Spaces:
Sleeping
Sleeping
File size: 2,883 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 |
"""Test Weaviate functionality."""
import logging
import os
from typing import Generator, Union
from uuid import uuid4
import pytest
from weaviate import Client
from langchain.docstore.document import Document
from langchain.retrievers.weaviate_hybrid_search import WeaviateHybridSearchRetriever
logging.basicConfig(level=logging.DEBUG)
"""
cd tests/integration_tests/vectorstores/docker-compose
docker compose -f weaviate.yml up
"""
class TestWeaviateHybridSearchRetriever:
@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_get_relevant_documents(self, weaviate_url: str) -> None:
"""Test end to end construction and MRR search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
client = Client(weaviate_url)
retriever = WeaviateHybridSearchRetriever(
client=client,
index_name=f"LangChain_{uuid4().hex}",
text_key="text",
attributes=["page"],
)
for i, text in enumerate(texts):
retriever.add_documents(
[Document(page_content=text, metadata=metadatas[i])]
)
output = retriever.get_relevant_documents("foo")
assert output == [
Document(page_content="foo", metadata={"page": 0}),
Document(page_content="baz", metadata={"page": 2}),
Document(page_content="bar", metadata={"page": 1}),
]
@pytest.mark.vcr(ignore_localhost=True)
def test_get_relevant_documents_with_filter(self, weaviate_url: str) -> None:
"""Test end to end construction and MRR search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
client = Client(weaviate_url)
retriever = WeaviateHybridSearchRetriever(
client=client,
index_name=f"LangChain_{uuid4().hex}",
text_key="text",
attributes=["page"],
)
for i, text in enumerate(texts):
retriever.add_documents(
[Document(page_content=text, metadata=metadatas[i])]
)
where_filter = {"path": ["page"], "operator": "Equal", "valueNumber": 0}
output = retriever.get_relevant_documents("foo", where_filter=where_filter)
assert output == [
Document(page_content="foo", metadata={"page": 0}),
]
|