haystack/test/test_utils.py

29 lines
1.4 KiB
Python
Raw Normal View History

[RAG] Integrate "Retrieval-Augmented Generation" with Haystack (#484) * Adding dummy generator implementation * Adding tutorial to try the model * Committing current non working code * Committing current update where we need to call generate function directly and need to convert embedding to tensor way * Addressing review comments. * Refactoring finder, and implementing rag_generator class. * Refined the implementation of RAGGenerator and now it is in clean shape * Renaming RAGGenerator to RAGenerator * Reverting change from finder.py and addressing review comments * Remove support for RagSequenceForGeneration * Utilizing embed_passage function from DensePassageRetriever * Adding sample test data to verify generator output * Updating testing script * Updating testing script * Fixing bug related to top_k * Updating latest farm dependency * Comment out farm dependency * Reverting changes from TransformersReader * Adding transformers dataset to compare transformers and haystack generator implementation * Using generator_encoder instead of question_encoder to generate context_input_ids * Adding workaround to install FARM dependency from master branch * Removing unnecessary changes * Fixing generator test * Removing transformers datasets * Fixing generator test * Some cleanup and updating TODO comments * Adding tutorial notebook * Updating tutorials with comments * Explicitly passing token model in RAG test * Addressing review comments * Fixing notebook * Refactoring tests to reduce memory footprint * Split generator tests in separate ci step and before running it reclaim memory by terminating containers * Moving tika dependent test to separate dir * Remove unwanted code * Brining reader under session scope * Farm is now session object hence restoring changes from default value * Updating assert for pdf converter * Dummy commit to trigger CI flow * REducing memory footprint required for generator tests * Fixing mypy issues * Marking test with tika and elasticsearch markers. Reverting changes in CI and pytest splits * reducing changes * Fixing CI * changing elastic search ci * Fixing test error * Disabling return of embedding * Marking generator test as well * Refactoring tutorials * Increasing ES memory to 750M * Trying another fix for ES CI * Reverting CI changes * Splitting tests in CI * Generator and non-generator markers split * Adding pytest.ini to add markers and enable strict-markers option * Reducing elastic search container memory * Simplifying generator test by using documents with embedding directly * Bump up farm to 0.5.0
2020-10-30 18:06:02 +01:00
import pytest
from pathlib import Path
[RAG] Integrate "Retrieval-Augmented Generation" with Haystack (#484) * Adding dummy generator implementation * Adding tutorial to try the model * Committing current non working code * Committing current update where we need to call generate function directly and need to convert embedding to tensor way * Addressing review comments. * Refactoring finder, and implementing rag_generator class. * Refined the implementation of RAGGenerator and now it is in clean shape * Renaming RAGGenerator to RAGenerator * Reverting change from finder.py and addressing review comments * Remove support for RagSequenceForGeneration * Utilizing embed_passage function from DensePassageRetriever * Adding sample test data to verify generator output * Updating testing script * Updating testing script * Fixing bug related to top_k * Updating latest farm dependency * Comment out farm dependency * Reverting changes from TransformersReader * Adding transformers dataset to compare transformers and haystack generator implementation * Using generator_encoder instead of question_encoder to generate context_input_ids * Adding workaround to install FARM dependency from master branch * Removing unnecessary changes * Fixing generator test * Removing transformers datasets * Fixing generator test * Some cleanup and updating TODO comments * Adding tutorial notebook * Updating tutorials with comments * Explicitly passing token model in RAG test * Addressing review comments * Fixing notebook * Refactoring tests to reduce memory footprint * Split generator tests in separate ci step and before running it reclaim memory by terminating containers * Moving tika dependent test to separate dir * Remove unwanted code * Brining reader under session scope * Farm is now session object hence restoring changes from default value * Updating assert for pdf converter * Dummy commit to trigger CI flow * REducing memory footprint required for generator tests * Fixing mypy issues * Marking test with tika and elasticsearch markers. Reverting changes in CI and pytest splits * reducing changes * Fixing CI * changing elastic search ci * Fixing test error * Disabling return of embedding * Marking generator test as well * Refactoring tutorials * Increasing ES memory to 750M * Trying another fix for ES CI * Reverting CI changes * Splitting tests in CI * Generator and non-generator markers split * Adding pytest.ini to add markers and enable strict-markers option * Reducing elastic search container memory * Simplifying generator test by using documents with embedding directly * Bump up farm to 0.5.0
