David S. Batista

Is there already a draft or any previously discussed ideas or proposals/suggestions on how this would be implemented?

I've tried to define some more formal requirements and draft a first proposal on how to implement them. https://www.notion.so/deepsetai/Implementing-Breakpoints-in-Haystack-Pipelines-1b3e210b37c4805c8ab1c03bfcdf6c3f

@tstadel thanks a lot for this!

Hey @aymbot! Thanks for your feedback :) We are eager to get any feedback and use cases for the breakpoints! > I was thinking of using it to snapshot pipelines...

> It's not applicable in production because the output should also be serializable (i.e. passed as ByteStream). The breakpoints produce serialisable pipeline states, as JSON objects, which you can encode...

I think the score should be excluded from this comparison, since the score is not part of the document itself, it's associated with the retrieval process.

In the context of Information Retrieval, my point is that document content and document score derived from a retrieval process are two completely distinct aspects, and it seems that Sebastian...

@sjrl not sure about this but looking at the type definition of `Variadic` it seems it doesn't support `str` [here](https://github.com/deepset-ai/haystack/blob/main/haystack/core/component/types.py#L10) ```python HAYSTACK_VARIADIC_ANNOTATION = "__haystack__variadic_t" # # Generic type variable used...

@sjrl have a look at this sample/testing code: https://github.com/deepset-ai/haystack/blob/main/haystack/testing/sample_components/joiner.py I think what you want might already be there

I've just tried the `StringJoiner` from the link I sent you get the same error as with your code