Haystack split_respect_sentence_boundary not supported with add_eval_data

[ali-issa9]

We are going to evaluate our pipeline on Haystack, and we set split_respect_sentence_boundary to be True inside our processor. But we are getting an error while we are setting this parameter to true inside add_eval_data

this is a copy of my code :

from haystack.nodes import PreProcessor

# Add evaluation data to Elasticsearch Document Store
# We first delete the custom tutorial indices to not have duplicate elements
# and also split our documents into shorter passages using the PreProcessor
preprocessor = PreProcessor(
    split_by="word",
    split_length=300,
    split_overlap=0,
    split_respect_sentence_boundary=True,
    clean_empty_lines=True,
    clean_whitespace=True,
)
document_store.delete_documents(index=doc_index)
document_store.delete_documents(index=label_index)

# The add_eval_data() method converts the given dataset in json format into Haystack document and label objects. Those objects are then indexed in their respective document and label index in the document store. The method can be used with any dataset in SQuAD format.
document_store.add_eval_data(
    filename="data/tutorial5/nq_dev_subset_v2.json",
    doc_index=doc_index,
    label_index=label_index,
    preprocessor=preprocessor,
)

[ZanSara]

Hello @ali-issa9, can you share the stacktrace as well?

[ali-issa9]

hello @ZanSara , what do you mean by stacktrace?

[ZanSara]

The output of your code, especially the error that you see when you run the code above