Python: Partial content filtering response in Python SDK #4197
Assignees
Labels
ai connector
Anything related to AI connectors
bug
Something isn't working
python
Pull requests for the Python Semantic Kernel
Comments
github-actions
bot
changed the title
|
Thanks for filing, @orsharab. How can I repro it on my end? |
|
@eavanvalkenburg we should chat about plans for proper error/exception handling. |
|
@juliomenendez if you have any bandwidth, could you please help take a look? |
4 tasks
|
@orsharab yes, the PR doesn't restrict what type of content filter is accepted. Jailbreak is handled in the |
github-merge-queue bot
pushed a commit
that referenced
this issue
Jan 4, 2024
…g is triggered (#4428) ### 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 <35585003+moonbox3@users.noreply.github.com>
|
@orsharab the changes have been merged and should go out in the next release. |
Bryan-Roe
pushed a commit
to Bryan-Roe-ai/semantic-kernel
that referenced
this issue
Oct 6, 2024
…g is triggered (microsoft#4428) ### 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 microsoft#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 <35585003+moonbox3@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Describe the bug
In Python SDK, when content filtering is triggered, the returned response is partial, missing "inner_error" property that indicates the reason of the content filtering:
'{"error":{"message":"The response was filtered due to the prompt triggering Azure OpenAI\'s content management policy. Please modify your prompt and retry. To learn more about our content filtering policies please read our documentation: [https://go.microsoft.com/fwlink/?linkid=2198766","type":null,"param":"prompt","code":"content_filter","status":400}](https://go.microsoft.com/fwlink/?linkid=2198766%22,%22type%22:null,%22param%22:%22prompt%22,%22code%22:%22content_filter%22,%22status%22:400%7d)}'See OpenAI API reference for "inner_error" property
Platform
Python SDK version - 0.3.15.dev0
The text was updated successfully, but these errors were encountered: