mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-28 03:12:54 +00:00

* Add BasePipeline.validate_config, BasePipeline.validate_yaml, and some new custom exception classes * Make error composition work properly * Clarify typing * Help mypy a bit more * Update Documentation & Code Style * Enable autogenerated docs for Milvus1 and 2 separately * Revert "Enable autogenerated docs for Milvus1 and 2 separately" This reverts commit 282be4a78a6e95862a9b4c924fc3dea5ca71e28d. * Update Documentation & Code Style * Re-enable 'additionalProperties: False' * Add pipeline.type to JSON Schema, was somehow forgotten * Disable additionalProperties on the pipeline properties too * Fix json-schemas for 1.1.0 and 1.2.0 (should not do it again in the future) * Cal super in PipelineValidationError * Improve _read_pipeline_config_from_yaml's error handling * Fix generate_json_schema.py to include document stores * Fix json schemas (retro-fix 1.1.0 again) * Improve custom errors printing, add link to docs * Add function in BaseComponent to list its subclasses in a module * Make some document stores base classes abstract * Add marker 'integration' in pytest flags * Slighly improve validation of pipelines at load * Adding tests for YAML loading and validation * Make custom_query Optional for validation issues * Fix bug in _read_pipeline_config_from_yaml * Improve error handling in BasePipeline and Pipeline and add DAG check * Move json schema generation into haystack/nodes/_json_schema.py (useful for tests) * Simplify errors slightly * Add some YAML validation tests * Remove load_from_config from BasePipeline, it was never used anyway * Improve tests * Include json-schemas in package * Fix conftest imports * Make BasePipeline abstract * Improve mocking by making the test independent from the YAML version * Add exportable_to_yaml decorator to forget about set_config on mock nodes * Fix mypy errors * Comment out one monkeypatch * Fix typing again * Improve error message for validation * Add required properties to pipelines * Fix YAML version for REST API YAMLs to 1.2.0 * Fix load_from_yaml call in load_from_deepset_cloud * fix HaystackError.__getattr__ * Add super().__init__()in most nodes and docstore, comment set_config * Remove type from REST API pipelines * Remove useless init from doc2answers * Call super in Seq3SeqGenerator * Typo in deepsetcloud.py * Fix rest api indexing error mismatch and mock version of JSON schema in all tests * Working on pipeline tests * Improve errors printing slightly * Add back test_pipeline.yaml * _json_schema.py supports different versions with identical schemas * Add type to 0.7 schema for backwards compatibility * Fix small bug in _json_schema.py * Try alternative to generate json schemas on the CI * Update Documentation & Code Style * Make linux CI match autoformat CI * Fix super-init-not-called * Accidentally committed file * Update Documentation & Code Style * fix test_summarizer_translation.py's import * Mock YAML in a few suites, split and simplify test_pipeline_debug_and_validation.py::test_invalid_run_args * Fix json schema for ray tests too * Update Documentation & Code Style * Reintroduce validation * Usa unstable version in tests and rest api * Make unstable support the latest versions * Update Documentation & Code Style * Remove needless fixture * Make type in pipeline optional in the strings validation * Fix schemas * Fix string validation for pipeline type * Improve validate_config_strings * Remove type from test p[ipelines * Update Documentation & Code Style * Fix test_pipeline * Removing more type from pipelines * Temporary CI patc * Fix issue with exportable_to_yaml never invoking the wrapped init * rm stray file * pipeline tests are green again * Linux CI now needs .[all] to generate the schema * Bugfixes, pipeline tests seems to be green * Typo in version after merge * Implement missing methods in Weaviate * Trying to avoid FAISS tests from running in the Milvus1 test suite * Fix some stray test paths and faiss index dumping * Fix pytest markers list * Temporarily disable cache to be able to see tests failures * Fix pyproject.toml syntax * Use only tmp_path * Fix preprocessor signature after merge * Fix faiss bug * Fix Ray test * Fix documentation issue by removing quotes from faiss type * Update Documentation & Code Style * use document properly in preprocessor tests * Update Documentation & Code Style * make preprocessor capable of handling documents * import document * Revert support for