2023-01-20 17:45:01 +00:00
|
|
|
"""Test Qdrant functionality."""
|
2023-03-02 15:05:14 +00:00
|
|
|
import pytest
|
|
|
|
|
2023-01-20 17:45:01 +00:00
|
|
|
from langchain.docstore.document import Document
|
|
|
|
from langchain.vectorstores import Qdrant
|
2023-02-03 06:05:47 +00:00
|
|
|
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
|
2023-01-20 17:45:01 +00:00
|
|
|
|
|
|
|
|
2023-03-02 15:05:14 +00:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
["content_payload_key", "metadata_payload_key"],
|
|
|
|
[
|
|
|
|
(Qdrant.CONTENT_KEY, Qdrant.METADATA_KEY),
|
|
|
|
("foo", "bar"),
|
|
|
|
(Qdrant.CONTENT_KEY, "bar"),
|
|
|
|
("foo", Qdrant.METADATA_KEY),
|
|
|
|
],
|
|
|
|
)
|
|
|
|
def test_qdrant(content_payload_key: str, metadata_payload_key: str) -> None:
|
2023-01-20 17:45:01 +00:00
|
|
|
"""Test end to end construction and search."""
|
|
|
|
texts = ["foo", "bar", "baz"]
|
2023-03-02 15:05:14 +00:00
|
|
|
docsearch = Qdrant.from_texts(
|
|
|
|
texts,
|
|
|
|
FakeEmbeddings(),
|
|
|
|
host="localhost",
|
|
|
|
content_payload_key=content_payload_key,
|
|
|
|
metadata_payload_key=metadata_payload_key,
|
|
|
|
)
|
2023-01-20 17:45:01 +00:00
|
|
|
output = docsearch.similarity_search("foo", k=1)
|
|
|
|
assert output == [Document(page_content="foo")]
|
|
|
|
|
|
|
|
|
2023-03-02 15:05:14 +00:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
["content_payload_key", "metadata_payload_key"],
|
|
|
|
[
|
|
|
|
(Qdrant.CONTENT_KEY, Qdrant.METADATA_KEY),
|
|
|
|
("test_content", "test_payload"),
|
|
|
|
(Qdrant.CONTENT_KEY, "payload_test"),
|
|
|
|
("content_test", Qdrant.METADATA_KEY),
|
|
|
|
],
|
|
|
|
)
|
|
|
|
def test_qdrant_with_metadatas(
|
|
|
|
content_payload_key: str, metadata_payload_key: str
|
|
|
|
) -> None:
|
2023-01-20 17:45:01 +00:00
|
|
|
"""Test end to end construction and search."""
|
|
|
|
texts = ["foo", "bar", "baz"]
|
|
|
|
metadatas = [{"page": i} for i in range(len(texts))]
|
|
|
|
docsearch = Qdrant.from_texts(
|
|
|
|
texts,
|
|
|
|
FakeEmbeddings(),
|
|
|
|
metadatas=metadatas,
|
|
|
|
host="localhost",
|
2023-03-02 15:05:14 +00:00
|
|
|
content_payload_key=content_payload_key,
|
|
|
|
metadata_payload_key=metadata_payload_key,
|
2023-01-20 17:45:01 +00:00
|
|
|
)
|
|
|
|
output = docsearch.similarity_search("foo", k=1)
|
|
|
|
assert output == [Document(page_content="foo", metadata={"page": 0})]
|
|
|
|
|
|
|
|
|
2023-03-02 15:05:14 +00:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
["content_payload_key", "metadata_payload_key"],
|
|
|
|
[
|
|
|
|
(Qdrant.CONTENT_KEY, Qdrant.METADATA_KEY),
|
|
|
|
("test_content", "test_payload"),
|
|
|
|
(Qdrant.CONTENT_KEY, "payload_test"),
|
|
|
|
("content_test", Qdrant.METADATA_KEY),
|
|
|
|
],
|
|
|
|
)
|
|
|
|
def test_qdrant_max_marginal_relevance_search(
|
|
|
|
content_payload_key: str, metadata_payload_key: str
|
|
|
|
) -> None:
|
2023-01-20 17:45:01 +00:00
|
|
|
"""Test end to end construction and MRR search."""
|
|
|
|
texts = ["foo", "bar", "baz"]
|
|
|
|
metadatas = [{"page": i} for i in range(len(texts))]
|
|
|
|
docsearch = Qdrant.from_texts(
|
|
|
|
texts,
|
|
|
|
FakeEmbeddings(),
|
|
|
|
metadatas=metadatas,
|
|
|
|
host="localhost",
|
2023-03-02 15:05:14 +00:00
|
|
|
content_payload_key=content_payload_key,
|
|
|
|
metadata_payload_key=metadata_payload_key,
|
2023-01-20 17:45:01 +00:00
|
|
|
)
|
|
|
|
output = docsearch.max_marginal_relevance_search("foo", k=2, fetch_k=3)
|
|
|
|
assert output == [
|
|
|
|
Document(page_content="foo", metadata={"page": 0}),
|
|
|
|
Document(page_content="bar", metadata={"page": 1}),
|
|
|
|
]
|