mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-08-22 23:48:09 +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
36 lines
2.1 KiB
Python
36 lines
2.1 KiB
Python
import pytest
|
|
from haystack import Finder
|
|
|
|
|
|
@pytest.mark.slow
|
|
@pytest.mark.elasticsearch
|
|
@pytest.mark.parametrize("document_store", ["elasticsearch", "faiss", "memory"], indirect=True)
|
|
@pytest.mark.parametrize("retriever", ["embedding"], indirect=True)
|
|
def test_embedding_retriever(retriever, document_store):
|
|
|
|
documents = [
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'How to test this library?', 'question': 'How to test this library?'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
{'text': 'By running tox in the command line!', 'meta': {'name': 'blah blah blah', 'question': 'blah blah blah'}},
|
|
]
|
|
|
|
embedded = []
|
|
for doc in documents:
|
|
doc['embedding'] = retriever.embed([doc['meta']['question']])[0]
|
|
embedded.append(doc)
|
|
|
|
document_store.write_documents(embedded)
|
|
|
|
finder = Finder(reader=None, retriever=retriever)
|
|
prediction = finder.get_answers_via_similar_questions(question="How to test this?", top_k_retriever=1)
|
|
|
|
assert len(prediction.get('answers', [])) == 1
|