Spaces:
Sleeping
Sleeping
File size: 3,966 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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
"""Test MyScale functionality."""
import pytest
from langchain.docstore.document import Document
from langchain.vectorstores import MyScale, MyScaleSettings
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
def test_myscale() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
config = MyScaleSettings()
config.table = "test_myscale"
docsearch = MyScale.from_texts(texts, FakeEmbeddings(), config=config)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo", metadata={"_dummy": 0})]
docsearch.drop()
@pytest.mark.asyncio
async def test_myscale_async() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
config = MyScaleSettings()
config.table = "test_myscale_async"
docsearch = MyScale.from_texts(
texts=texts, embedding=FakeEmbeddings(), config=config
)
output = await docsearch.asimilarity_search("foo", k=1)
assert output == [Document(page_content="foo", metadata={"_dummy": 0})]
docsearch.drop()
def test_myscale_with_metadatas() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": str(i)} for i in range(len(texts))]
config = MyScaleSettings()
config.table = "test_myscale_with_metadatas"
docsearch = MyScale.from_texts(
texts=texts,
embedding=FakeEmbeddings(),
config=config,
metadatas=metadatas,
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo", metadata={"page": "0"})]
docsearch.drop()
def test_myscale_with_metadatas_with_relevance_scores() -> None:
"""Test end to end construction and scored search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": str(i)} for i in range(len(texts))]
config = MyScaleSettings()
config.table = "test_myscale_with_metadatas_with_relevance_scores"
docsearch = MyScale.from_texts(
texts=texts, embedding=FakeEmbeddings(), metadatas=metadatas, config=config
)
output = docsearch.similarity_search_with_relevance_scores("foo", k=1)
assert output[0][0] == Document(page_content="foo", metadata={"page": "0"})
docsearch.drop()
def test_myscale_search_filter() -> None:
"""Test end to end construction and search with metadata filtering."""
texts = ["far", "bar", "baz"]
metadatas = [{"first_letter": "{}".format(text[0])} for text in texts]
config = MyScaleSettings()
config.table = "test_myscale_search_filter"
docsearch = MyScale.from_texts(
texts=texts, embedding=FakeEmbeddings(), metadatas=metadatas, config=config
)
output = docsearch.similarity_search(
"far", k=1, where_str=f"{docsearch.metadata_column}.first_letter='f'"
)
assert output == [Document(page_content="far", metadata={"first_letter": "f"})]
output = docsearch.similarity_search(
"bar", k=1, where_str=f"{docsearch.metadata_column}.first_letter='b'"
)
assert output == [Document(page_content="bar", metadata={"first_letter": "b"})]
docsearch.drop()
def test_myscale_with_persistence() -> None:
"""Test end to end construction and search, with persistence."""
config = MyScaleSettings()
config.table = "test_myscale_with_persistence"
texts = [
"foo",
"bar",
"baz",
]
docsearch = MyScale.from_texts(
texts=texts, embedding=FakeEmbeddings(), config=config
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo", metadata={"_dummy": 0})]
# Get a new VectorStore with same config
# it will reuse the table spontaneously
# unless you drop it
docsearch = MyScale(embedding=FakeEmbeddings(), config=config)
output = docsearch.similarity_search("foo", k=1)
# Clean up
docsearch.drop()
|