mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-27 10:49:52 +00:00
dde9d59271
* fix pip backtracking issue * restrict azure-core version * Remove the trailing comma * Add skip_magic_trailing_comma in pyproject.toml for pydoc compatibility * Pin pydoc-markdown _again_ Co-authored-by: Sara Zan <sarazanzo94@gmail.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
47 lines
1.9 KiB
Python
47 lines
1.9 KiB
Python
import pytest
|
|
|
|
from haystack.nodes.retriever.sparse import ElasticsearchRetriever
|
|
from haystack.nodes.reader import FARMReader
|
|
from haystack.pipelines import Pipeline
|
|
|
|
from haystack.nodes.extractor import EntityExtractor, simplify_ner_for_qa
|
|
|
|
|
|
@pytest.mark.parametrize("document_store_with_docs", ["elasticsearch"], indirect=True)
|
|
def test_extractor(document_store_with_docs):
|
|
|
|
es_retriever = ElasticsearchRetriever(document_store=document_store_with_docs)
|
|
ner = EntityExtractor()
|
|
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", num_processes=0)
|
|
|
|
pipeline = Pipeline()
|
|
pipeline.add_node(component=es_retriever, name="ESRetriever", inputs=["Query"])
|
|
pipeline.add_node(component=ner, name="NER", inputs=["ESRetriever"])
|
|
pipeline.add_node(component=reader, name="Reader", inputs=["NER"])
|
|
|
|
prediction = pipeline.run(
|
|
query="Who lives in Berlin?", params={"ESRetriever": {"top_k": 1}, "Reader": {"top_k": 1}}
|
|
)
|
|
entities = [entity["word"] for entity in prediction["answers"][0].meta["entities"]]
|
|
assert "Carla" in entities
|
|
assert "Berlin" in entities
|
|
|
|
|
|
@pytest.mark.parametrize("document_store_with_docs", ["elasticsearch"], indirect=True)
|
|
def test_extractor_output_simplifier(document_store_with_docs):
|
|
|
|
es_retriever = ElasticsearchRetriever(document_store=document_store_with_docs)
|
|
ner = EntityExtractor()
|
|
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", num_processes=0)
|
|
|
|
pipeline = Pipeline()
|
|
pipeline.add_node(component=es_retriever, name="ESRetriever", inputs=["Query"])
|
|
pipeline.add_node(component=ner, name="NER", inputs=["ESRetriever"])
|
|
pipeline.add_node(component=reader, name="Reader", inputs=["NER"])
|
|
|
|
prediction = pipeline.run(
|
|
query="Who lives in Berlin?", params={"ESRetriever": {"top_k": 1}, "Reader": {"top_k": 1}}
|
|
)
|
|
simplified = simplify_ner_for_qa(prediction)
|
|
assert simplified[0] == {"answer": "Carla", "entities": ["Carla"]}
|