community: tablestore vector store check the dimension of the embedding when writing it to store. (#28812)

Added some restrictions to a vectorstore I released in the community
before.

docs/docs/integrations/vectorstores/tablestore.ipynb

@@ -8,10 +8,11 @@
     }
    },
    "source": [
-    "# TablestoreVectorStore\n",
+    "# Tablestore\n",
     "\n",
-    "> [Tablestore](https://www.aliyun.com/product/ots) is a fully managed NoSQL cloud database service that enables storage of a massive amount of structured\n",
+    "[Tablestore](https://www.aliyun.com/product/ots) is a fully managed NoSQL cloud database service.\n",
-    "and semi-structured data.\n",
+    "\n",
+    "Tablestore enables storage of a massive amount of structured and semi-structured data.\n",
     "\n",
     "This notebook shows how to use functionality related to the `Tablestore` vector database.\n",
     "\n",

libs/community/langchain_community/vectorstores/tablestore.py

@@ -458,6 +458,11 @@ class TablestoreVectorStore(VectorStore):
             row_id = ids[i]
             text = text_list[i]
             embedding_vector = embeddings[i]
+            if len(embedding_vector) != self.__vector_dimension:
+                raise RuntimeError(
+                    "embedding vector size:%d is not the same as vector store dim:%d"
+                    % (len(embedding_vector), self.__vector_dimension)
+                )
             metadata = dict()
             if metadatas and metadatas[i]:
                 metadata = metadatas[i]

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

@@ -91,3 +91,26 @@ def test_tablestore() -> None:
     """
     search_result = store.similarity_search_with_score(query="hello world", k=2)
     assert len(search_result) == 2
+
+
+def test_tablestore_add_documents() -> None:
+    embeddings = FakeEmbeddings(size=128)
+    store = TablestoreVectorStore(
+        embedding=embeddings,
+        endpoint="http://test.a.com",
+        instance_name="test",
+        access_key_id="test",
+        access_key_secret="test",
+        vector_dimension=512,
+    )
+    doc = Document(
+        id="1",
+        page_content="1 hello world",
+        metadata={"type": "pc", "time": 2000},
+    )
+
+    try:
+        store.add_documents([doc])
+        raise RuntimeError("should failed")
+    except Exception as e:
+        assert "not the same as" in e.args[0]