Spaces:
Sleeping
Sleeping
File size: 5,467 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 |
"""Test PGVector functionality."""
import os
from typing import List
from sqlalchemy.orm import Session
from langchain.docstore.document import Document
from langchain.vectorstores.analyticdb import AnalyticDB
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
CONNECTION_STRING = AnalyticDB.connection_string_from_db_params(
driver=os.environ.get("PG_DRIVER", "psycopg2cffi"),
host=os.environ.get("PG_HOST", "localhost"),
port=int(os.environ.get("PG_HOST", "5432")),
database=os.environ.get("PG_DATABASE", "postgres"),
user=os.environ.get("PG_USER", "postgres"),
password=os.environ.get("PG_PASSWORD", "postgres"),
)
ADA_TOKEN_COUNT = 1536
class FakeEmbeddingsWithAdaDimension(FakeEmbeddings):
"""Fake embeddings functionality for testing."""
def embed_documents(self, texts: List[str]) -> List[List[float]]:
"""Return simple embeddings."""
return [
[float(1.0)] * (ADA_TOKEN_COUNT - 1) + [float(i)] for i in range(len(texts))
]
def embed_query(self, text: str) -> List[float]:
"""Return simple embeddings."""
return [float(1.0)] * (ADA_TOKEN_COUNT - 1) + [float(0.0)]
def test_analyticdb() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
docsearch = AnalyticDB.from_texts(
texts=texts,
collection_name="test_collection",
embedding=FakeEmbeddingsWithAdaDimension(),
connection_string=CONNECTION_STRING,
pre_delete_collection=True,
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
def test_analyticdb_with_metadatas() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": str(i)} for i in range(len(texts))]
docsearch = AnalyticDB.from_texts(
texts=texts,
collection_name="test_collection",
embedding=FakeEmbeddingsWithAdaDimension(),
metadatas=metadatas,
connection_string=CONNECTION_STRING,
pre_delete_collection=True,
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo", metadata={"page": "0"})]
def test_analyticdb_with_metadatas_with_scores() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": str(i)} for i in range(len(texts))]
docsearch = AnalyticDB.from_texts(
texts=texts,
collection_name="test_collection",
embedding=FakeEmbeddingsWithAdaDimension(),
metadatas=metadatas,
connection_string=CONNECTION_STRING,
pre_delete_collection=True,
)
output = docsearch.similarity_search_with_score("foo", k=1)
assert output == [(Document(page_content="foo", metadata={"page": "0"}), 0.0)]
def test_analyticdb_with_filter_match() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": str(i)} for i in range(len(texts))]
docsearch = AnalyticDB.from_texts(
texts=texts,
collection_name="test_collection_filter",
embedding=FakeEmbeddingsWithAdaDimension(),
metadatas=metadatas,
connection_string=CONNECTION_STRING,
pre_delete_collection=True,
)
output = docsearch.similarity_search_with_score("foo", k=1, filter={"page": "0"})
assert output == [(Document(page_content="foo", metadata={"page": "0"}), 0.0)]
def test_analyticdb_with_filter_distant_match() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": str(i)} for i in range(len(texts))]
docsearch = AnalyticDB.from_texts(
texts=texts,
collection_name="test_collection_filter",
embedding=FakeEmbeddingsWithAdaDimension(),
metadatas=metadatas,
connection_string=CONNECTION_STRING,
pre_delete_collection=True,
)
output = docsearch.similarity_search_with_score("foo", k=1, filter={"page": "2"})
print(output)
assert output == [(Document(page_content="baz", metadata={"page": "2"}), 4.0)]
def test_analyticdb_with_filter_no_match() -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": str(i)} for i in range(len(texts))]
docsearch = AnalyticDB.from_texts(
texts=texts,
collection_name="test_collection_filter",
embedding=FakeEmbeddingsWithAdaDimension(),
metadatas=metadatas,
connection_string=CONNECTION_STRING,
pre_delete_collection=True,
)
output = docsearch.similarity_search_with_score("foo", k=1, filter={"page": "5"})
assert output == []
def test_analyticdb_collection_with_metadata() -> None:
"""Test end to end collection construction"""
pgvector = AnalyticDB(
collection_name="test_collection",
collection_metadata={"foo": "bar"},
embedding_function=FakeEmbeddingsWithAdaDimension(),
connection_string=CONNECTION_STRING,
pre_delete_collection=True,
)
session = Session(pgvector.connect())
collection = pgvector.get_collection(session)
if collection is None:
assert False, "Expected a CollectionStore object but received None"
else:
assert collection.name == "test_collection"
assert collection.cmetadata == {"foo": "bar"}
|