documents in preprocessor, do later * Fix bug in _json_schema.py that was breaking validation * re-enable cache * Update Documentation & Code Style * Simplify calling _json_schema.py from the CI * Remove redundant ABC inheritance * Ensure exportable_to_yaml works only on implementations * Rename subclass to class_ in Meta * Make run() and get_config() abstract in BasePipeline * Revert unintended change in preprocessor * Move outgoing_edges_input_node check inside try block * Rename VALID_CODE_GEN_INPUT_REGEX into VALID_INPUT_REGEX * Add check for a RecursionError on validate_config_strings * Address usages of _pipeline_config in data silo and elasticsearch * Rename _pipeline_config into _init_parameters * Fix pytest marker and remove unused imports * Remove most redundant ABCs * Rename _init_parameters into _component_configuration * Remove set_config and type from _component_configuration's dict * Remove last instances of set_config and replace with super().__init__() * Implement __init_subclass__ approach * Simplify checks on the existence of _component_configuration * Fix faiss issue * Dynamic generation of node schemas & weed out old schemas * Add debatable test * Add docstring to debatable test * Positive diff between schemas implemented * Improve diff printing * Rename REST API YAML files to trigger IDE validation * Fix typing issues * Fix more typing * Typo in YAML filename * Remove needless type:ignore * Add tests * Fix tests & validation feedback for accessory classes in custom nodes * Refactor RAGeneratorType out * Fix broken import in conftest * Improve source error handling * Remove unused import in test_eval.py breaking tests * Fix changed error message in tests matches too * Normalize generate_openapi_specs.py and generate_json_schema.py in the actions * Fix path to generate_openapi_specs.py in autoformat.yml * Update Documentation & Code Style * Add test for FAISSDocumentStore-like situations (superclass with init params) * Update Documentation & Code Style * Fix indentation * Remove commented set_config * Store model_name_or_path in FARMReader to use in DistillationDataSilo * Rename _component_configuration into _component_config * Update Documentation & Code Style Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
72 lines
2.3 KiB
Python
72 lines
2.3 KiB
Python
import pytest
|
|
import pandas as pd
|
|
from pathlib import Path
|
|
|
|
from haystack.utils.preprocessing import convert_files_to_dicts, tika_convert_files_to_dicts
|
|
from haystack.utils.cleaning import clean_wiki_text
|
|
from haystack.utils.augment_squad import augment_squad
|
|
from haystack.utils.squad_data import SquadData
|
|
|
|
from .conftest import SAMPLES_PATH
|
|
|
|
|
|
def test_convert_files_to_dicts():
|
|
documents = convert_files_to_dicts(
|
|
dir_path=(SAMPLES_PATH).absolute(), clean_func=clean_wiki_text, split_paragraphs=True
|
|
)
|
|
assert documents and len(documents) > 0
|
|
|
|
|
|
@pytest.mark.tika
|
|
def test_tika_convert_files_to_dicts():
|
|
documents = tika_convert_files_to_dicts(dir_path=SAMPLES_PATH, clean_func=clean_wiki_text, split_paragraphs=True)
|
|
assert documents and len(documents) > 0
|
|
|
|
|
|
def test_squad_augmentation():
|
|
input_ = SAMPLES_PATH / "squad" / "tiny.json"
|
|
output = SAMPLES_PATH / "squad" / "tiny_augmented.json"
|
|
glove_path = SAMPLES_PATH / "glove" / "tiny.txt" # dummy glove file, will not even be use when augmenting tiny.json
|
|
multiplication_factor = 5
|
|
augment_squad(
|
|
model="distilbert-base-uncased",
|
|
tokenizer="distilbert-base-uncased",
|
|
squad_path=input_,
|
|
output_path=output,
|
|
glove_path=glove_path,
|
|
multiplication_factor=multiplication_factor,
|
|
)
|
|
original_squad = SquadData.from_file(input_)
|
|
augmented_squad = SquadData.from_file(output)
|
|
assert original_squad.count(unit="paragraph") == augmented_squad.count(unit="paragraph") * multiplication_factor
|
|
|
|
|
|
def test_squad_to_df():
|
|
df = pd.DataFrame(
|
|
[["title", "context", "question", "id", "answer", 1, False]],
|
|
columns=["title", "context", "question", "id", "answer_text", "answer_start", "is_impossible"],
|
|
)
|
|
|
|
expected_result = [
|
|
{
|
|
"title": "title",
|
|
"paragraphs": [
|
|
{
|
|
"context": "context",
|
|
"qas": [
|
|
{
|
|
"question": "question",
|
|
"id": "id",
|
|
"answers": [{"text": "answer", "answer_start": 1}],
|
|
"is_impossible": False,
|
|
}
|
|
],
|
|
}
|
|
],
|
|
}
|
|
]
|
|
|
|
result = SquadData.df_to_data(df)
|
|
|
|
assert result == expected_result
|