joining forces to create a new entity, greater in magnitude.
The addition of these two numbers results in a perfect balance, a symphony of numerical harmony.
```
<!-- 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]>
### Motivation and Context
Completes work item: #4846. The Kernel class was not following the
Pydantic convention.
<!-- 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 Kernel class to use the KernelBaseModel and Pydantic
fields. All unit and integration tests passing.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
---------
Co-authored-by: Evan Mattson <[email protected]>
Co-authored-by: Eduard van Valkenburg <[email protected]>
### Motivation and Context
This PR solves two works items: #4560 and #4667. The Python SDK had
different ways of handling plugins and collections. The work in the PR
helps align the SDK with dotnet nomenclature and structure.
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
### Description
A `KernelPluginCollection` is introduced with an underlying
`DefaultKernelPlugin` and a `KernelPlugin` base class. Other code is
refactored to use this new `KernelPluginCollection` model which should
simplify how plugins are handled. Unit tests are added to test the new
functionality. Existing unit tests and integration tests, along with
kernel examples and notebooks were updated based on these changes.
Unlike before, we're requiring plugins to be defined with a name, which
removes the GLOBAL_PLUGIN constant name of "__GLOBAL_PLUGIN__". In some
senses, while creating a plugin or a function, a name may not be
provided and so a random name in the form of a plugin
(p_<random_ascii_chars>) or function (f_<random_ascii_chars>) is used.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
---------
Co-authored-by: Evan Mattson <[email protected]>
### Motivation and Context
Completes #4794.
Most of SK Python is written with async code; however, there were some
code paths that masked the underlying async code and made it look like a
sync function invoke. In reality, asyncio spun up event loops and
attempted to manage them properly. This becomes tricky when running a
Jupyter notebook as they have their own event loop.
<!-- 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 removes the ability to call a kernel function synchronously.
Since the majority of the code base is written with async methods, and
to match dotnet, which is async, we're removing the sync function invoke
and its dependent code. Some Planners were also run synchronously --
these were updated to run asynchronously. Kernel examples, notebooks,
docs, and tests were updated accordingly.
<!-- 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
Following the C# implementation, renames all classes and variables of
`*RequestSettings` to `*PromptExecutionSettings`.
Fixes#4676
### 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 are going to add
[Astra](https://docs.datastax.com/en/home/docs/index.html) as a memory
store.
DataStax Astra DB is a serverless vector database that’s perfect for
managing mission-critical AI workloads. It’s built on Apache Cassandra®,
making Astra DB a highly scalable, reliable database technology. It’s a
powerful all-in-one data storage solution, ideal for Generative AI
projects.
### Description
- Add astra into python/semantic_kernel/connectors/memory/astradb
- Add test into
python/tests/integration/connectors/memory/test_astradb.py
### 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: jsbilgi <[email protected]>
Co-authored-by: Obioma Anomnachi <[email protected]>
### 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.
-->
As we are preparing to move towards v1 where the context no longer is
used, we need a better way of handling the responses from models and
capture them in a more structured way, also in preparation of
multi-modal models and the like.
Closes#4598
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Added KernelContent and StreamingKernelContent base classs, consistent
with the dotnet versions of those.
Subclasses of this class for specific services, for instance, the OpenAI
class has parsing for the content, function_calls, tool_calls in it, and
the Azure OpenAI one has parsing for the context in it.
### 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
<!-- 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.
-->
Fixes#4711 and #4705 and addresses some inconsistencies in the way the
chat_prompt_template is created, now has more control.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Added parse flags to chatPromptTemplate to allow the user to control is
something is loaded into messages or not.
Added better docstrings and tests for this as well.
### 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
When the RAI response doesn't contain a `code` the class
`ContentFilterAIException` would fail to initialize because it was
setting `""` as content_filter_code. This sets
`"ResponsibleAIPolicyViolation"` instead in that case.
