File size: 5,370 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
"""Test Chroma functionality."""
import pytest

from langchain.docstore.document import Document
from langchain.vectorstores import Chroma
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings


def test_chroma() -> None:
    """Test end to end construction and search."""
    texts = ["foo", "bar", "baz"]
    docsearch = Chroma.from_texts(
        collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()
    )
    output = docsearch.similarity_search("foo", k=1)
    assert output == [Document(page_content="foo")]


@pytest.mark.asyncio
async def test_chroma_async() -> None:
    """Test end to end construction and search."""
    texts = ["foo", "bar", "baz"]
    docsearch = Chroma.from_texts(
        collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()
    )
    output = await docsearch.asimilarity_search("foo", k=1)
    assert output == [Document(page_content="foo")]


def test_chroma_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 = Chroma.from_texts(
        collection_name="test_collection",
        texts=texts,
        embedding=FakeEmbeddings(),
        metadatas=metadatas,
    )
    output = docsearch.similarity_search("foo", k=1)
    assert output == [Document(page_content="foo", metadata={"page": "0"})]


def test_chroma_with_metadatas_with_scores() -> None:
    """Test end to end construction and scored search."""
    texts = ["foo", "bar", "baz"]
    metadatas = [{"page": str(i)} for i in range(len(texts))]
    docsearch = Chroma.from_texts(
        collection_name="test_collection",
        texts=texts,
        embedding=FakeEmbeddings(),
        metadatas=metadatas,
    )
    output = docsearch.similarity_search_with_score("foo", k=1)
    assert output == [(Document(page_content="foo", metadata={"page": "0"}), 0.0)]


def test_chroma_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]
    docsearch = Chroma.from_texts(
        collection_name="test_collection",
        texts=texts,
        embedding=FakeEmbeddings(),
        metadatas=metadatas,
    )
    output = docsearch.similarity_search("far", k=1, filter={"first_letter": "f"})
    assert output == [Document(page_content="far", metadata={"first_letter": "f"})]
    output = docsearch.similarity_search("far", k=1, filter={"first_letter": "b"})
    assert output == [Document(page_content="bar", metadata={"first_letter": "b"})]


def test_chroma_search_filter_with_scores() -> None:
    """Test end to end construction and scored search with metadata filtering."""
    texts = ["far", "bar", "baz"]
    metadatas = [{"first_letter": "{}".format(text[0])} for text in texts]
    docsearch = Chroma.from_texts(
        collection_name="test_collection",
        texts=texts,
        embedding=FakeEmbeddings(),
        metadatas=metadatas,
    )
    output = docsearch.similarity_search_with_score(
        "far", k=1, filter={"first_letter": "f"}
    )
    assert output == [
        (Document(page_content="far", metadata={"first_letter": "f"}), 0.0)
    ]
    output = docsearch.similarity_search_with_score(
        "far", k=1, filter={"first_letter": "b"}
    )
    assert output == [
        (Document(page_content="bar", metadata={"first_letter": "b"}), 1.0)
    ]


def test_chroma_with_persistence() -> None:
    """Test end to end construction and search, with persistence."""
    chroma_persist_dir = "./tests/persist_dir"
    collection_name = "test_collection"
    texts = ["foo", "bar", "baz"]
    docsearch = Chroma.from_texts(
        collection_name=collection_name,
        texts=texts,
        embedding=FakeEmbeddings(),
        persist_directory=chroma_persist_dir,
    )

    output = docsearch.similarity_search("foo", k=1)
    assert output == [Document(page_content="foo")]

    docsearch.persist()

    # Get a new VectorStore from the persisted directory
    docsearch = Chroma(
        collection_name=collection_name,
        embedding_function=FakeEmbeddings(),
        persist_directory=chroma_persist_dir,
    )
    output = docsearch.similarity_search("foo", k=1)

    # Clean up
    docsearch.delete_collection()

    # Persist doesn't need to be called again
    # Data will be automatically persisted on object deletion
    # Or on program exit


def test_chroma_mmr() -> None:
    """Test end to end construction and search."""
    texts = ["foo", "bar", "baz"]
    docsearch = Chroma.from_texts(
        collection_name="test_collection", texts=texts, embedding=FakeEmbeddings()
    )
    output = docsearch.max_marginal_relevance_search("foo", k=1)
    assert output == [Document(page_content="foo")]


def test_chroma_mmr_by_vector() -> None:
    """Test end to end construction and search."""
    texts = ["foo", "bar", "baz"]
    embeddings = FakeEmbeddings()
    docsearch = Chroma.from_texts(
        collection_name="test_collection", texts=texts, embedding=embeddings
    )
    embedded_query = embeddings.embed_query("foo")
    output = docsearch.max_marginal_relevance_search_by_vector(embedded_query, k=1)
    assert output == [Document(page_content="foo")]