tstadel

@NThakur20 I'm happy to receive your comments about this draft. Let me know if moving `score_function` is too intrusive. I just thought it makes more sense to have it only...

Hey @NThakur20, sure. I'll submit a PR in the next days.

They seem to use multiple prediction heads which we have already implemented in `AdaptiveModel`. However they use an additional feedforward network to determine which prediction head should be used to...

> Looks good to me! 👍 Instead of just `token`, I'd find `use_auth_token` more consistent with the setting in PromptNode and in HFLocalInvocationLayer https://docs.haystack.deepset.ai/v1.26-unstable/reference/invocation-layers-api#hflocalinvocationlayer__init__ Ok, it's a bit weird in...

No, I haven't seen this so far. But afaik I haven't seen the usage of three retrievers either. I would suspect the problem somewhere here https://github.com/deepset-ai/haystack/blob/179e9cea08f00f25c785e371c4ca1b092837bb4c/haystack/pipelines/base.py#L580-L600 Looks like the else...