mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-10-30 01:09:43 +00:00
738e008020
* Add run_batch methods for batch querying * Update Documentation & Code Style * Fix mypy * Update Documentation & Code Style * Fix mypy * Fix linter * Fix tests * Update Documentation & Code Style * Fix tests * Update Documentation & Code Style * Fix mypy * Fix rest api test * Update Documentation & Code Style * Add Doc strings * Update Documentation & Code Style * Add batch_size as attribute to nodes supporting batching * Adapt error messages * Adapt type of filters in retrievers * Revert change about truncation_warning in summarizer * Unify multiple_doc_lists tests * Use smaller models in extractor tests * Add return types to JoinAnswers and RouteDocuments * Adapt return statements in reader's run_batch method * Allow list of filters * Adapt error messages * Update Documentation & Code Style * Fix tests * Fix mypy * Adapt print_questions * Remove disabling warning about too many public methods * Add flag for pylint to disable warning about too many public methods in pipelines/base.py and document_stores/base.py * Add type check * Update Documentation & Code Style * Adapt tutorial 11 * Update Documentation & Code Style * Add query_batch method for DCDocStore * Update Documentation & Code Style Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
121 lines
4.6 KiB
Python
121 lines
4.6 KiB
Python
import pytest
|
|
|
|
from haystack.schema import Document
|
|
from haystack.nodes.document_classifier.base import BaseDocumentClassifier
|
|
|
|
|
|
@pytest.mark.slow
|
|
def test_document_classifier(document_classifier):
|
|
assert isinstance(document_classifier, BaseDocumentClassifier)
|
|
|
|
docs = [
|
|
Document(
|
|
content="""That's good. I like it.""" * 700, # extra long text to check truncation
|
|
meta={"name": "0"},
|
|
id="1",
|
|
),
|
|
Document(content="""That's bad. I don't like it.""", meta={"name": "1"}, id="2"),
|
|
]
|
|
results = document_classifier.predict(documents=docs)
|
|
expected_labels = ["joy", "sadness"]
|
|
for i, doc in enumerate(results):
|
|
assert doc.to_dict()["meta"]["classification"]["label"] == expected_labels[i]
|
|
|
|
|
|
@pytest.mark.slow
|
|
def test_document_classifier_batch_single_doc_list(document_classifier):
|
|
docs = [
|
|
Document(content="""That's good. I like it.""", meta={"name": "0"}, id="1"),
|
|
Document(content="""That's bad. I don't like it.""", meta={"name": "1"}, id="2"),
|
|
]
|
|
results = document_classifier.predict_batch(documents=docs)
|
|
expected_labels = ["joy", "sadness"]
|
|
for i, doc in enumerate(results):
|
|
assert doc.to_dict()["meta"]["classification"]["label"] == expected_labels[i]
|
|
|
|
|
|
@pytest.mark.slow
|
|
def test_document_classifier_batch_multiple_doc_lists(document_classifier):
|
|
docs = [
|
|
Document(content="""That's good. I like it.""", meta={"name": "0"}, id="1"),
|
|
Document(content="""That's bad. I don't like it.""", meta={"name": "1"}, id="2"),
|
|
]
|
|
results = document_classifier.predict_batch(documents=[docs, docs])
|
|
assert len(results) == 2 # 2 Document lists
|
|
expected_labels = ["joy", "sadness"]
|
|
for i, doc in enumerate(results[0]):
|
|
assert doc.to_dict()["meta"]["classification"]["label"] == expected_labels[i]
|
|
|
|
|
|
@pytest.mark.slow
|
|
def test_zero_shot_document_classifier(zero_shot_document_classifier):
|
|
assert isinstance(zero_shot_document_classifier, BaseDocumentClassifier)
|
|
|
|
docs = [
|
|
Document(
|
|
content="""That's good. I like it.""" * 700, # extra long text to check truncation
|
|
meta={"name": "0"},
|
|
id="1",
|
|
),
|
|
Document(content="""That's bad. I don't like it.""", meta={"name": "1"}, id="2"),
|
|
]
|
|
results = zero_shot_document_classifier.predict(documents=docs)
|
|
expected_labels = ["positive", "negative"]
|
|
for i, doc in enumerate(results):
|
|
assert doc.to_dict()["meta"]["classification"]["label"] == expected_labels[i]
|
|
|
|
|
|
@pytest.mark.slow
|
|
def test_document_classifier_batch_size(batched_document_classifier):
|
|
assert isinstance(batched_document_classifier, BaseDocumentClassifier)
|
|
|
|
docs = [
|
|
Document(
|
|
content="""That's good. I like it.""" * 700, # extra long text to check truncation
|
|
meta={"name": "0"},
|
|
id="1",
|
|
),
|
|
Document(content="""That's bad. I don't like it.""", meta={"name": "1"}, id="2"),
|
|
]
|
|
results = batched_document_classifier.predict(documents=docs)
|
|
expected_labels = ["joy", "sadness"]
|
|
for i, doc in enumerate(results):
|
|
assert doc.to_dict()["meta"]["classification"]["label"] == expected_labels[i]
|
|
|
|
|
|
@pytest.mark.slow
|
|
def test_document_classifier_as_index_node(indexing_document_classifier):
|
|
assert isinstance(indexing_document_classifier, BaseDocumentClassifier)
|
|
|
|
docs = [
|
|
{
|
|
"content": """That's good. I like it.""" * 700, # extra long text to check truncation
|
|
"meta": {"name": "0"},
|
|
"id": "1",
|
|
"class_field": "That's bad.",
|
|
},
|
|
{"content": """That's bad. I like it.""", "meta": {"name": "1"}, "id": "2", "class_field": "That's good."},
|
|
]
|
|
output, output_name = indexing_document_classifier.run(documents=docs, root_node="File")
|
|
expected_labels = ["sadness", "joy"]
|
|
for i, doc in enumerate(output["documents"]):
|
|
assert doc["meta"]["classification"]["label"] == expected_labels[i]
|
|
|
|
|
|
@pytest.mark.slow
|
|
def test_document_classifier_as_query_node(document_classifier):
|
|
assert isinstance(document_classifier, BaseDocumentClassifier)
|
|
|
|
docs = [
|
|
Document(
|
|
content="""That's good. I like it.""" * 700, # extra long text to check truncation
|
|
meta={"name": "0"},
|
|
id="1",
|
|
),
|
|
Document(content="""That's bad. I don't like it.""", meta={"name": "1"}, id="2"),
|
|
]
|
|
output, output_name = document_classifier.run(documents=docs, root_node="Query")
|
|
expected_labels = ["joy", "sadness"]
|
|
for i, doc in enumerate(output["documents"]):
|
|
assert doc.to_dict()["meta"]["classification"]["label"] == expected_labels[i]
|