mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-28 03:12:54 +00:00
a59bca3661
* Testing black on ui/ * Applying black on docstores * Add latest docstring and tutorial changes * Create a single GH action for Black and docs to reduce commit noise to the minimum, slightly refactor the OpenAPI action too * Remove comments * Relax constraints on pydoc-markdown * Split temporary black from the docs. Pydoc-markdown was obsolete and needs a separate PR to upgrade * Fix a couple of bugs * Add a type: ignore that was missing somehow * Give path to black * Apply Black * Apply Black * Relocate a couple of type: ignore * Update documentation * Make Linux CI run after applying Black * Triggering Black * Apply Black * Remove dependency, does not work well * Remove manually double trailing commas * Update documentation Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
86 lines
3.8 KiB
Python
86 lines
3.8 KiB
Python
import pytest
|
|
|
|
from haystack.pipelines import TranslationWrapperPipeline, ExtractiveQAPipeline
|
|
|
|
from haystack.schema import Answer
|
|
|
|
|
|
@pytest.mark.slow
|
|
@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.slow
|
|
@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 <= 11
|
|
assert prediction["answers"][0].score >= 10
|
|
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.slow
|
|
@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
|
|
|
|
|
|
@pytest.mark.slow
|
|
@pytest.mark.parametrize("retriever_with_docs", ["tfidf"], indirect=True)
|
|
def test_extractive_qa_answers_with_translator(reader, retriever_with_docs, en_to_de_translator, de_to_en_translator):
|
|
base_pipeline = ExtractiveQAPipeline(reader=reader, retriever=retriever_with_docs)
|
|
pipeline = TranslationWrapperPipeline(
|
|
input_translator=de_to_en_translator,
|
|
output_translator=en_to_de_translator,
|
|
pipeline=base_pipeline,
|
|
)
|
|
|
|
prediction = pipeline.run(query="Wer lebt in Berlin?", params={"Reader": {"top_k": 3}})
|
|
assert prediction is not None
|
|
assert prediction["query"] == "Wer lebt in Berlin?"
|
|
assert "Carla" in prediction["answers"][0].answer
|
|
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"
|