mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-30 12:22:52 +00:00
59608ca474
* Unify CI tests (from #2466) * Update Documentation & Code Style * Change folder names * Fix markers list * Remove marker 'slow', replaced with 'integration' * Soften children check * Start ES first so it has time to boot while Python is setup * Run the full workflow * Try to make pip upgrade on Windows * Set KG tests as integration * Update Documentation & Code Style * typo * faster pylint * Make Pylint use the cache * filter diff files for pylint * debug pylint statement * revert pylint changes * Remove path from asserted log (fails on Windows) * Skip preprocessor test on Windows * Tackling Windows specific failures * Fix pytest command for windows suites * Remove \ from command * Move poppler test into integration * Skip opensearch test on windows * Add tolerance in reader sas score for Windows * Another pytorch approx * Raise time limit for unit tests :( * Skip poppler test on Windows CI * Specify to pull with FF only in docs check * temporarily run the docs check immediately * Allow merge commit for now * Try without fetch depth * Accelerating test * Accelerating test * Add repository and ref alongside fetch-depth * Separate out code&docs check from tests * Use setup-python cache * Delete custom action * Remove the pull step in the docs check, will find a way to run on bot commits * Add requirements.txt in .github for caching * Actually install dependencies * Change deps group for pylint * Unclear why the requirements.txt is still required :/ * Fix the code check python setup * Install all deps for pylint * Make the autoformat check depend on tests and doc updates workflows * Try installing dependencies in another order * Try again to install the deps * quoting the paths * Ad back the requirements * Try again to install rest_api and ui * Change deps group * Duplicate haystack install line * See if the cache is the problem * Disable also in mypy, who knows * split the install step * Split install step everywhere * Revert "Separate out code&docs check from tests" This reverts commit 1cd59b15ffc5b984e1d642dcbf4c8ccc2bb6c9bd. * Add back the action * Proactive support for audio (see text2speech branch) * Fix label generator tests * Remove install of libsndfile1 on win temporarily * exclude audio tests on win * install ffmpeg for integration tests Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
63 lines
2.4 KiB
Python
63 lines
2.4 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from haystack.nodes import QuestionGenerator, EmbeddingRetriever, PseudoLabelGenerator
|
|
from test.conftest import DOCS_WITH_EMBEDDINGS
|
|
|
|
|
|
@pytest.mark.generator
|
|
@pytest.mark.integration
|
|
@pytest.mark.parametrize("document_store", ["memory"], indirect=True)
|
|
@pytest.mark.parametrize("retriever", ["embedding_sbert"], indirect=True)
|
|
def test_pseudo_label_generator(
|
|
document_store, retriever: EmbeddingRetriever, question_generator: QuestionGenerator, tmp_path: Path
|
|
):
|
|
document_store.write_documents(DOCS_WITH_EMBEDDINGS)
|
|
psg = PseudoLabelGenerator(question_generator, retriever)
|
|
train_examples = []
|
|
for idx, doc in enumerate(document_store):
|
|
output, stream = psg.run(documents=[doc])
|
|
assert "gpl_labels" in output
|
|
for item in output["gpl_labels"]:
|
|
assert "question" in item and "pos_doc" in item and "neg_doc" in item and "score" in item
|
|
train_examples.append(item)
|
|
|
|
assert len(train_examples) > 0
|
|
retriever.train(train_examples)
|
|
retriever.save(tmp_path)
|
|
|
|
|
|
@pytest.mark.generator
|
|
@pytest.mark.integration
|
|
@pytest.mark.parametrize("document_store", ["memory"], indirect=True)
|
|
@pytest.mark.parametrize("retriever", ["embedding_sbert"], indirect=True)
|
|
def test_pseudo_label_generator_using_question_document_pairs(
|
|
document_store, retriever: EmbeddingRetriever, tmp_path: Path
|
|
):
|
|
document_store.write_documents(DOCS_WITH_EMBEDDINGS)
|
|
docs = [
|
|
{
|
|
"question": "What is the capital of Germany?",
|
|
"document": "Berlin is the capital and largest city of Germany by both area and population.",
|
|
},
|
|
{
|
|
"question": "What is the largest city in Germany by population and area?",
|
|
"document": "Berlin is the capital and largest city of Germany by both area and population.",
|
|
},
|
|
]
|
|
psg = PseudoLabelGenerator(docs, retriever)
|
|
train_examples = []
|
|
for idx, doc in enumerate(document_store):
|
|
# the documents passed here are ignored as we provided source documents in the constructor
|
|
output, stream = psg.run(documents=[doc])
|
|
assert "gpl_labels" in output
|
|
for item in output["gpl_labels"]:
|
|
assert "question" in item and "pos_doc" in item and "neg_doc" in item and "score" in item
|
|
train_examples.append(item)
|
|
|
|
assert len(train_examples) > 0
|
|
|
|
retriever.train(train_examples)
|
|
retriever.save(tmp_path)
|