Fixes#4709
### 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]>
### Motivation and Context
To better align with SK dotnet v1, Python skills have been renamed to
plugins. This removes the root samples skills directory as dotnet
supports the plugins and their configs. This the beginning of more work
to consolidate other files/names, per the backlog. I've run several
greps for files or file names containing "skill" (case insensitive), and
no results appear. Do alert if you find anything else that includes
"skill."
Fixes#3319
<!-- 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 is a large, breaking change PR as the replacement of "skills" to
"plugins" affects many files. It was difficult to break this up into
smaller chunks without leaving the SK Python repo in a bad state for
some time. Other updates include:
- Prompt template has been updated to use `execution_settings`, which
aligns with dotnet, from the previous `completion` that Python used.
- AzureOpenAI/OpenAI function calling has been updated to match the
current versions of tools/tool_choice. Parsing messages in the open_ai
utils respects this as it now looks for tool_calls and it configures the
function_call with the id (new), name, and argument).
- File renames, where the filename used to contain "skill" will look
like new code, but it's the same code, just with "plugin" in the name.
- Kernel examples and notebooks have been tested and are working. Unit
tests and integration tests are passing.
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄
---------
Co-authored-by: Evan Mattson <[email protected]>
### 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.
-->
Ollama is a great way to run several smaller models locally, this
connector allows that to be used with SK.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Added services and request settings for Ollama.
### 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.
-->
Fixes#4538 - data source parameters in ExtraBody were not serialized
correctly by Pydantic, so the call to the chat completions extensions
API was failing.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
- Add Pydantic annotation `SerializeAsAny` to `AzureDataSources` to
ensure all parameters of subclasses are serialized, not just the ones in
the base class.
- Update with-data samples to use `AzureChatRequestSettings`
- Update unit tests and unskip integration test
### 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: Sarah Widder <[email protected]>
### 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
When an Azure OpenAI content filter error is triggered the current
`AIException` hides the details of that specific error. This makes it
hard for the consumer to see a more detailed description of the error in
their prompt or input.
Solves #4197
### Description
Detects when a content filter error is raised, then parses the
meaningful information about it and raises a new
`ContentFilterAIException` with that information ready for the consumer
to use.
### 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]>
### 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.
-->
As we are tightening the formatting and linting setups, this was
missing, now the line-length for black and ruff are the same, thereby no
longer running into black issues as often.
### 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.
-->
This PR implements the new approach to AI Request settings as described
here:
https://github.com/microsoft/semantic-kernel/blob/main/docs/decisions/0008-support-generic-llm-request-settings.md
and completes #3312
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Does this:
- Creates AI Request Settings with service_id (referring to the
registered AI services in a kernel) and extension_data, a dict that can
hold any number of settings
- has several methods:
- `from_ai_request_settings` -> constructor to create a new
request_settings object based on another, supports creating specific
ai_request_settings from generic ones.
- `update_from_ai_request_settings` -> updating the fields of a request
setting from another ones.
- `prepare_settings_dict` -> method that is used when actually creating
the dict that get's passed to the handler of the AI service.
- Created subclasses like OpenAIChatRequestSettings which has all the
required fields of a OpenAI Chat completion, same for OpenAIText,
AzureChat, GooglePalm, HuggingFace, etc.
- added `get_request_settings_class` to ai_services to return the class
used for the settings for that service.
The goal is that when running, this settings object get's updated and a
single operations (called `prepare_settings_dict`) is used to return a
dict that can be passed to the api call directly, thereby reducing the
need for custom logic everywhere, this will also negate the need for
things like `complete_chat_with_functions_async` and others. So also
removed complete_chat_..._async methods from openai and azure openai.
It has also changed the prompt_template_config with the generic type for
the AIRequestSettings or subclasses, and some other changes.
### 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 `test_can_execute_stepwise_plan` integration test succeeds sometimes
and fails others. Marking it with `xfail` until we can root-cause the
issue. It's blocking PRs from completing successfully.
Underlying issue is #4466.
<!-- 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 above.
