community: update Memgraph integration (#27017)

**Description:**
- **Memgraph** no longer relies on `Neo4jGraphStore` but **implements
`GraphStore`**, just like other graph databases.
- **Memgraph** no longer relies on `GraphQAChain`, but implements
`MemgraphQAChain`, just like other graph databases.
- The refresh schema procedure has been updated to try using `SHOW
SCHEMA INFO`. The fallback uses Cypher queries (a combination of schema
and Cypher) → **LangChain integration no longer relies on MAGE
library**.
- The **schema structure** has been reformatted. Regardless of the
procedures used to get schema, schema structure is the same.
- The `add_graph_documents()` method has been implemented. It transforms
`GraphDocument` into Cypher queries and creates a graph in Memgraph. It
implements the ability to use `baseEntityLabel` to improve speed
(`baseEntityLabel` has an index on the `id` property). It also
implements the ability to include sources by creating a `MENTIONS`
relationship to the source document.
- Jupyter Notebook for Memgraph has been updated.
- **Issue:** /
- **Dependencies:** /
- **Twitter handle:** supe_katarina (DX Engineer @ Memgraph)

Closes #25606

libs/community/tests/integration_tests/graphs/test_memgraph.py

@@ -1,24 +1,44 @@
 import os
 
+from langchain_core.documents import Document
+
 from langchain_community.graphs import MemgraphGraph
+from langchain_community.graphs.graph_document import GraphDocument, Node, Relationship
+from langchain_community.graphs.memgraph_graph import NODE_PROPERTIES_QUERY, REL_QUERY
+
+test_data = [
+    GraphDocument(
+        nodes=[Node(id="foo", type="foo"), Node(id="bar", type="bar")],
+        relationships=[
+            Relationship(
+                source=Node(id="foo", type="foo"),
+                target=Node(id="bar", type="bar"),
+                type="REL",
+            )
+        ],
+        source=Document(page_content="source document"),
+    )
+]
 
 
 def test_cypher_return_correct_schema() -> None:
     """Test that chain returns direct results."""
+
     url = os.environ.get("MEMGRAPH_URI", "bolt://localhost:7687")
     username = os.environ.get("MEMGRAPH_USERNAME", "")
     password = os.environ.get("MEMGRAPH_PASSWORD", "")
+
     assert url is not None
     assert username is not None
     assert password is not None
 
-    graph = MemgraphGraph(
-        url=url,
-        username=username,
-        password=password,
-    )
-    # Delete all nodes in the graph
-    graph.query("MATCH (n) DETACH DELETE n")
+    graph = MemgraphGraph(url=url, username=username, password=password)
+
+    # Drop graph
+    graph.query("STORAGE MODE IN_MEMORY_ANALYTICAL")
+    graph.query("DROP GRAPH")
+    graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL")
+
     # Create two nodes and a relationship
     graph.query(
         """
@@ -31,32 +51,123 @@ def test_cypher_return_correct_schema() -> None:
     )
     # Refresh schema information
     graph.refresh_schema()
-    relationships = graph.query(
-        "CALL llm_util.schema('raw') YIELD schema "
-        "WITH schema.relationships AS relationships "
-        "UNWIND relationships AS relationship "
-        "RETURN relationship['start'] AS start, "
-        "relationship['type'] AS type, "
-        "relationship['end'] AS end "
-        "ORDER BY start, type, end;"
-    )
 
-    node_props = graph.query(
-        "CALL llm_util.schema('raw') YIELD schema "
-        "WITH schema.node_props AS nodes "
-        "WITH nodes['LabelA'] AS properties "
-        "UNWIND properties AS property "
-        "RETURN property['property'] AS prop, "
-        "property['type'] AS type "
-        "ORDER BY prop ASC;"
-    )
+    node_properties = graph.query(NODE_PROPERTIES_QUERY)
+    relationships = graph.query(REL_QUERY)
 
-    expected_relationships = [
-        {"start": "LabelA", "type": "REL_TYPE", "end": "LabelB"},
-        {"start": "LabelA", "type": "REL_TYPE", "end": "LabelC"},
+    expected_node_properties = [
+        {
+            "output": {
+                "labels": ":`LabelA`",
+                "properties": [{"key": "property_a", "types": ["String"]}],
+            }
+        },
+        {"output": {"labels": ":`LabelB`", "properties": [{"key": "", "types": []}]}},
+        {"output": {"labels": ":`LabelC`", "properties": [{"key": "", "types": []}]}},
     ]
 
