mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-08-21 06:58:27 +00:00
db6864d159
* Fix type casting for vectors in FAISS Co-authored-by: philipp-bode <philipp.bode@student.hpi.de> * add type casts for elastic. refactor embedding retriever tests * fix case: empty embedding field * fix faiss tolerance * add assert in test_faiss_retrieving Co-authored-by: philipp-bode <philipp.bode@student.hpi.de>
36 lines
2.1 KiB
Python
36 lines
2.1 KiB
Python
import pytest
|
|
from haystack import Finder
|
|
from haystack.retriever.dense import EmbeddingRetriever
|
|
|
|
|
|
@pytest.mark.parametrize("document_store", ["elasticsearch", "faiss", "memory"], indirect=True)
|
|
def test_embedding_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'}},
|
|
]
|
|
|
|
retriever = EmbeddingRetriever(document_store=document_store, embedding_model="deepset/sentence_bert", use_gpu=False)
|
|
|
|
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
|