<!-- 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]>
### Motivation and Context
This replaces passing Logger instances as arguments around with the
preferred Python way of having each module define a module-wide `logger`
instance at the top of the module. Fixes#3711
### Description
Removes any `log` argument and argument documentation. Replaces usage of
those `log` arguments with the module-wide `logger` instance.
### 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: Eduard van Valkenburg <[email protected]>
### 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 change adds a python connector for Azure OpenAI chat completions
with data, which was already supported in the .NET SDK.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Add connector for Azure OpenAI chat completions with data and associated
sample code for how to use it. Some minor changes were made to the SK
function to handle the "tool" message that contains the citations and
other information returned from the chat completions extensions API.
### 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: Sarah Widder <[email protected]>
### Motivation and Context
Currently, users in Python have no ability to configure default_headers
for the AzureOpenAI/OpenAI clients we use. Additionally, if a user wants
to set up their own AzureOpenAI/OpenAI client, this isn't possible. This
PR addresses #2895.
<!-- 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
Allow users to set default_headers for Chat/Text/Embedding Completion
classes for both OpenAI and AzureOpenAI. Additionally, allow users to
pass in a customer OpenAI/AzureOpenAI client, if desired. Update tests
accordingly.
<!-- 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]>
### 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.
-->
Fixes the issue flagged by @sarah-widder in #3919,
and added tests for base_url scenario's.
### 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.
-->
Upgraded pydantic to 2.0+, much cleaner, less complexity in different
types of base models.
### 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
I have added Azure CosmosDB MongoDB vCore as a data store. MongoDB vCore
now supports vector search on embeddings, and it could be used to
seamlessly integrate your AI-based applications with your data stored in
the Azure CosmosDB. More details about Mongo vCore can be found here:
https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/vector-search.
Issue https://github.com/microsoft/semantic-kernel/issues/2375
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, by providing the following
information:
-->
1. Why is this change required? **MongoDB vCore now supports vector
search on embeddings, and it could be used to seamlessly integrate your
AI-based applications with your data stored in the Azure CosmosDB.**
2. What problem does it solve? This adds a new memory store MongoDB
vCore(Azure CosmosDB)
### Description
<!-- Describe your changes, the overall approach, and the underlying
design.
These notes will help you understand 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: Abby Harrison <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Mark Wallace <[email protected]>
### Motivation and Context
Replaces: https://github.com/microsoft/semantic-kernel/pull/3074
This PR adds the User-Agent header "Semantic Kernel" to calls made to
OpenAI/Azure OpenAI and OpenAPI calls.
### Description
* Addition of telemetry.py file containing telemetry constants
* ability to disable Azure/OpenAI telemetry with an environment variable
called AZURE_TELEMETRY_DISABLED
### 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: Devis Lucato <[email protected]>
### 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.
-->
#3038
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
---------
Co-authored-by: Roger Barreto <[email protected]>
Co-authored-by: Dmytro Struk <[email protected]>
### 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?
- A substring in string check was being done using a '.contains' method
which doesn't exist in python.
2. What problem does it solve?
- avoids the error: Error occurred while running plan step: 'str' object
has no attribute 'contains'", AttributeError("'str' object has no
attribute 'contains'"))
3. What scenario does it contribute to?
- stepwise planner execution
7. If it fixes an open issue, please link to the issue here.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
I changed the substring in string check to the proper method for python.
### 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: Kevin Kent <[email protected]>
Co-authored-by: Dmytro Struk <[email protected]>
### 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.
-->
It's shame sometimes it shines through that some of the earliest code in
the python code base was a direct port from C#, like with the .get
method on the context variables, made the change here to have the exact
some signature as the default python dict.
Also replaces contains_key with __contains__ so that 'in' keyword can be
used, just like a normal dict.
Fixes#2962
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Changed the .get method
Replaced the contains_key method with __contains__
Made changes in samples, tests and planner to deal with that.
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
---------
Co-authored-by: Devis Lucato <[email protected]>
Co-authored-by: Devis Lucato <[email protected]>
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
I built support for function calling into SK!
