community[patch]: Added add_images method to SingleStoreDB vector store (#17871)

In this pull request, we introduce the add_images method to the
SingleStoreDB vector store class, expanding its capabilities to handle
multi-modal embeddings seamlessly. This method facilitates the
incorporation of image data into the vector store by associating each
image's URI with corresponding document content, metadata, and either
pre-generated embeddings or embeddings computed using the embed_image
method of the provided embedding object.

the change includes integration tests, validating the behavior of the
add_images. Additionally, we provide a notebook showcasing the usage of
this new method.

---------

Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>

libs/community/langchain_community/vectorstores/singlestoredb.py

@@ -303,6 +303,35 @@ class SingleStoreDB(VectorStore):
         finally:
             conn.close()
 
+    def add_images(
+        self,
+        uris: List[str],
+        metadatas: Optional[List[dict]] = None,
+        embeddings: Optional[List[List[float]]] = None,
+        **kwargs: Any,
+    ) -> List[str]:
+        """Run images through the embeddings and add to the vectorstore.
+
+        Args:
+            uris List[str]: File path to images.
+                Each URI will be added to the vectorstore as document content.
+            metadatas (Optional[List[dict]], optional): Optional list of metadatas.
+                Defaults to None.
+            embeddings (Optional[List[List[float]]], optional): Optional pre-generated
+                embeddings. Defaults to None.
+
+        Returns:
+            List[str]: empty list
+        """
+        # Set embeddings
+        if (
+            embeddings is None
+            and self.embedding is not None
+            and hasattr(self.embedding, "embed_image")
+        ):
+            embeddings = self.embedding.embed_image(uris=uris)
+        return self.add_texts(uris, metadatas, embeddings, **kwargs)
+
     def add_texts(
         self,
         texts: Iterable[str],

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

@@ -1,4 +1,6 @@
 """Test SingleStoreDB functionality."""
+import os
+import tempfile
 from typing import List
 
 import numpy as np
@@ -14,6 +16,7 @@ TEST_SINGLESTOREDB_URL = "root:pass@localhost:3306/db"
 TEST_SINGLE_RESULT = [Document(page_content="foo")]
 TEST_SINGLE_WITH_METADATA_RESULT = [Document(page_content="foo", metadata={"a": "b"})]
 TEST_RESULT = [Document(page_content="foo"), Document(page_content="foo")]
+TEST_IMAGES_DIR = ""
 
 try:
     import singlestoredb as s2
@@ -22,6 +25,13 @@ try:
 except ImportError:
     singlestoredb_installed = False
 
+try:
+    from langchain_experimental.open_clip import OpenCLIPEmbeddings
+
+    langchain_experimental_installed = True
+except ImportError:
+    langchain_experimental_installed = False
+
 
 def drop(table_name: str) -> None:
     with s2.connect(TEST_SINGLESTOREDB_URL) as conn:
@@ -53,6 +63,9 @@ class RandomEmbeddings(Embeddings):
     def embed_query(self, text: str) -> List[float]:
         return np.random.rand(100).tolist()
 
+    def embed_image(self, uris: List[str]) -> List[List[float]]:
+        return [np.random.rand(100).tolist() for _ in uris]
+
 
 @pytest.fixture
 def texts() -> List[str]:
@@ -156,7 +169,7 @@ def test_singlestoredb_vector_index_large() -> None:
     table_name = "test_singlestoredb_vector_index_large"
     drop(table_name)
     docsearch = SingleStoreDB.from_texts(
-        ["foo"] * 300000,
+        ["foo"] * 30,
         RandomEmbeddings(),
         distance_strategy=DistanceStrategy.EUCLIDEAN_DISTANCE,
         table_name=table_name,
@@ -444,3 +457,51 @@ def test_singlestoredb_as_retriever(texts: List[str]) -> None:
         ),
     ]
     drop(table_name)
+
+
+@pytest.mark.skipif(not singlestoredb_installed, reason="singlestoredb not installed")
+def test_singlestoredb_add_image(texts: List[str]) -> None:
+    """Test adding images"""
+    table_name = "test_singlestoredb_add_image"
+    drop(table_name)
+    docsearch = SingleStoreDB(
+        RandomEmbeddings(),
+        table_name=table_name,
+        host=TEST_SINGLESTOREDB_URL,
+    )
+    temp_files = []
+    for _ in range(3):
+        temp_file = tempfile.NamedTemporaryFile(delete=False)
+        temp_file.write(b"foo")
+        temp_file.close()
+        temp_files.append(temp_file.name)
+
+    docsearch.add_images(temp_files)
+    output = docsearch.similarity_search("foo", k=1)
+    assert output[0].page_content in temp_files
+    drop(table_name)
+
+
+@pytest.mark.skipif(not singlestoredb_installed, reason="singlestoredb not installed")
+@pytest.mark.skipif(
+    not langchain_experimental_installed, reason="langchain_experimental not installed"
+)
+def test_singestoredb_add_image2() -> None:
+    table_name = "test_singlestoredb_add_images"
+    drop(table_name)
+    docsearch = SingleStoreDB(
+        OpenCLIPEmbeddings(),
+        table_name=table_name,
+        host=TEST_SINGLESTOREDB_URL,
+    )
+    image_uris = sorted(
+        [
+            os.path.join(TEST_IMAGES_DIR, image_name)
+            for image_name in os.listdir(TEST_IMAGES_DIR)
+            if image_name.endswith(".jpg")
+        ]
+    )
+    docsearch.add_images(image_uris)
+    output = docsearch.similarity_search("horse", k=1)
+    assert "horse" in output[0].page_content
+    drop(table_name)