def test_finder_get_answers():
test_docs = [{
"name": "testing the finder 1",
"text": "testing the finder with pyhton unit test 1",
"meta": {
"test": "test"
}
}, {
"name": "testing the finder 2",
"text": "testing the finder with pyhton unit test 2",
"meta": {
"test": "test"
}
}, {
"name": "testing the finder 3",
"text": "testing the finder with pyhton unit test 3",
"meta": {
"test": "test"
}
}]
document_store = SQLDocumentStore(url="sqlite:///qa_test.db")
document_store.write_documents(test_docs)
retriever = TfidfRetriever(document_store=document_store)
reader = TransformersReader(
model="distilbert-base-uncased-distilled-squad",
tokenizer="distilbert-base-uncased",
use_gpu=-1)
finder = Finder(reader, retriever)
prediction = finder.get_answers(question="testing finder",
top_k_retriever=10,
top_k_reader=5)
assert prediction is not None
def test_sql_write_read():
sql_document_store = SQLDocumentStore()
documents = convert_files_to_dicts(dir_path="samples/docs")
sql_document_store.write_documents(documents)
documents = sql_document_store.get_all_documents()
assert len(documents) == 2
doc = sql_document_store.get_document_by_id("1")
assert doc.id
assert doc.text
def document_store_with_docs(request, test_docs_xs, elasticsearch_fixture):
if request.param == "sql":
if os.path.exists("qa_test.db"):
os.remove("qa_test.db")
document_store = SQLDocumentStore(url="sqlite:///qa_test.db")
document_store.write_documents(test_docs_xs)
if request.param == "memory":
document_store = InMemoryDocumentStore()
document_store.write_documents(test_docs_xs)
if request.param == "elasticsearch":
# make sure we start from a fresh index
client = Elasticsearch()
client.indices.delete(index='haystack_test', ignore=[404])
document_store = ElasticsearchDocumentStore(index="haystack_test")
assert document_store.get_document_count() == 0
document_store.write_documents(test_docs_xs)
return document_store