Related to/fixes:
- #2315
- #2175
- #1450
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
This implementation builds on top of all the existing pieces, but did
require some major work, so feel free to comment on where that is or is
not appropriate.
- Added a `ChatMessage` class to capture the relevant pieces of function
calling (name and content)
- Added a `complete_chat_with_functions_async` into
OpenAIChatCompletions class
- Added a `function_call` field to ChatRequestSettings class
- Added several helper functions and smaller changes
- Added a sample with updated core_skill that uses function calling to
demonstrate
- Added a second sample that shows how to use function_calling with
non-sk functions.
### 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: Abby Harrison <[email protected]>
### 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.
-->
Allow ActionPlanner to exclude skills and functions when generating the
plan. This is very useful and other planner types all have this
functionality.
Solve #3072
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
- Add `ActionPlannerConfig` class for three settings:
- `excluded_skills`
- `excluded_functions`
- `max_tokens`
- Filter out available skills and functions in
`ActionPlanner.list_of_functions` method.
- Rename class attribute "ActionPlanner._skill_name" to
"ActionPlanner.RESTRICTED_SKILL_NAME" just like other planners and
update its value to "ActionPlanner". The `this.*` skills defined in
`skprompt.txt` must also be updated.
- Add the missing `__init__.py`:
`semantic_kernel/planning/action_planner/__init__.py`
### 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: Dmytro Struk <[email protected]>
### Motivation and Context
Resolves: #2591
<!-- 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! -->
* Added in the `MongoDBAtlasMemoryStore`. A memory store abstraction
that facilitates connections between a MongoDB Atlas cluster to conduct
[Atlas Vector
Search](https://www.mongodb.com/products/platform/atlas-vector-search)
on the Microsoft Semantic Kernel.
* Leverages our async python driver
[motor](https://motor.readthedocs.io/en/stable/) to keep with the
heuristic of asynchronous code
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄
### Callout
* When writing my test, I noticed there's a habit of other tests
conducting a `try` on imports. Grepping through those implementations, I
see some of them [encapsulate their respective libraries in function
calls rather than doing direct imports in the
module.](https://github.com/microsoft/semantic-kernel/blob/main/python/semantic_kernel/connectors/memory/chroma/chroma_memory_store.py#L55-L63)
Is this the general code pattern we should follow? Or is it fine to have
our imports at the top of the module fine?
---------
Co-authored-by: Steven Silvester <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
### 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 solves [this
issue](https://github.com/microsoft/semantic-kernel/issues/1069) where
native functions are not returning the expected result. In python,
return typehints are optional. However, the semantic kernel requires a
return typehint to determine how to handle the function. For that
reason, we're now enforcing return typehints and raising an exception
when one is not provided. This may break existing void functions but
none in our repo are affected.
Fixes#1069
### 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 😄
## Summary
This pull request includes two sets of changes. First, it fixes the
return type annotations in three core skills: file_io_skill,
text_memory_skill, and wait_skill. Specifically, the write_async method
in file_io_skill and the save_async method in text_memory_skill now have
a return type of None, and the wait method in wait_skill now has a
return type of None. Additionally, the
import_native_skill_from_directory method in kernel.py has been
refactored to simplify the code. Second, this pull request adds error
handling for functions with no return type in the delegate inference
module. Previously, if a function did not specify a return type, the
DelegateType could not be inferred, leading to errors. This pull request
adds a check for functions with no return type and raises a
KernelException with an appropriate error message. Additionally, this
pull request includes some minor changes to unit tests for native
functions.
## Changes
- Fixed return type annotation for write_async method in file_io_skill
- Fixed return type annotation for save_async method in
text_memory_skill
- Fixed return type annotation for wait method in wait_skill
- Refactored import_native_skill_from_directory method in kernel.py
- Added error handling for functions with no return type in the delegate
inference module
- Added a check for functions with no return type and raised a
KernelException with an appropriate error message
- Made minor changes to unit tests for native functions
---
*Powered by [Microsoft Semantic
Kernel](https://github.com/microsoft/semantic-kernel)*
### Motivation and Context
This PR parallels work done in .NET for
https://github.com/microsoft/semantic-kernel/pull/2671 and closes
https://github.com/microsoft/semantic-kernel/issues/2722.
