Usando AWS re:Post, accetti AWS re:Post Termini di utilizzo
AWS re:Postre:Post

getting UnsupportedOperationException: An error occurred (UnsupportedOperationException) when calling the ExecuteOpenCypherQuery operation: CALL clause is not supported in this release.

0

im trying to run this query using boto3

nep.execute_open_cypher_query( openCypherQuery="""MATCH ( n {~id: '0'} ) CALL neptune.algo.vectors.get(n) YIELD embedding AS vector CALL neptune.algo.vectors.topKByEmbedding( vector, { topK: 3 }) YIELD node, score RETURN node, score""" )

after running this query im getting UnsupportedOperationException: An error occurred (UnsupportedOperationException) when calling the ExecuteOpenCypherQuery operation: CALL clause is not supported in this release.

Argomenti
Database
Tag
Amazon Neptune
Lingua
English
lalit
posta 2 mesi fa184 visualizzazioni
1 Risposta
0
Risposta accettata

The algorithms available via the CALL clause are accessible only when using Neptune Analytics. These algorithms are not available on Neptune Database.

Neptune Database uses the concept of clusters and instances and is designed for OLTP graph workloads. https://docs.aws.amazon.com/neptune/latest/userguide/neptune-setup.html

Neptune Analytics uses the concept of a "graph" (that abstracts the backend hardware used by the service) and is designed to be used for more OLAP and ephemeral graph analytics workloads. https://docs.aws.amazon.com/neptune-analytics/latest/userguide/create-graph-using-console.html

profile pictureAWS
Taylor-AWS
con risposta 2 mesi fa
  • lalit
    2 mesi fa

    how to connect to a graph using python ne4j library.

  • Taylor-AWS
    2 mesi fa

    Socket-based connections, such as Bolt, are not supported with Neptune Analytics graphs. You'll need to use the NeptuneGraph APIs within the AWS SDK for Python (boto3): https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/neptune-graph/client/execute_query.html

  • lalit
    2 mesi fa

    can you give me some reference how to add vector embedding to one node.

  • lalit
    2 mesi fa

    response = client.execute_query( graphIdentifier='g-4c9vlm5rg5', queryString=f""" MATCH (user:User {{user_id: 'string'}}) MERGE (chunk:Chunk {{text: "{text}", , embeddings: {list(embeddings)}}}) MERGE (user)-[:Has_chunk]->(chunk) """, language='OPEN_CYPHER',

    )

    error:

    ValidationException: An error occurred (ValidationException) when calling the ExecuteQuery operation: Expected a simple literal but found CType.

  • Taylor-AWS
    2 mesi fa

    You need to use the CALL clause:

    MATCH (n) 
WHERE n.code in ['SEA', 'ANC']
CALL neptune.algo.vectors.upsert(n)
YIELD node, embedding
RETURN n.code, embedding

    Where n is the embedding you want to add. Only one embedding per node is currently supported.

Accesso non effettuato. Accedi per postare una risposta.

Una buona risposta soddisfa chiaramente la domanda, fornisce un feedback costruttivo e incoraggia la crescita professionale del richiedente.

Linee guida per rispondere alle domande

Contenuto pertinente