2020-10-30 18:06:02 +01:00
Add CI for windows runner (#1458) * Feat: Removing use of temp file while downloading archive from url along with adding CI for windows and mac platform * Windows CI by default installing pytorch gpu hence updating CI to pick cpu version * fixing mac cache build issue * updating windows pip install command for torch * another attempt * updating ci * Adding sudo * fixing ls failure on windows * another attempt to fix build issue * Saving env variable of test files * Adding debug log * Github action differ on windows * adding debug * anohter attempt * Windows have different ways to receive env * fixing template * minor fx * Adding debug * Removing use of json * Adding back fromJson * addin toJson * removing print * anohter attempt * disabling parallel run at least for testing * installing docker for mac runner * correcting docker install command * Linux dockers are not suported in windows * Removing mac changes * Upgrading pytorch * using lts pytorch * Separating win and ubuntu * Install java 11 * enabling linux container env * docker cli command * docker cli command * start elastic service * List all service * correcting service name * Attempt to fix multiple test run * convert to json * another attempt to check * Updating build cache step * attempt * Add tika * Separating windows CI * Changing CI name * Skipping test which does not work in windows * Skipping tests for windows * create cleanup function in conftest * adding skipif marker on tests * Run windows PR on only push to master * Addressing review comments * Enabling windows ci for this PR * Tika init is being called when importing tika function * handling tika import issue * handling tika import issue in test * Fixing import issue * removing tika fixure * Removing fixture from tests * Disable windows ci on pull request * Add back extra pytorch install step Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2021-10-29 13:52:28 +05:30
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
Add CI for windows runner (#1458) * Feat: Removing use of temp file while downloading archive from url along with adding CI for windows and mac platform * Windows CI by default installing pytorch gpu hence updating CI to pick cpu version * fixing mac cache build issue * updating windows pip install command for torch * another attempt * updating ci * Adding sudo * fixing ls failure on windows * another attempt to fix build issue * Saving env variable of test files * Adding debug log * Github action differ on windows * adding debug * anohter attempt * Windows have different ways to receive env * fixing template * minor fx * Adding debug * Removing use of json * Adding back fromJson * addin toJson * removing print * anohter attempt * disabling parallel run at least for testing * installing docker for mac runner * correcting docker install command * Linux dockers are not suported in windows * Removing mac changes * Upgrading pytorch * using lts pytorch * Separating win and ubuntu * Install java 11 * enabling linux container env * docker cli command * docker cli command * start elastic service * List all service * correcting service name * Attempt to fix multiple test run * convert to json * another attempt to check * Updating build cache step * attempt * Add tika * Separating windows CI * Changing CI name * Skipping test which does not work in windows * Skipping tests for windows * create cleanup function in conftest * adding skipif marker on tests * Run windows PR on only push to master * Addressing review comments * Enabling windows ci for this PR * Tika init is being called when importing tika function * handling tika import issue * handling tika import issue in test * Fixing import issue * removing tika fixure * Removing fixture from tests * Disable windows ci on pull request * Add back extra pytorch install step Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2021-10-29 13:52:28 +05:30
def test_convert_files_to_dicts():
