Handle content_filter errors during document indexing

[Allob]

DescriptionRetirever indexing uses gpt-4o-mini to get image descriptions. Some documents may trigger content filter error which will look like that in the stream:

{'error': {'inner_error': {'code': 'ResponsibleAIPolicyViolation', 'content_filter_results': {'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': True, 'severity': 'high'}, 'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}}}, 'code': 'content_filter', '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: \r\nhttps://go.microsoft.com/fwlink/?linkid=2198766.", 'param': 'prompt', 'type': None}}

The main indicator is code=content_filter.

Currently, such error will be reported to the UI as the following message:

I'm sorry, but I can't process the documents because of the following errors:
<document>: Internal error

Dial RAG should be able to detect such errors in the stream and show some user-friendly message.

[Allob]

Alternatively, the output stream can be terminated with finish_reason: content_filter and with not error message in the stream.