Spaces:
Sleeping
Sleeping
File size: 4,943 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 |
"""Test ElasticSearch functionality."""
import logging
import os
import uuid
from typing import Generator, List, Union
import pytest
from elasticsearch import Elasticsearch
from langchain.docstore.document import Document
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
logging.basicConfig(level=logging.DEBUG)
"""
cd tests/integration_tests/vectorstores/docker-compose
docker-compose -f elasticsearch.yml up
"""
class TestElasticsearch:
@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 elasticsearch_url(self) -> Union[str, Generator[str, None, None]]:
"""Return the elasticsearch url."""
url = "http://localhost:9200"
yield url
es = Elasticsearch(hosts=url)
# Clear all indexes
index_names = es.indices.get(index="_all").keys()
for index_name in index_names:
# print(index_name)
es.indices.delete(index=index_name)
def test_similarity_search_without_metadata(self, elasticsearch_url: str) -> None:
"""Test end to end construction and search without metadata."""
texts = ["foo", "bar", "baz"]
docsearch = ElasticVectorSearch.from_texts(
texts, FakeEmbeddings(), elasticsearch_url=elasticsearch_url
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
def test_similarity_search_with_metadata(self, elasticsearch_url: str) -> None:
"""Test end to end construction and search with metadata."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = ElasticVectorSearch.from_texts(
texts,
FakeEmbeddings(),
metadatas=metadatas,
elasticsearch_url=elasticsearch_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_default_index_from_documents(
self,
documents: List[Document],
embedding_openai: OpenAIEmbeddings,
elasticsearch_url: str,
) -> None:
"""This test checks the construction of a default
ElasticSearch index using the 'from_documents'."""
elastic_vector_search = ElasticVectorSearch.from_documents(
documents=documents,
embedding=embedding_openai,
elasticsearch_url=elasticsearch_url,
)
search_result = elastic_vector_search.similarity_search("sharks")
print(search_result)
assert len(search_result) != 0
@pytest.mark.vcr(ignore_localhost=True)
def test_custom_index_from_documents(
self,
documents: List[Document],
embedding_openai: OpenAIEmbeddings,
elasticsearch_url: str,
) -> None:
"""This test checks the construction of a custom
ElasticSearch index using the 'from_documents'."""
index_name = f"custom_index_{uuid.uuid4().hex}"
elastic_vector_search = ElasticVectorSearch.from_documents(
documents=documents,
embedding=embedding_openai,
elasticsearch_url=elasticsearch_url,
index_name=index_name,
)
es = Elasticsearch(hosts=elasticsearch_url)
index_names = es.indices.get(index="_all").keys()
assert index_name in index_names
search_result = elastic_vector_search.similarity_search("sharks")
print(search_result)
assert len(search_result) != 0
@pytest.mark.vcr(ignore_localhost=True)
def test_custom_index_add_documents(
self,
documents: List[Document],
embedding_openai: OpenAIEmbeddings,
elasticsearch_url: str,
) -> None:
"""This test checks the construction of a custom
ElasticSearch index using the 'add_documents'."""
index_name = f"custom_index_{uuid.uuid4().hex}"
elastic_vector_search = ElasticVectorSearch(
embedding=embedding_openai,
elasticsearch_url=elasticsearch_url,
index_name=index_name,
)
es = Elasticsearch(hosts=elasticsearch_url)
elastic_vector_search.add_documents(documents)
index_names = es.indices.get(index="_all").keys()
assert index_name in index_names
search_result = elastic_vector_search.similarity_search("sharks")
print(search_result)
assert len(search_result) != 0
def test_custom_index_add_documents_to_exists_store(self) -> None:
# TODO: implement it
pass
|