Refactoring of the `haystack` package (#1624) * Files moved, imports all broken * Fix most imports and docstrings into * Fix the paths to the modules in the API docs * Add latest docstring and tutorial changes * Add a few pipelines that were lost in the inports * Fix a bunch of mypy warnings * Add latest docstring and tutorial changes * Create a file_classifier module * Add docs for file_classifier * Fixed most circular imports, now the REST API can start * Add latest docstring and tutorial changes * Tackling more mypy issues * Reintroduce from FARM and fix last mypy issues hopefully * Re-enable old-style imports * Fix some more import from the top-level package in an attempt to sort out circular imports * Fix some imports in tests to new-style to prevent failed class equalities from breaking tests * Change document_store into document_stores * Update imports in tutorials * Add latest docstring and tutorial changes * Probably fixes summarizer tests * Improve the old-style import allowing module imports (should work) * Try to fix the docs * Remove dedicated KnowledgeGraph page from autodocs * Remove dedicated GraphRetriever page from autodocs * Fix generate_docstrings.sh with an updated list of yaml files to look for * Fix some more modules in the docs * Fix the document stores docs too * Fix a small issue on Tutorial14 * Add latest docstring and tutorial changes * Add deprecation warning to old-style imports * Remove stray folder and import Dict into dense.py * Change import path for MLFlowLogger * Add old loggers path to the import path aliases * Fix debug output of convert_ipynb.py * Fix circular import on BaseRetriever * Missed one merge block * re-run tutorial 5 * Fix imports in tutorial 5 * Re-enable squad_to_dpr CLI from the root package and move get_batches_from_generator into document_stores.base * Add latest docstring and tutorial changes * Fix typo in utils __init__ * Fix a few more imports * Fix benchmarks too * New-style imports in test_knowledge_graph * Rollback setup.py * Rollback squad_to_dpr too Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2021-10-25 15:50:23 +02:00
documents = convert_files_to_dicts(dir_path="samples", clean_func=clean_wiki_text, split_paragraphs=True)
assert documents and len(documents) > 0
[RAG] Integrate "Retrieval-Augmented Generation" with Haystack (#484) * Adding dummy generator implementation * Adding tutorial to try the model * Committing current non working code * Committing current update where we need to call generate function directly and need to convert embedding to tensor way * Addressing review comments. * Refactoring finder, and implementing rag_generator class. * Refined the implementation of RAGGenerator and now it is in clean shape * Renaming RAGGenerator to RAGenerator * Reverting change from finder.py and addressing review comments * Remove support for RagSequenceForGeneration * Utilizing embed_passage function from DensePassageRetriever * Adding sample test data to verify generator output * Updating testing script * Updating testing script * Fixing bug related to top_k * Updating latest farm dependency * Comment out farm dependency * Reverting changes from TransformersReader * Adding transformers dataset to compare transformers and haystack generator implementation * Using generator_encoder instead of question_encoder to generate context_input_ids * Adding workaround to install FARM dependency from master branch * Removing unnecessary changes * Fixing generator test * Removing transformers datasets * Fixing generator test * Some cleanup and updating TODO comments * Adding tutorial notebook * Updating tutorials with comments * Explicitly passing token model in RAG test * Addressing review comments * Fixing notebook * Refactoring tests to reduce memory footprint * Split generator tests in separate ci step and before running it reclaim memory by terminating containers * Moving tika dependent test to separate dir * Remove unwanted code * Brining reader under session scope * Farm is now session object hence restoring changes from default value * Updating assert for pdf converter * Dummy commit to trigger CI flow * REducing memory footprint required for generator tests * Fixing mypy issues * Marking test with tika and elasticsearch markers. Reverting changes in CI and pytest splits * reducing changes * Fixing CI * changing elastic search ci * Fixing test error * Disabling return of embedding * Marking generator test as well * Refactoring tutorials * Increasing ES memory to 750M * Trying another fix for ES CI * Reverting CI changes * Splitting tests in CI * Generator and non-generator markers split * Adding pytest.ini to add markers and enable strict-markers option * Reducing elastic search container memory * Simplifying generator test by using documents with embedding directly * Bump up farm to 0.5.0