-    expected_node_props = [{"prop": "property_a", "type": "str"}]
+    expected_relationships = [
+        {
+            "start_node_labels": ["LabelA"],
+            "rel_type": "REL_TYPE",
+            "end_node_labels": ["LabelC"],
+            "properties_info": [["rel_prop", "STRING"]],
+        },
+        {
+            "start_node_labels": ["LabelA"],
+            "rel_type": "REL_TYPE",
+            "end_node_labels": ["LabelB"],
+            "properties_info": [],
+        },
+    ]
 
+    graph.close()
+
+    assert node_properties == expected_node_properties
     assert relationships == expected_relationships
-    assert node_props == expected_node_props
+
+
+def test_add_graph_documents() -> None:
+    """Test that Memgraph correctly imports graph document."""
+    url = os.environ.get("MEMGRAPH_URI", "bolt://localhost:7687")
+    username = os.environ.get("MEMGRAPH_USERNAME", "")
+    password = os.environ.get("MEMGRAPH_PASSWORD", "")
+
+    assert url is not None
+    assert username is not None
+    assert password is not None
+
+    graph = MemgraphGraph(
+        url=url, username=username, password=password, refresh_schema=False
+    )
+    # Drop graph
+    graph.query("STORAGE MODE IN_MEMORY_ANALYTICAL")
+    graph.query("DROP GRAPH")
+    graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL")
+    # Create KG
+    graph.add_graph_documents(test_data)
+    output = graph.query("MATCH (n) RETURN labels(n) AS label, count(*) AS count")
+    # Close the connection
+    graph.close()
+    assert output == [{"label": ["bar"], "count": 1}, {"label": ["foo"], "count": 1}]
+
+
+def test_add_graph_documents_base_entity() -> None:
+    """Test that Memgraph correctly imports graph document with Entity label."""
+    url = os.environ.get("MEMGRAPH_URI", "bolt://localhost:7687")
+    username = os.environ.get("MEMGRAPH_USERNAME", "")
+    password = os.environ.get("MEMGRAPH_PASSWORD", "")
+
+    assert url is not None
+    assert username is not None
+    assert password is not None
+
+    graph = MemgraphGraph(
+        url=url, username=username, password=password, refresh_schema=False
+    )
+    # Drop graph
+    graph.query("STORAGE MODE IN_MEMORY_ANALYTICAL")
+    graph.query("DROP GRAPH")
+    graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL")
+    # Create KG
+    graph.add_graph_documents(test_data, baseEntityLabel=True)
+    output = graph.query("MATCH (n) RETURN labels(n) AS label, count(*) AS count")
+
+    # Close the connection
+    graph.close()
+
+    assert output == [
+        {"label": ["__Entity__", "bar"], "count": 1},
+        {"label": ["__Entity__", "foo"], "count": 1},
+    ]
+
+
+def test_add_graph_documents_include_source() -> None:
+    """Test that Memgraph correctly imports graph document with source included."""
+    url = os.environ.get("MEMGRAPH_URI", "bolt://localhost:7687")
+    username = os.environ.get("MEMGRAPH_USERNAME", "")
+    password = os.environ.get("MEMGRAPH_PASSWORD", "")
+
+    assert url is not None
+    assert username is not None
+    assert password is not None
+
+    graph = MemgraphGraph(
+        url=url, username=username, password=password, refresh_schema=False
+    )
+    # Drop graph
+    graph.query("STORAGE MODE IN_MEMORY_ANALYTICAL")
+    graph.query("DROP GRAPH")
+    graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL")
+    # Create KG
+    graph.add_graph_documents(test_data, include_source=True)
+    output = graph.query("MATCH (n) RETURN labels(n) AS label, count(*) AS count")
+
+    # Close the connection
+    graph.close()
+
+    assert output == [
+        {"label": ["bar"], "count": 1},
+        {"label": ["foo"], "count": 1},
+        {"label": ["Document"], "count": 1},
+    ]