This PR allows users to set the chat system message using the semantic
function prompt template.
### Description
* added new `chat_system_message` parameter to
`complete_request_setttings` (defaults to None) and
`chat_request_settings `(defults to "Assistant is a large language
model.")
* added handling of this new parameter to the `chat_prompt_template`
* added corresponding tests
* added a small helper function for deserializing prompt_configs - token
selection biases need to be deserialized to ints, otherwise json loads
deserializes the keys in the set to be strings.
Unrelated
* added missing __init__ file to the weaviate connector's directory
### 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
The python integration tests use the public redis docker image. This
image is not available to our macOS and windows test agents. This PR
ensures that the tests are skipped on non-linux platforms (CI only).
### 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
<!-- 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.
-->
Noticed that another commonly edited environment setting for api_version
was missing from the settings util. And want to pass the env to the
constructor.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Added api_version to the settings util so that that can be controlled
through .env as well.
Added convenience function that outputs a dict that can be passed
directly into Completion constructors.
Updated sample to use that.
### 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#dev-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
---------
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Lee Miller <[email protected]>
### 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. .NET supports Redis memory while Python does not
2. Match up Python features w/ .NET
3. Users can utilize a Redis backend for memories
4. Closes#1981
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
Implemented a memory connector for Redis and made unit tests for it.
Also added .env configuration for a connection string.
### 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#dev-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: Dmytro Struk <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
### Motivation and Context
<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
1. Why is this change required?
2. What problem does it solve?
3. What scenario does it contribute to?
4. If it fixes an open issue, please link to the issue here.
-->
I was trying to use this library to load and use [HF Falcon
model](https://huggingface.co/tiiuae/falcon-7b-instruct). Unfortunately
in order to make it work I needed to pass in some additional arguments
such as `torch_dtype`, `cache_dir` or `tokenizer`. It was not possible
with current implementation so I decided to add `model_kwargs` and
`pipeline_kwargs` to the `HuggingFaceTextCompletion` class init function
so now, with the changes I introduced I can successfully load any
`falcon` models by using this code:
```python
import semantic_kernel as sk
import semantic_kernel.connectors.ai.hugging_face as sk_hf
import torch
from transformers import AutoTokenizer
cache_dir = "/mnt/tmp"
model_name = "tiiuae/falcon-7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(
pretrained_model_name_or_path=model_name,
cache_dir=cache_dir,
trust_remote_code=True)
hf_model = sk_hf.HuggingFaceTextCompletion(
model_name,
task="text-generation",
model_kwargs={
"cache_dir": cache_dir,
"torch_dtype": torch.bfloat16
},
pipeline_kwargs={
"tokenizer": tokenizer,
"trust_remote_code": True,
"device": 0,
}
)
```
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
The changes I introduced add `model_kwargs` and `pipeline_kwargs` to
`HuggingFaceTextCompletion` class so that these arguments are then
passed to the underlying `transformers.pipeline()` function and thus
allow more customization options.
### 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: Abby Harrison <[email protected]>
SKFunction has been excluded for now.
Handles issues arising due to many circular imports Update
DelegateInference to handle some cases where annotation is given as a
string to avoid circular imports like in FileIOSkill.
### 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: -->
- [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: Abby Harrison <[email protected]>
Co-authored-by: Mark Karle <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Lee Miller <[email protected]>
Co-authored-by: Devis Lucato <[email protected]>
### Motivation and Context
The integration of [USearch](https://github.com/unum-cloud/usearch) as a
memory connector to Semantic Kernel (SK).
### Description
The USearch `Index` does not natively have the ability to store
different collections, and it only stores embeddings without other
attributes like `MemoryRecord`.
