mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-09-19 21:23:37 +00:00
9727829cc6
* rename database to documentstore * move document, label, multilabel to haystack/schema.py * rename documentstore -> document_store * split indexing modules -> file_converter + preprocessor * fix order of imports * Update tutorial notebooks * fix torch version in tutorial 4
20 lines
809 B
Python
20 lines
809 B
Python
def test_tfidf_retriever():
|
|
from haystack.retriever.sparse import TfidfRetriever
|
|
|
|
test_docs = [
|
|
{"id": "26f84672c6d7aaeb8e2cd53e9c62d62d", "name": "testing the finder 1", "text": "godzilla says hello"},
|
|
{"name": "testing the finder 2", "text": "optimus prime says bye"},
|
|
{"name": "testing the finder 3", "text": "alien says arghh"}
|
|
]
|
|
|
|
from haystack.document_store.memory import InMemoryDocumentStore
|
|
document_store = InMemoryDocumentStore()
|
|
document_store.write_documents(test_docs)
|
|
|
|
retriever = TfidfRetriever(document_store)
|
|
retriever.fit()
|
|
doc = retriever.retrieve("godzilla", top_k=1)[0]
|
|
assert doc.id == "26f84672c6d7aaeb8e2cd53e9c62d62d"
|
|
assert doc.text == 'godzilla says hello'
|
|
assert doc.meta == {"name": "testing the finder 1"}
|