Spaces:
Sleeping
Sleeping
File size: 7,084 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 |
"""Test Weaviate functionality."""
import logging
import os
from typing import Generator, Union
import pytest
from weaviate import Client
from langchain.docstore.document import Document
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores.weaviate import Weaviate
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
logging.basicConfig(level=logging.DEBUG)
"""
cd tests/integration_tests/vectorstores/docker-compose
docker compose -f weaviate.yml up
"""
class TestWeaviate:
@classmethod
def setup_class(cls) -> None:
if not os.getenv("OPENAI_API_KEY"):
raise ValueError("OPENAI_API_KEY environment variable is not set")
@pytest.fixture(scope="class", autouse=True)
def weaviate_url(self) -> Union[str, Generator[str, None, None]]:
"""Return the weaviate url."""
url = "http://localhost:8080"
yield url
# Clear the test index
client = Client(url)
client.schema.delete_all()
@pytest.mark.vcr(ignore_localhost=True)
def test_similarity_search_without_metadata(
self, weaviate_url: str, embedding_openai: OpenAIEmbeddings
) -> None:
"""Test end to end construction and search without metadata."""
texts = ["foo", "bar", "baz"]
docsearch = Weaviate.from_texts(
texts,
embedding_openai,
weaviate_url=weaviate_url,
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
@pytest.mark.vcr(ignore_localhost=True)
def test_similarity_search_with_metadata(
self, weaviate_url: str, embedding_openai: OpenAIEmbeddings
) -> None:
"""Test end to end construction and search with metadata."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = Weaviate.from_texts(
texts, embedding_openai, metadatas=metadatas, weaviate_url=weaviate_url
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo", metadata={"page": 0})]
@pytest.mark.vcr(ignore_localhost=True)
def test_similarity_search_with_metadata_and_filter(
self, weaviate_url: str, embedding_openai: OpenAIEmbeddings
) -> None:
"""Test end to end construction and search with metadata."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = Weaviate.from_texts(
texts, embedding_openai, metadatas=metadatas, weaviate_url=weaviate_url
)
output = docsearch.similarity_search(
"foo",
k=2,
where_filter={"path": ["page"], "operator": "Equal", "valueNumber": 0},
)
assert output == [Document(page_content="foo", metadata={"page": 0})]
@pytest.mark.vcr(ignore_localhost=True)
def test_max_marginal_relevance_search(
self, weaviate_url: str, embedding_openai: OpenAIEmbeddings
) -> None:
"""Test end to end construction and MRR search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = Weaviate.from_texts(
texts, embedding_openai, metadatas=metadatas, weaviate_url=weaviate_url
)
# if lambda=1 the algorithm should be equivalent to standard ranking
standard_ranking = docsearch.similarity_search("foo", k=2)
output = docsearch.max_marginal_relevance_search(
"foo", k=2, fetch_k=3, lambda_mult=1.0
)
assert output == standard_ranking
# if lambda=0 the algorithm should favour maximal diversity
output = docsearch.max_marginal_relevance_search(
"foo", k=2, fetch_k=3, lambda_mult=0.0
)
assert output == [
Document(page_content="foo", metadata={"page": 0}),
Document(page_content="bar", metadata={"page": 1}),
]
@pytest.mark.vcr(ignore_localhost=True)
def test_max_marginal_relevance_search_by_vector(
self, weaviate_url: str, embedding_openai: OpenAIEmbeddings
) -> None:
"""Test end to end construction and MRR search by vector."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = Weaviate.from_texts(
texts, embedding_openai, metadatas=metadatas, weaviate_url=weaviate_url
)
foo_embedding = embedding_openai.embed_query("foo")
# if lambda=1 the algorithm should be equivalent to standard ranking
standard_ranking = docsearch.similarity_search("foo", k=2)
output = docsearch.max_marginal_relevance_search_by_vector(
foo_embedding, k=2, fetch_k=3, lambda_mult=1.0
)
assert output == standard_ranking
# if lambda=0 the algorithm should favour maximal diversity
output = docsearch.max_marginal_relevance_search_by_vector(
foo_embedding, k=2, fetch_k=3, lambda_mult=0.0
)
assert output == [
Document(page_content="foo", metadata={"page": 0}),
Document(page_content="bar", metadata={"page": 1}),
]
@pytest.mark.vcr(ignore_localhost=True)
def test_max_marginal_relevance_search_with_filter(
self, weaviate_url: str, embedding_openai: OpenAIEmbeddings
) -> None:
"""Test end to end construction and MRR search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = Weaviate.from_texts(
texts, embedding_openai, metadatas=metadatas, weaviate_url=weaviate_url
)
where_filter = {"path": ["page"], "operator": "Equal", "valueNumber": 0}
# if lambda=1 the algorithm should be equivalent to standard ranking
standard_ranking = docsearch.similarity_search(
"foo", k=2, where_filter=where_filter
)
output = docsearch.max_marginal_relevance_search(
"foo", k=2, fetch_k=3, lambda_mult=1.0, where_filter=where_filter
)
assert output == standard_ranking
# if lambda=0 the algorithm should favour maximal diversity
output = docsearch.max_marginal_relevance_search(
"foo", k=2, fetch_k=3, lambda_mult=0.0, where_filter=where_filter
)
assert output == [
Document(page_content="foo", metadata={"page": 0}),
]
def test_add_texts_with_given_embedding(self, weaviate_url: str) -> None:
texts = ["foo", "bar", "baz"]
embedding = FakeEmbeddings()
docsearch = Weaviate.from_texts(
texts, embedding=embedding, weaviate_url=weaviate_url
)
docsearch.add_texts(["foo"])
output = docsearch.similarity_search_by_vector(
embedding.embed_query("foo"), k=2
)
assert output == [
Document(page_content="foo"),
Document(page_content="foo"),
]
|