The `USearchMemoryStore` class encapsulates these capabilities. It uses
the USearch `Index` to store a collection of embeddings under unique
IDs, with original collection names mapped to those IDs. Other
`MemoryRecord ` attributes are stored in a `pyarrow.Table`, which is
mapped to each collection.
It's important to note the current behavior when a user removes a record
or upserts a new one with an existing ID: the old row is not removed
from the `pyarrow.Table`. This is done for performance reasons but could
lead to the table growing in size.
By default, `USearchMemoryStore` operates as an in-memory store. To
enable persistence, you must set the persist mode with calling
appropriate `__init__ `, supplying a path to the directory for the
persist files. For each collection, two files will be created:
`{collection_name}.usearch` and `{collection_name}.parquet`. Changes
will only be dumped to the disk when `close_async` is called. Due to the
interface provided by the base class `MemoryStoreBase`, this happens
implicitly when using a context manager, or it may be called explicitly.
Since collection names are used to store files on disk, all names are
converted to lowercase.
To ensure efficient use of memory, you should call `close_async`.
---------
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Devis Lucato <[email protected]>
### 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.
-->
solve #2321
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
---------
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Lee Miller <[email protected]>
### 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.
-->
implement stepwise planner #2221
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
---------
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Lee Miller <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
Fix failing integration tests introduced in #2474 (May be filing follow
up issue on that)
- Update WriterSkillFake to include a context parameter for the end
marker
- Update test_sequential_planner to use the new end marker parameter in
WriterSkillFake
### 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
Implementation of Google PaLM connector with chat completion, text
embedding and three example files to demonstrate their functionality.
Closes#2098
I also opened a PR for text completion #2076
<!-- 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
**What's new:**
1. Implemented Google Palm connector with chat completion and text
embedding
2. Added 3 example files to `python/samples/kernel-syntax-examples`
3. The example files show PaLM chat in action with skills, memory, and
just with user messages. The memory example uses PaLM embedding as well
5. Added integration tests to test chat with skills and embedding with
kernel.memory functions
6. Added unit tests to verify successful class initialization and
correct behavior from class functions
**There are some important differences between google palm chat and open
ai chat:**
1. PaLM has two functions for chatting, `chat` and `reply`. The chat
function in google's genai library starts a new conversation, and reply
continues the conversation. Reply is an attribute of the response object
returned by chat. So an instance of the `GooglePalmChatCompletion` class
needs a way to determine which function to use, which is why I
introduced a private attribute to store the response object. See
https://developers.generativeai.google/api/python/google/generativeai/types/ChatResponse
2. PaLM does not use system messages. Instead, the chat function takes a
parameter called context. It serves the same purpose, to prime the
assistant with certain behaviors and information. So when the user
passes a system message to `complete_chat_async`, it is passed to `chat`
as the context parameter.
3. Semantic memory works with the chat service as long as the user
creates a chat prompt template. The prompt containing the memory needs
to be added to the chat prompt template as a system message. See
`python\samples\kernel-syntax-examples\google_palm_chat_with_memory.py`
for more details. If the only purpose of `complete_async` in
`GooglePalmChatCompletion` is to send memories + user messages to the
chat service as a text prompt, then `complete_async` is not fulfilling
its intended purpose. A possible solution would be to send the text
prompt as a request to the text service within `complete_async`.
<!-- 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 😄
Currently no warnings, there was 1 warning when first installing genai
with `poetry add google.generativeai==v0.1.0rc2` from within poetry
shell: "The locked version 0.1.0rc2 for google-generativeai is a yanked
version. Reason for being yanked: Release is marked as supporting Py3.8,
but in practice it requires 3.9". We would need to require later
versions of python to fix it.
---------
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
Co-authored-by: Abby Harrison <[email protected]>
### 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.
-->
solve #2473 and add unit test to prevent this from happening again.
### Description
<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
### Contribution Checklist
<!-- Before submitting this PR, please make sure: -->
- [ ] The code builds clean without any errors or warnings
- [ ] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄
---------
Co-authored-by: Abby Harrison <[email protected]>
