How pipeline handles custom pre-processing or post-processing. For example, different doc_stride, max_seq_length in Question Answering?
I dont think that is possible. But lets hear from someone experienced.
Hi @s4sarath
it’s possible to pass different doc_stride
, max_seq_length
etc directly to the __call__
method, i.e when calling the pipeline, have a look at the docstring of __call__
of QA pipeline here
Agree. But I am asking more of like a custom preprocessing. Let’s say I want to add token type I’d 2 to question and 0s to context .
In that case, you could subclass the pipeline to add the custom behavior.
1 Like
That’s what I was looking for .