AI · GraphQL query

aiGenerateGraphQLQuery query

Asks the AI assistant to write a Wartiva GraphQL query from a natural-language request, for the object type the thread was created with (see aiThreadCreate). Returns the assistant's message and the generated query. Each call clears the thread's earlier history before generating, so every request is answered on its own. Returns an error when the AI service is not available; check aiStatus.

Response

Returns an AiThreadEntry!

Arguments

Name Description
threadId - AiThreadId! The thread ID.
message - String! Natural language input to base the query generation on.
aiModel - AiModelInput Optionally specify AI model to utilize.

Example

Query

query aiGenerateGraphQLQuery(
  $threadId: AiThreadId!,
  $message: String!,
  $aiModel: AiModelInput
) {
  aiGenerateGraphQLQuery(
    threadId: $threadId,
    message: $message,
    aiModel: $aiModel
  ) {
    timestamp
    isFromUser
    message
  }
}

Variables

{
  "threadId": AiThreadId,
  "message": "xyz789",
  "aiModel": AiModelInput
}

Response

{
  "data": {
    "aiGenerateGraphQLQuery": {
      "timestamp": "2021-10-07T18:23:25.829Z",
      "isFromUser": false,
      "message": "abc123"
    }
  }
}

Related operations

  • aiGenerateSearchQuery query: Asks the AI assistant to turn a natural-language request into a graph search query, such as "Windows endpoints with an unencrypted disk", that can…
  • aiQueryObject query: Asks the AI assistant a natural-language question about the specific graph object the thread was created for (see aiThreadCreate with an object id).
  • aiQuerySearch query: Asks the AI assistant a natural-language question that it answers by searching the security graph, for example "which endpoints have not reported in…
  • aiThreadMessage query: Sends a message to an AI chat thread and returns the assistant's reply.