mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-08-20 14:38:44 +00:00
9f7f95221f
* Initial commit for Milvus integration * Add latest docstring and tutorial changes * Updating implementation of Milvus document store * Add latest docstring and tutorial changes * Adding tests and updating doc string * Add latest docstring and tutorial changes * Fixing issue caught by tests * Addressing review comments * Fixing mypy detected issue * Fixing issue caught in test about sorting of vector ids * fixing test * Fixing generator test failure * update docstrings * Addressing review comments about multiple network call while fetching embedding from milvus server * Add latest docstring and tutorial changes * Ignoring mypy issue while converting vector_id to int Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai>
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", "milvus"], 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
|