mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-28 19:29:40 +00:00

* first draft / notes on new primitives * wip label / feedback refactor * rename doc.text -> doc.content. add doc.content_type * add datatype for content * remove faq_question_field from ES and weaviate. rename text_field -> content_field in docstores. update tutorials for content field * update converters for . Add warning for empty * renam label.question -> label.query. Allow sorting of Answers. * WIP primitives * update ui/reader for new Answer format * Improve Label. First refactoring of MultiLabel. Adjust eval code * fixed workflow conflict with introducing new one (#1472) * Add latest docstring and tutorial changes * make add_eval_data() work again * fix reader formats. WIP fix _extract_docs_and_labels_from_dict * fix test reader * Add latest docstring and tutorial changes * fix another test case for reader * fix mypy in farm reader.eval() * fix mypy in farm reader.eval() * WIP ORM refactor * Add latest docstring and tutorial changes * fix mypy weaviate * make label and multilabel dataclasses * bump mypy env in CI to python 3.8 * WIP refactor Label ORM * WIP refactor Label ORM * simplify tests for individual doc stores * WIP refactoring markers of tests * test alternative approach for tests with existing parametrization * WIP refactor ORMs * fix skip logic of already parametrized tests * fix weaviate behaviour in tests - not parametrizing it in our general test cases. * Add latest docstring and tutorial changes * fix some tests * remove sql from document_store_types * fix markers for generator and pipeline test * remove inmemory marker * remove unneeded elasticsearch markers * add dataclasses-json dependency. adjust ORM to just store JSON repr * ignore type as dataclasses_json seems to miss functionality here * update readme and contributing.md * update contributing * adjust example * fix duplicate doc handling for custom index * Add latest docstring and tutorial changes * fix some ORM issues. fix get_all_labels_aggregated. * update drop flags where get_all_labels_aggregated() was used before * Add latest docstring and tutorial changes * add to_json(). add + fix tests * fix no_answer handling in label / multilabel * fix duplicate docs in memory doc store. change primary key for sql doc table * fix mypy issues * fix mypy issues * haystack/retriever/base.py * fix test_write_document_meta[elastic] * fix test_elasticsearch_custom_fields * fix test_labels[elastic] * fix crawler * fix converter * fix docx converter * fix preprocessor * fix test_utils * fix tfidf retriever. fix selection of docstore in tests with multiple fixtures / parameterizations * Add latest docstring and tutorial changes * fix crawler test. fix ocrconverter attribute * fix test_elasticsearch_custom_query * fix generator pipeline * fix ocr converter * fix ragenerator * Add latest docstring and tutorial changes * fix test_load_and_save_yaml for elasticsearch * fixes for pipeline tests * fix faq pipeline * fix pipeline tests * Add latest docstring and tutorial changes * fix weaviate * Add latest docstring and tutorial changes * trigger CI * satisfy mypy * Add latest docstring and tutorial changes * satisfy mypy * Add latest docstring and tutorial changes * trigger CI * fix question generation test * fix ray. fix Q-generation * fix translator test * satisfy mypy * wip refactor feedback rest api * fix rest api feedback endpoint * fix doc classifier * remove relation of Labels -> Docs in SQL ORM * fix faiss/milvus tests * fix doc classifier test * fix eval test * fixing eval issues * Add latest docstring and tutorial changes * fix mypy * WIP replace dataclasses-json with manual serialization * Add latest docstring and tutorial changes * revert to dataclass-json serialization for now. remove debug prints. * update docstrings * fix extractor. fix Answer Span init * fix api test * keep meta data of answers in reader.run() * fix meta handling * adress review feedback * Add latest docstring and tutorial changes * make document=None for open domain labels * add import * fix print utils * fix rest api * adress review feedback * Add latest docstring and tutorial changes * fix mypy Co-authored-by: Markus Paff <markuspaff.mp@gmail.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
57 lines
2.0 KiB
Python
57 lines
2.0 KiB
Python
import pytest
|
|
|
|
from haystack.retriever.sparse import ElasticsearchRetriever
|
|
from haystack.reader import FARMReader
|
|
from haystack.pipeline import Pipeline
|
|
|
|
from haystack.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")
|
|
|
|
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")
|
|
|
|
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"]
|
|
} |