community[minor]: Add relyt vector database (#20316)

Co-authored-by: kaka <kaka@zbyte-inc.cloud>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: jingsi <jingsi@leadincloud.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>

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

@@ -0,0 +1,167 @@
+"""Test Relyt functionality."""
+import os
+from typing import List
+
+from langchain_core.documents import Document
+
+from langchain_community.vectorstores.relyt import Relyt
+from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
+
+CONNECTION_STRING = Relyt.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_PORT", "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_relyt() -> None:
+    """Test end to end construction and search."""
+    texts = ["foo", "bar", "baz"]
+    docsearch = Relyt.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_relyt_with_engine_args() -> None:
+    engine_args = {"pool_recycle": 3600, "pool_size": 50}
+    """Test end to end construction and search."""
+    texts = ["foo", "bar", "baz"]
+    docsearch = Relyt.from_texts(
+        texts=texts,
+        collection_name="test_collection",
+        embedding=FakeEmbeddingsWithAdaDimension(),
+        connection_string=CONNECTION_STRING,
+        pre_delete_collection=True,
+        engine_args=engine_args,
+    )
+    output = docsearch.similarity_search("foo", k=1)
+    assert output == [Document(page_content="foo")]
+
+
+def test_relyt_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 = Relyt.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_relyt_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 = Relyt.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_relyt_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 = Relyt.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_relyt_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 = Relyt.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)  # noqa: T201
+    assert output == [(Document(page_content="baz", metadata={"page": "2"}), 4.0)]
+
+
+def test_relyt_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 = Relyt.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_relyt_delete() -> None:
+    """Test end to end construction and search."""
+    texts = ["foo", "bar", "baz"]
+    ids = ["fooid", "barid", "bazid"]
+    metadatas = [{"page": str(i)} for i in range(len(texts))]
+    docsearch = Relyt.from_texts(
+        texts=texts,
+        collection_name="test_collection_delete",
+        embedding=FakeEmbeddingsWithAdaDimension(),
+        metadatas=metadatas,
+        connection_string=CONNECTION_STRING,
+        ids=ids,
+        pre_delete_collection=True,
+    )
+    output = docsearch.similarity_search_with_score("foo", k=1, filter={"page": "2"})
+    print(output)  # noqa: T201
+    assert output == [(Document(page_content="baz", metadata={"page": "2"}), 4.0)]
+    docsearch.delete(ids=ids)
+    output = docsearch.similarity_search_with_score("foo", k=1, filter={"page": "2"})
+    assert output == []

libs/community/tests/unit_tests/vectorstores/test_imports.py

@@ -66,6 +66,7 @@ EXPECTED_ALL = [
     "Pinecone",
     "Qdrant",
     "Redis",
+    "Relyt",
     "Rockset",
     "SKLearnVectorStore",
     "SQLiteVSS",

libs/community/tests/unit_tests/vectorstores/test_indexing_docs.py

@@ -76,6 +76,7 @@ def test_compatible_vectorstore_documentation() -> None:
         "Pinecone",
         "Qdrant",
         "Redis",
+        "Relyt",
         "Rockset",
         "ScaNN",
         "SemaDB",

libs/community/tests/unit_tests/vectorstores/test_public_api.py

@@ -61,6 +61,7 @@ _EXPECTED = [
     "Pinecone",
     "Qdrant",
     "Redis",
+    "Relyt",
     "Rockset",
     "SKLearnVectorStore",
     "ScaNN",