semantic-kernel

mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 02:19:06 +00:00

Files

T

Tao Chen 5476ac3acb Python: Update model diagnostics (#8346 )

### 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 a module that performs tracing for model invocations. However,
that module only works with OpenAI. We need it to work for all AI
connectors. This PR does the refactoring necessary for the module to
become more generic.

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->
1. Rename the tracing module to `model_diagnostics`.
2. Restructure and optimize code.
3. Add tracing to all AI connectors except the HuggingFace connector,
because the HuggingFace connector will need some refactoring in the near
future.

### 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 😄

2024-08-27 21:23:03 +00:00

telemetry

Python: Update model diagnostics (#8346 )

2024-08-27 21:23:03 +00:00

__init__.py

Python: further improvements to checks and docs in dev_setup (#6445 )

2024-05-31 13:06:41 +00:00

chat.py

Python: upgraded all files to 310 plus format and removed from future (#6353 )

2024-05-21 16:33:08 +00:00

experimental_decorator.py

Python: fix: Preserve class type in experimental_class decorator to avoid type inference issues (#6709 )