The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
Neo4j: Update with non-deprecated cypher methods, and new method to associate relationship embeddings (#23725)
Rafael Pereiracf28708e7b70
diff --git a/libs/community/langchain_community/vectorstores/neo4j_vector.py b/libs/community/langchain_community/vectorstores/neo4j_vector.pyindex caefda2042..e083f3ba3e 100644--- a/libs/community/langchain_community/vectorstores/neo4j_vector.py+++ b/libs/community/langchain_community/vectorstores/neo4j_vector.py@@ -854,11 +854,11 @@ class Neo4jVector(VectorStore):"CALL { WITH row "f"MERGE (c:`{self.node_label}` {{id: row.id}}) ""WITH c, row "- f"CALL db.create.setVectorProperty(c, "+ f"CALL db.create.setNodeVectorProperty(c, "f"'{self.embedding_node_property}', row.embedding) "- "YIELD node "f"SET c.`{self.text_node_property}` = row.text "- "SET c += row.metadata } IN TRANSACTIONS OF 1000 ROWS"+ "SET c += row.metadata "+ "} IN TRANSACTIONS OF 1000 ROWS ")parameters = {@@ -1462,9 +1462,9 @@ class Neo4jVector(VectorStore):"UNWIND $data AS row "f"MATCH (n:`{node_label}`) ""WHERE elementId(n) = row.id "- f"CALL db.create.setVectorProperty(n, "+ f"CALL db.create.setNodeVectorProperty(n, "f"'{embedding_node_property}', row.embedding) "- "YIELD node RETURN count(*)",+ "RETURN count(*)",params=params,)# If embedding calculation should be stoppeddiff --git a/libs/community/tests/integration_tests/vectorstores/test_neo4jvector.py b/libs/community/tests/integration_tests/vectorstores/test_neo4jvector.pyindex 50869b985f..761450f4a9 100644--- a/libs/community/tests/integration_tests/vectorstores/test_neo4jvector.py+++ b/libs/community/tests/integration_tests/vectorstores/test_neo4jvector.py@@ -199,7 +199,10 @@ def test_neo4jvector_with_metadatas_with_scores() -> None:password=password,pre_delete_collection=True,)- output = docsearch.similarity_search_with_score("foo", k=1)+ output = [+ (doc, round(score, 1))+ for doc, score in docsearch.similarity_search_with_score("foo", k=1)+ ]assert output == [(Document(page_content="foo", metadata={"page": "0"}), 1.0)]drop_vector_indexes(docsearch)