feat: add Google BigQueryVectorSearch in vectorstore (#14829)

BigQuery vector search lets you use GoogleSQL to do semantic search,
using vector indexes for fast but approximate results, or using brute
force for exact results.

This PR integrates LangChain vectorstore with BigQuery Vector Search.

<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://python.langchain.com/docs/contributing/

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

---------

Co-authored-by: Vlad Kolesnikov <vladkol@google.com>

libs/community/tests/integration_tests/vectorstores/test_bigquery_vector_search.py

@@ -0,0 +1,102 @@
+"""Test BigQuery Vector Search.
+In order to run this test, you need to install Google Cloud BigQuery SDK
+pip install google-cloud-bigquery
+Your end-user credentials would be used to make the calls (make sure you've run
+`gcloud auth login` first).
+"""
+
+import os
+import uuid
+
+import pytest
+
+from langchain_community.vectorstores.bigquery_vector_search import BigQueryVectorSearch
+from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
+
+TEST_TABLE_NAME = "langchain_test_table"
+
+
+@pytest.fixture(scope="class")
+def store(request: pytest.FixtureRequest) -> BigQueryVectorSearch:
+    """BigQueryVectorStore tests context.
+
+    In order to run this test, you define PROJECT environment variable
+    with GCP project id.
+
+    Example:
+    export PROJECT=...
+    """
+    from google.cloud import bigquery
+
+    bigquery.Client(location="US").create_dataset(
+        TestBigQueryVectorStore.dataset_name, exists_ok=True
+    )
+    TestBigQueryVectorStore.store = BigQueryVectorSearch(
+        project_id=os.environ.get("PROJECT", None),
+        embedding=FakeEmbeddings(),
+        dataset_name=TestBigQueryVectorStore.dataset_name,
+        table_name=TEST_TABLE_NAME,
+    )
+    TestBigQueryVectorStore.store.add_texts(
+        TestBigQueryVectorStore.texts, TestBigQueryVectorStore.metadatas
+    )
+
+    def teardown() -> None:
+        bigquery.Client(location="US").delete_dataset(
+            TestBigQueryVectorStore.dataset_name,
+            delete_contents=True,
+            not_found_ok=True,
+        )
+
+    request.addfinalizer(teardown)
+    return TestBigQueryVectorStore.store
+
+
+class TestBigQueryVectorStore:
+    """BigQueryVectorStore tests class."""
+
+    dataset_name = uuid.uuid4().hex
+    store: BigQueryVectorSearch
+    texts = ["apple", "ice cream", "Saturn", "candy", "banana"]
+    metadatas = [
+        {
+            "kind": "fruit",
+        },
+        {
+            "kind": "treat",
+        },
+        {
+            "kind": "planet",
+        },
+        {
+            "kind": "treat",
+        },
+        {
+            "kind": "fruit",
+        },
+    ]
+
+    def test_semantic_search(self, store: BigQueryVectorSearch) -> None:
+        """Test on semantic similarity."""
+        docs = store.similarity_search("food", k=4)
+        print(docs)
+        kinds = [d.metadata["kind"] for d in docs]
+        assert "fruit" in kinds
+        assert "treat" in kinds
+        assert "planet" not in kinds
+
+    def test_semantic_search_filter_fruits(self, store: BigQueryVectorSearch) -> None:
+        """Test on semantic similarity with metadata filter."""
+        docs = store.similarity_search("food", filter={"kind": "fruit"})
+        kinds = [d.metadata["kind"] for d in docs]
+        assert "fruit" in kinds
+        assert "treat" not in kinds
+        assert "planet" not in kinds
+
+    def test_get_doc_by_filter(self, store: BigQueryVectorSearch) -> None:
+        """Test on document retrieval with metadata filter."""
+        docs = store.get_documents(filter={"kind": "fruit"})
+        kinds = [d.metadata["kind"] for d in docs]
+        assert "fruit" in kinds
+        assert "treat" not in kinds
+        assert "planet" not in kinds