mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-27 19:00:35 +00:00
54518ac790
* Refactor document fixtures * Add embedding files * Update Documentation & Code Style * Indentation issue * Update Documentation & Code Style * Fix type conversion in conftest.py * Update Documentation & Code Style * mypy on sql.py * mypy on crawler.py * mypy on pinecone.py * Adapt retriever tests * Update Documentation & Code Style * mypy on crawler.py * Update Documentation & Code Style * mypy on crawler.py again * Update Documentation & Code Style * mypy fix was too rough * Fix some more tests * Update Documentation & Code Style * Skip meaningless test on FilterRetriever * Make embedding values less specific * Update Documentation & Code Style * Use stable IDs in retriever tests that depend on it * Remove needless fixtures * docs_with_ids * Update Documentation & Code Style * Typo * Fix retriever tests * Fix reader tests * Update Documentation & Code Style * Workaround #2626 * Update Documentation & Code Style * Fix label generator tests * Reorder vectors * remove print * Update Documentation & Code Style * Update Documentation & Code Style * git tags leftover * Update Documentation & Code Style * fix last failing test Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
58 lines
1.9 KiB
Python
58 lines
1.9 KiB
Python
import pytest
|
|
import pandas as pd
|
|
|
|
from haystack import Document, Answer
|
|
from haystack.nodes.other.route_documents import RouteDocuments
|
|
from haystack.nodes.other.join_answers import JoinAnswers
|
|
|
|
|
|
#
|
|
# RouteDocuments tests
|
|
#
|
|
|
|
|
|
def test_routedocuments_by_content_type():
|
|
docs = [
|
|
Document(content="text document", content_type="text"),
|
|
Document(
|
|
content=pd.DataFrame(columns=["col 1", "col 2"], data=[["row 1", "row 1"], ["row 2", "row 2"]]),
|
|
content_type="table",
|
|
),
|
|
]
|
|
route_documents = RouteDocuments()
|
|
result, _ = route_documents.run(documents=docs)
|
|
assert len(result["output_1"]) == 1
|
|
assert len(result["output_2"]) == 1
|
|
assert result["output_1"][0].content_type == "text"
|
|
assert result["output_2"][0].content_type == "table"
|
|
|
|
|
|
def test_routedocuments_by_metafield(docs):
|
|
route_documents = RouteDocuments(split_by="meta_field", metadata_values=["test1", "test3", "test5"])
|
|
result, _ = route_documents.run(docs)
|
|
assert len(result["output_1"]) == 1
|
|
assert len(result["output_2"]) == 1
|
|
assert len(result["output_3"]) == 1
|
|
assert result["output_1"][0].meta["meta_field"] == "test1"
|
|
assert result["output_2"][0].meta["meta_field"] == "test3"
|
|
assert result["output_3"][0].meta["meta_field"] == "test5"
|
|
|
|
|
|
#
|
|
# JoinAnswers tests
|
|
#
|
|
|
|
|
|
@pytest.mark.parametrize("join_mode", ["concatenate", "merge"])
|
|
def test_joinanswers(join_mode):
|
|
inputs = [{"answers": [Answer(answer="answer 1", score=0.7)]}, {"answers": [Answer(answer="answer 2", score=0.8)]}]
|
|
|
|
join_answers = JoinAnswers(join_mode=join_mode)
|
|
result, _ = join_answers.run(inputs)
|
|
assert len(result["answers"]) == 2
|
|
assert result["answers"] == sorted(result["answers"], reverse=True)
|
|
|
|
result, _ = join_answers.run(inputs, top_k_join=1)
|
|
assert len(result["answers"]) == 1
|
|
assert result["answers"][0].answer == "answer 2"
|