Knowledge graph configuration

Available on the Enterprise Edition only.

When AI_DATA_ACCESS_CLUSTER_ENABLED is set to false, the V4 agent can still serve metadata-based capabilities (dataset discovery, schema lookups, and KG search) as long as you have configured the knowledge graph service URL and model. Without this configuration, the agent will fail to call KG tools even when the knowledge graph has been indexed.

Prerequisites

Kubernetes access to the namespace where Prophecy is deployed
An existing and successfully indexed knowledge graph

Configure the knowledge graph service

Update the sql-sandbox-config-map to specify the Claude model and knowledge graph service URL. If the ConfigMap already exists, append the keys under data. Replace <namespace> with your actual namespace.

apiVersion: v1
kind: ConfigMap
metadata:
  name: sql-sandbox-config-map
  namespace: <namespace>
data:
  CLAUDE_MODEL: claude-opus-4-5
  KNOWLEDGE_GRAPH_BASE_URL: http://knowledge-graph-service.<namespace>.svc.cluster.local:50055

Apply the configuration:

kubectl apply -f <filename>.yaml

Then restart the orchestrator to pick up the changes:

kubectl -n <namespace> rollout restart deploy orchestrator-<namespace>

After restarting, verify that the agent can resolve dataset and schema queries before closing your session. See Agent behavior when data access is disabled for expected behavior.

Platform

Setup

Management

Help and resources

Prerequisites

Configure the knowledge graph service

​Prerequisites

​Configure the knowledge graph service

Prerequisites

Configure the knowledge graph service