### Motivation and Context
The release of Python SK from 0.2.4 -> 0.2.6 significantly increased the
size of the pip package. The dependencies causing this are not core to
the kernel, so this PR establishes a pattern for SK connector
dependencies (ex: Hugging Face, memory storage)
### Description
- Added a poetry group called hugging_face - this is the same name as
the connectors namespace in the code.
- Added dependency installs to the Hugging Face sample notebook.
- removed Hugging Face dependencies from requirements.txt.
- Added import errors for torch, transformers, and sentence-transformers
in the hugging_face connector classes.
- Added command `--with hugging_face` to integration test setup.
### Motivation and Context
Run python integration tests on every push to main, and every 12 hours.
These integration tests will run on every push to main as well as twice
a day. At the time of this PR, we are seeing ~3 PRs to the python SK per
day. Each Integration test run will make ~32 AI requests. For each PR,
12 runs will be made: 3 each for python 3.8, 3.9, 3.10, and 3.11 for a
total of ~400 calls per push to main.
We should re-evaluate the trigger on pushes to main if PRs to the python
SK significantly increase.
### Description
- add workflow definition for integration tests
- Example run:
https://github.com/microsoft/semantic-kernel/actions/runs/4874609026/jobs/8695771345?pr=763
- For push triggers, add path checks for dotnet/** or python/**
depending on the type of workflow
- pinned requirements.txt dependencies to the versions pinned in the
pyproject.toml file to ensure parity between pip package dependencies
and local code
**Note**: Integration tests are failing on windows with python 3.8 -
already captured a task to address the problem
### Motivation and Context
This PR introduces the ability to run formal integration tests for
python using pytest - separated from unit tests for easier automation.
### Description
- moved `python/tests/end-to-end` directory to
`python/tests/integration`
- renamed integration tests to test_* pattern so pytest will detect them
- import `GenerationConfig` for hugging face completions - according to
logs, this is the recommended practice
### Motivation and Context
This PR makes creating a kernel instance more pythonic. The builder
pattern is removed and the kernel is constructed using Kernel(...).
Work originally started with #137
### Description
- Removed kernel_builder.py.
- Instance creation pattern `kernel = sk.create_kernel() -> kernel =
sk.Kernel()`
- For notebook 6, there is no need to create a separate kernel for the
GitHub files. Changed to use a separate collection.
Co-authored-by: Devis Lucato <[email protected]>
### Motivation and Context
New features:
* AAD auth for Azure OpenAI
* Azure ChatGPT
* Completion streaming
* Chat streaming
* log probs
### Description
* Split kernel core nuget in 3 nugets and add dependency on Azure OpenAI
SDK:
* MS.SK.Abstractions: interfaces and common classes, ideally no business
logic
* MS.SK: SK runtime, depends on SK.Abstractions
* MS.SK.Connectors.AI.OpenAI: OpenAI/Azure OpenAI code, depends on
SK.Abstractions and Azure OpenAI SDK
* Rewrote TextCompletion, ChatCompletion, EmbeddingGeneration clients to
use Azure OpenAI SDK
* Deleted unused code. The old OpenAI client is still in use only for
DALL-E2
Note: custom retry logic doesn't work with Azure OpenAI SDK. The SDK
already retries internally, using a different approach.
Nugets:
* Microsoft.SemanticKernel.0.12.0.nupkg
* **Microsoft.SemanticKernel.Abstractions.0.12.0.nupkg**
* **Microsoft.SemanticKernel.Connectors.AI.OpenAI.0.12.0.nupkg**
* Microsoft.SemanticKernel.Connectors.Memory.Qdrant.0.12.0.nupkg
* Microsoft.SemanticKernel.Connectors.Memory.Sqlite.0.12.0.nupkg
* Microsoft.SemanticKernel.Skills.MsGraph.0.12.0.nupkg
* Microsoft.SemanticKernel.Skills.Document.0.12.0.nupkg
* Microsoft.SemanticKernel.Skills.OpenAPI.0.12.0.nupkg
* Microsoft.SemanticKernel.Skills.Web.0.12.0.nupkg
Abby Harrison