langchain/tests/integration_tests/vectorstores/test_opensearch.py
Naveen Tatikonda 0118706fd6
Add Support for OpenSearch Vector database (#1191)
### Description
This PR adds a wrapper which adds support for the OpenSearch vector
database. Using opensearch-py client we are ingesting the embeddings of
given text into opensearch cluster using Bulk API. We can perform the
`similarity_search` on the index using the 3 popular searching methods
of OpenSearch k-NN plugin:

- `Approximate k-NN Search` use approximate nearest neighbor (ANN)
algorithms from the [nmslib](https://github.com/nmslib/nmslib),
[faiss](https://github.com/facebookresearch/faiss), and
[Lucene](https://lucene.apache.org/) libraries to power k-NN search.
- `Script Scoring` extends OpenSearch’s script scoring functionality to
execute a brute force, exact k-NN search.
- `Painless Scripting` adds the distance functions as painless
extensions that can be used in more complex combinations. Also, supports
brute force, exact k-NN search like Script Scoring.

### Issues Resolved 
https://github.com/hwchase17/langchain/issues/1054

---------

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
2023-02-20 18:39:34 -08:00

129 lines
4.7 KiB
Python

"""Test OpenSearch functionality."""
import pytest
from langchain.docstore.document import Document
from langchain.vectorstores.opensearch_vector_search import (
PAINLESS_SCRIPTING_SEARCH,
SCRIPT_SCORING_SEARCH,
OpenSearchVectorSearch,
)
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
DEFAULT_OPENSEARCH_URL = "http://localhost:9200"
texts = ["foo", "bar", "baz"]
def test_opensearch() -> None:
"""Test end to end indexing and search using Approximate Search."""
docsearch = OpenSearchVectorSearch.from_texts(
texts, FakeEmbeddings(), opensearch_url=DEFAULT_OPENSEARCH_URL
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
def test_opensearch_with_metadatas() -> None:
"""Test end to end indexing and search with metadata."""
metadatas = [{"page": i} for i in range(len(texts))]
docsearch = OpenSearchVectorSearch.from_texts(
texts,
FakeEmbeddings(),
metadatas=metadatas,
opensearch_url=DEFAULT_OPENSEARCH_URL,
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo", metadata={"page": 0})]
def test_add_text() -> None:
"""Test adding additional text elements to existing index."""
text_input = ["test", "add", "text", "method"]
metadatas = [{"page": i} for i in range(len(text_input))]
docsearch = OpenSearchVectorSearch.from_texts(
texts, FakeEmbeddings(), opensearch_url=DEFAULT_OPENSEARCH_URL
)
docids = OpenSearchVectorSearch.add_texts(docsearch, text_input, metadatas)
assert len(docids) == len(text_input)
def test_opensearch_script_scoring() -> None:
"""Test end to end indexing and search using Script Scoring Search."""
pre_filter_val = {"bool": {"filter": {"term": {"text": "bar"}}}}
docsearch = OpenSearchVectorSearch.from_texts(
texts,
FakeEmbeddings(),
opensearch_url=DEFAULT_OPENSEARCH_URL,
is_appx_search=False,
)
output = docsearch.similarity_search(
"foo", k=1, search_type=SCRIPT_SCORING_SEARCH, pre_filter=pre_filter_val
)
assert output == [Document(page_content="bar")]
def test_add_text_script_scoring() -> None:
"""Test adding additional text elements and validating using Script Scoring."""
text_input = ["test", "add", "text", "method"]
metadatas = [{"page": i} for i in range(len(text_input))]
docsearch = OpenSearchVectorSearch.from_texts(
text_input,
FakeEmbeddings(),
opensearch_url=DEFAULT_OPENSEARCH_URL,
is_appx_search=False,
)
OpenSearchVectorSearch.add_texts(docsearch, texts, metadatas)
output = docsearch.similarity_search(
"add", k=1, search_type=SCRIPT_SCORING_SEARCH, space_type="innerproduct"
)
assert output == [Document(page_content="test")]
def test_opensearch_painless_scripting() -> None:
"""Test end to end indexing and search using Painless Scripting Search."""
pre_filter_val = {"bool": {"filter": {"term": {"text": "baz"}}}}
docsearch = OpenSearchVectorSearch.from_texts(
texts,
FakeEmbeddings(),
opensearch_url=DEFAULT_OPENSEARCH_URL,
is_appx_search=False,
)
output = docsearch.similarity_search(
"foo", k=1, search_type=PAINLESS_SCRIPTING_SEARCH, pre_filter=pre_filter_val
)
assert output == [Document(page_content="baz")]
def test_add_text_painless_scripting() -> None:
"""Test adding additional text elements and validating using Painless Scripting."""
text_input = ["test", "add", "text", "method"]
metadatas = [{"page": i} for i in range(len(text_input))]
docsearch = OpenSearchVectorSearch.from_texts(
text_input,
FakeEmbeddings(),
opensearch_url=DEFAULT_OPENSEARCH_URL,
is_appx_search=False,
)
OpenSearchVectorSearch.add_texts(docsearch, texts, metadatas)
output = docsearch.similarity_search(
"add", k=1, search_type=PAINLESS_SCRIPTING_SEARCH, space_type="cosineSimilarity"
)
assert output == [Document(page_content="test")]
def test_opensearch_invalid_search_type() -> None:
"""Test to validate similarity_search by providing invalid search_type."""
docsearch = OpenSearchVectorSearch.from_texts(
texts, FakeEmbeddings(), opensearch_url=DEFAULT_OPENSEARCH_URL
)
with pytest.raises(ValueError):
docsearch.similarity_search("foo", k=1, search_type="invalid_search_type")
def test_opensearch_embedding_size_zero() -> None:
"""Test to validate indexing when embedding size is zero."""
with pytest.raises(RuntimeError):
OpenSearchVectorSearch.from_texts(
[], FakeEmbeddings(), opensearch_url=DEFAULT_OPENSEARCH_URL
)