neo4j.exceptions.CypherTypeError: {code: Neo.ClientError.Statement.TypeError} {message: Property values can only be of primitive types or arrays thereof. Encountered:
i use Neo4j Browser version: [5.26.2] Neo4j Server version: [5.24.0]
warning when:
await graphiti.build_indices_and_constraints(delete_existing=True)
Received notification from DBMS server: {severity: WARNING} {code: Neo.ClientNotification.Statement.UnknownPropertyKeyWarning} {category: UNRECOGNIZED} {title: The provided property key is not in the database} {description: One of the property names in your query is not available in the database, make sure you didn't misspell it or that the label is available when you run this statement in your application (the missing property name is: fact_embedding)} {position: line: 15, column: 23, offset: 760} for query: '\n MATCH (n:Entity)-[r:RELATES_TO]->(m:Entity)\n WHERE r.group_id IN $group_ids\nAND (m.uuid IN [$source_uuid, $target_uuid])\nWITH DISTINCT r, vector.similarity.cosine(r.fact_embedding, $search_vector) AS score\n WHERE score > $min_score\n RETURN\n r.uuid AS uuid,\n r.group_id AS group_id,\n startNode(r).uuid AS source_node_uuid,\n endNode(r).uuid AS target_node_uuid,\n r.created_at AS created_at,\n r.name AS name,\n r.fact AS fact,\n r.fact_embedding AS fact_embedding,\n r.episodes AS episodes,\n r.expired_at AS expired_at,\n r.valid_at AS valid_at,\n r.invalid_at AS invalid_at\n ORDER BY score DESC\n LIMIT $limit\n '
error when
await graphiti.add_episode( name=f"对话 {i}", episode_body=episode, source=EpisodeType.text, source_description="podcast", reference_time=datetime.now(timezone.utc) )
neo4j.exceptions.CypherTypeError: {code: Neo.ClientError.Statement.TypeError} {message: Property values can only be of primitive types or arrays thereof. Encountered: Map{summary -> Map{description -> String("他指马云,是阿里巴巴的创始人,之前是一个英语老师,在1996 - 2000年期间担任英语老师。"), title -> String("Summary"), type -> String("string")}}.}
help please
You should be using Neo4j 5.26.2 for the DB as well.
Do you have your embedder client set up and is it properly creating embeddings?