Nir Gazit
Nir Gazit
@dtee1 so when calling azure it may filter the response returned from the model if it contains harmful text, see https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new We should add attributes to the span according to...
Superseded by #1539
@dtee1 yes please :) let me know if you have any questions - you're welcome to join our [slack](https://traceloop.com/slack) as well.
@sukidesuka thanks for flagging! I was lazy and didn't test it properly for Azure. I've now added proper testing specifically for Azure and fixed the issue so this won't happen....
Sounds good @lauradowell! @dtee1, are you still on this?
Cool @gyliu513 would love your assistance here! Note that work on metrics have began with #251
Yes @gyliu513 I think that would be best.
Sure @PrashantDixit0 would love that! Let me know if I can assist you somehow here or on [slack](https://traceloop.com/slack)
@quest-bot stash 300