mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-08-04 06:38:34 +00:00
165a0a5faa
* mock all translator tests and move one to e2e * typo * extract pipeline tests using translator * remove duplicate test * move generator test in e2e * Update e2e/pipelines/test_extractive_qa.py * pytest.mark.unit * black * remove model name as well * remove unused fixture * rename original and improve pipeline tests * fixes * pylint
63 lines
2.8 KiB
Python
63 lines
2.8 KiB
Python
import pytest
|
|
|
|
from haystack.pipelines import TranslationWrapperPipeline, ExtractiveQAPipeline
|
|
|
|
from haystack.schema import Answer
|
|
|
|
|
|
@pytest.mark.integration
|
|
@pytest.mark.parametrize("retriever_with_docs", ["tfidf"], indirect=True)
|
|
def test_extractive_qa_answers(reader, retriever_with_docs, document_store_with_docs):
|
|
pipeline = ExtractiveQAPipeline(reader=reader, retriever=retriever_with_docs)
|
|
prediction = pipeline.run(query="Who lives in Berlin?", params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 3}})
|
|
assert prediction is not None
|
|
assert type(prediction["answers"][0]) == Answer
|
|
assert prediction["query"] == "Who lives in Berlin?"
|
|
assert prediction["answers"][0].answer == "Carla"
|
|
assert prediction["answers"][0].score <= 1
|
|
assert prediction["answers"][0].score >= 0
|
|
assert prediction["answers"][0].meta["meta_field"] == "test1"
|
|
assert prediction["answers"][0].context == "My name is Carla and I live in Berlin"
|
|
|
|
assert len(prediction["answers"]) == 3
|
|
|
|
|
|
@pytest.mark.integration
|
|
@pytest.mark.parametrize("retriever_with_docs", ["tfidf"], indirect=True)
|
|
def test_extractive_qa_answers_without_normalized_scores(reader_without_normalized_scores, retriever_with_docs):
|
|
pipeline = ExtractiveQAPipeline(reader=reader_without_normalized_scores, retriever=retriever_with_docs)
|
|
prediction = pipeline.run(query="Who lives in Berlin?", params={"Reader": {"top_k": 3}})
|
|
assert prediction is not None
|
|
assert prediction["query"] == "Who lives in Berlin?"
|
|
assert prediction["answers"][0].answer == "Carla"
|
|
assert prediction["answers"][0].score <= 9
|
|
assert prediction["answers"][0].score >= 8
|
|
assert prediction["answers"][0].meta["meta_field"] == "test1"
|
|
assert prediction["answers"][0].context == "My name is Carla and I live in Berlin"
|
|
|
|
assert len(prediction["answers"]) == 3
|
|
|
|
|
|
@pytest.mark.parametrize("retriever_with_docs", ["tfidf"], indirect=True)
|
|
def test_extractive_qa_offsets(reader, retriever_with_docs):
|
|
pipeline = ExtractiveQAPipeline(reader=reader, retriever=retriever_with_docs)
|
|
prediction = pipeline.run(query="Who lives in Berlin?", params={"Retriever": {"top_k": 5}})
|
|
|
|
start = prediction["answers"][0].offsets_in_context[0].start
|
|
end = prediction["answers"][0].offsets_in_context[0].end
|
|
|
|
assert start == 11
|
|
assert end == 16
|
|
|
|
assert prediction["answers"][0].context[start:end] == prediction["answers"][0].answer
|
|
|
|
|
|
@pytest.mark.integration
|
|
@pytest.mark.parametrize("retriever_with_docs", ["tfidf"], indirect=True)
|
|
def test_extractive_qa_answers_single_result(reader, retriever_with_docs):
|
|
pipeline = ExtractiveQAPipeline(reader=reader, retriever=retriever_with_docs)
|
|
query = "testing finder"
|
|
prediction = pipeline.run(query=query, params={"Retriever": {"top_k": 1}, "Reader": {"top_k": 1}})
|
|
assert prediction is not None
|
|
assert len(prediction["answers"]) == 1
|