You must be thinking of a use case I am unable to anticipate 🙂 Can you elaborate?

Sometimes you want to generate attacks that include previous turns and then add new turns on top. The problem is if those previous turns were audio, and the new turn you want to add on top is based on a text prompt. Then you have a mix of audio & text together and when you have the convertor attached to the target all prompts go through the convertor leading to it throwing an error when it tries to convert the audio_file of the previous turns. You could account for this in the notebook at run time but its easier and cleaner to have the convertor handle this and just pass through things are already audio. I couldn't really see a downside to having this in the convertor but keen to know if you can think of a problem this may cause.

This is actually doable with the selective text converter + translation converter, see https://azure.github.io/PyRIT/code/converters/6_selectively_converting.html#example-7-applying-converters-to-different-parts

I do see the appeal of having a shortcut, though. Wdyt?

Yeah so I spent some time on this. My reasoning for having a separate convertor for this is:

1. Without digging into the docs a bit its not easy to see how to do this, type of splitting so its not easily discoverable
2. Implementing it in a notebook flow is a bit cumbersome, especially when you want to try a lot of different approaches. Having a convertor makes it cleaner and easier to implement but happy to change course if other disagree.
3. Baking the capability into the RandomTranslationConverter could be doable be would add a level of complexity to the convertor that I felt having a separate one made sense from a maintainability point of view but very happy to take guidance on this.

I'm wondering if we could do something like:

1. Wrap the splitting and chaining logic in something like SequenceLevelConverter (effectively a generalized version of WordLevelConverter)
2. Merge MultiLanguageTranslationConverter and RandomTranslationConverter, maybe inheriting this new SequenceLevelConverter, supporting both fixed/random language selection, and sequence/word splitting.

nit:

does it matter at all that all of these are going to be part of a different conversation?

is there an upper bound ?

should info be assigned here ? what happens on line 80 if it's not ?