2020-10-30 18:06:02 +01:00
@pytest.mark.tika
Add CI for windows runner (#1458) * Feat: Removing use of temp file while downloading archive from url along with adding CI for windows and mac platform * Windows CI by default installing pytorch gpu hence updating CI to pick cpu version * fixing mac cache build issue * updating windows pip install command for torch * another attempt * updating ci * Adding sudo * fixing ls failure on windows * another attempt to fix build issue * Saving env variable of test files * Adding debug log * Github action differ on windows * adding debug * anohter attempt * Windows have different ways to receive env * fixing template * minor fx * Adding debug * Removing use of json * Adding back fromJson * addin toJson * removing print * anohter attempt * disabling parallel run at least for testing * installing docker for mac runner * correcting docker install command * Linux dockers are not suported in windows * Removing mac changes * Upgrading pytorch * using lts pytorch * Separating win and ubuntu * Install java 11 * enabling linux container env * docker cli command * docker cli command * start elastic service * List all service * correcting service name * Attempt to fix multiple test run * convert to json * another attempt to check * Updating build cache step * attempt * Add tika * Separating windows CI * Changing CI name * Skipping test which does not work in windows * Skipping tests for windows * create cleanup function in conftest * adding skipif marker on tests * Run windows PR on only push to master * Addressing review comments * Enabling windows ci for this PR * Tika init is being called when importing tika function * handling tika import issue * handling tika import issue in test * Fixing import issue * removing tika fixure * Removing fixture from tests * Disable windows ci on pull request * Add back extra pytorch install step Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
2021-10-29 13:52:28 +05:30
def test_tika_convert_files_to_dicts():
Refactoring of the `haystack` package (#1624) * Files moved, imports all broken * Fix most imports and docstrings into * Fix the paths to the modules in the API docs * Add latest docstring and tutorial changes * Add a few pipelines that were lost in the inports * Fix a bunch of mypy warnings * Add latest docstring and tutorial changes * Create a file_classifier module * Add docs for file_classifier * Fixed most circular imports, now the REST API can start * Add latest docstring and tutorial changes * Tackling more mypy issues * Reintroduce from FARM and fix last mypy issues hopefully * Re-enable old-style imports * Fix some more import from the top-level package in an attempt to sort out circular imports * Fix some imports in tests to new-style to prevent failed class equalities from breaking tests * Change document_store into document_stores * Update imports in tutorials * Add latest docstring and tutorial changes * Probably fixes summarizer tests * Improve the old-style import allowing module imports (should work) * Try to fix the docs * Remove dedicated KnowledgeGraph page from autodocs * Remove dedicated GraphRetriever page from autodocs * Fix generate_docstrings.sh with an updated list of yaml files to look for * Fix some more modules in the docs * Fix the document stores docs too * Fix a small issue on Tutorial14 * Add latest docstring and tutorial changes * Add deprecation warning to old-style imports * Remove stray folder and import Dict into dense.py * Change import path for MLFlowLogger * Add old loggers path to the import path aliases * Fix debug output of convert_ipynb.py * Fix circular import on BaseRetriever * Missed one merge block * re-run tutorial 5 * Fix imports in tutorial 5 * Re-enable squad_to_dpr CLI from the root package and move get_batches_from_generator into document_stores.base * Add latest docstring and tutorial changes * Fix typo in utils __init__ * Fix a few more imports * Fix benchmarks too * New-style imports in test_knowledge_graph * Rollback setup.py * Rollback squad_to_dpr too Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2021-10-25 15:50:23 +02:00
documents = tika_convert_files_to_dicts(dir_path="samples", clean_func=clean_wiki_text, split_paragraphs=True)
assert documents and len(documents) > 0
def test_squad_augmentation():
input_ = Path("samples/squad/tiny.json")
output = Path("samples/squad/tiny_augmented.json")
glove_path = Path("samples/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