Functional tests for Semantic Kernel

Azure-Samples / chat-with-your-data-solution-accelerator

A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.

https://azure.microsoft.com/products/search

MIT License

521 stars 274 forks source link

Functional tests for Semantic Kernel #800

Closed cecheta closed 2 weeks ago

cecheta commented 2 weeks ago

Closes #766

Purpose

Adds functional tests for semantic kernel

Does this introduce a breaking change?

[ ] Yes
[x] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[ ] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[x] Other... Please describe: Tests

How to Test

pytest -m functional

What to Check

Tests pass

github-actions[bot] commented 2 weeks ago

Coverage Report •

File	Stmts	Miss	Cover
code/backend/batch/utilities/helpers
ConfigHelper.py	115	0	100%
TOTAL	2216	763	65%

Tests	Skipped	Failures	Errors	Time
164	0 :zzz:	0 :x:	0 :fire:	10.262s :stopwatch:

superhindupur commented 2 weeks ago

@adamdougal, @cecheta and I had a discussion about the possibility of running the orchestrator tests for all three orchestrator types - langchain, openai_functions and semantic kernel, rather thn just for sematntic kernel.

But at the moment we're spinning up a new mock server instance for each config combination - making it hard to test lots of them. After discussing possible solutions, I opened an issue to solve this.