Spaces:
Sleeping
Sleeping
File size: 2,881 Bytes
cfd3735 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
"""Test Milvus functionality."""
from typing import List, Optional
from langchain.docstore.document import Document
from langchain.vectorstores import Milvus
from tests.integration_tests.vectorstores.fake_embeddings import (
FakeEmbeddings,
fake_texts,
)
def _milvus_from_texts(
metadatas: Optional[List[dict]] = None, drop: bool = True
) -> Milvus:
return Milvus.from_texts(
fake_texts,
FakeEmbeddings(),
metadatas=metadatas,
connection_args={"host": "127.0.0.1", "port": "19530"},
drop_old=drop,
)
def test_milvus() -> None:
"""Test end to end construction and search."""
docsearch = _milvus_from_texts()
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
def test_milvus_with_score() -> None:
"""Test end to end construction and search with scores and IDs."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = _milvus_from_texts(metadatas=metadatas)
output = docsearch.similarity_search_with_score("foo", k=3)
docs = [o[0] for o in output]
scores = [o[1] for o in output]
assert docs == [
Document(page_content="foo", metadata={"page": 0}),
Document(page_content="bar", metadata={"page": 1}),
Document(page_content="baz", metadata={"page": 2}),
]
assert scores[0] < scores[1] < scores[2]
def test_milvus_max_marginal_relevance_search() -> None:
"""Test end to end construction and MRR search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = _milvus_from_texts(metadatas=metadatas)
output = docsearch.max_marginal_relevance_search("foo", k=2, fetch_k=3)
assert output == [
Document(page_content="foo", metadata={"page": 0}),
Document(page_content="baz", metadata={"page": 2}),
]
def test_milvus_add_extra() -> None:
"""Test end to end construction and MRR search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = _milvus_from_texts(metadatas=metadatas)
docsearch.add_texts(texts, metadatas)
output = docsearch.similarity_search("foo", k=10)
assert len(output) == 6
def test_milvus_no_drop() -> None:
"""Test end to end construction and MRR search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = _milvus_from_texts(metadatas=metadatas)
del docsearch
docsearch = _milvus_from_texts(metadatas=metadatas, drop=False)
output = docsearch.similarity_search("foo", k=10)
assert len(output) == 6
# if __name__ == "__main__":
# test_milvus()
# test_milvus_with_score()
# test_milvus_max_marginal_relevance_search()
# test_milvus_add_extra()
# test_milvus_no_drop()
|