mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-27 10:49:52 +00:00
f13443054a
* 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
73 lines
2.8 KiB
Python
73 lines
2.8 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from haystack.file_converter.pdf import PDFToTextConverter
|
|
from haystack.preprocessor.preprocessor import PreProcessor
|
|
|
|
TEXT = """
|
|
This is a sample sentence in paragraph_1. This is a sample sentence in paragraph_1. This is a sample sentence in
|
|
paragraph_1. This is a sample sentence in paragraph_1. This is a sample sentence in paragraph_1.
|
|
|
|
This is a sample sentence in paragraph_2. This is a sample sentence in paragraph_2. This is a sample sentence in
|
|
paragraph_2. This is a sample sentence in paragraph_2. This is a sample sentence in paragraph_2.
|
|
|
|
This is a sample sentence in paragraph_3. This is a sample sentence in paragraph_3. This is a sample sentence in
|
|
paragraph_3. This is a sample sentence in paragraph_3. This is to trick the test with using an abbreviation like Dr.
|
|
in the sentence.
|
|
"""
|
|
|
|
|
|
@pytest.mark.tika
|
|
def test_preprocess_sentence_split():
|
|
document = {"text": TEXT}
|
|
preprocessor = PreProcessor(split_length=1, split_stride=0, split_by="sentence")
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 15
|
|
|
|
preprocessor = PreProcessor(
|
|
split_length=10, split_stride=0, split_by="sentence"
|
|
)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 2
|
|
|
|
|
|
@pytest.mark.tika
|
|
def test_preprocess_word_split():
|
|
document = {"text": TEXT}
|
|
preprocessor = PreProcessor(split_length=10, split_stride=0, split_by="word", split_respect_sentence_boundary=False)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 11
|
|
|
|
preprocessor = PreProcessor(split_length=10, split_stride=0, split_by="word", split_respect_sentence_boundary=True)
|
|
documents = preprocessor.process(document)
|
|
for doc in documents:
|
|
assert len(doc["text"].split(" ")) <= 10 or doc["text"].startswith("This is to trick")
|
|
assert len(documents) == 15
|
|
|
|
|
|
@pytest.mark.tika
|
|
def test_preprocess_passage_split():
|
|
document = {"text": TEXT}
|
|
preprocessor = PreProcessor(split_length=1, split_stride=0, split_by="passage", split_respect_sentence_boundary=False)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 3
|
|
|
|
preprocessor = PreProcessor(split_length=2, split_stride=0, split_by="passage", split_respect_sentence_boundary=False)
|
|
documents = preprocessor.process(document)
|
|
assert len(documents) == 2
|
|
|
|
|
|
@pytest.mark.tika
|
|
def test_clean_header_footer():
|
|
converter = PDFToTextConverter()
|
|
document = converter.convert(file_path=Path("samples/pdf/sample_pdf_2.pdf")) # file contains header/footer
|
|
|
|
preprocessor = PreProcessor(clean_header_footer=True, split_by=None)
|
|
documents = preprocessor.process(document)
|
|
|
|
assert len(documents) == 1
|
|
|
|
assert "This is a header." not in documents[0]["text"]
|
|
assert "footer" not in documents[0]["text"]
|