migrate_rag_engine

ArtificialIntelligenceApi.migrate_rag_engine(action, resource, role_id, _request_timeout=None, _request_auth=None, _content_type=None, _headers=None, _host_index=0)

Migrate RAG engine

Initiates RAG engine migration for knowledge bases (for example between OpenSearch and Aurora RDS). Requires action=repair and resource=knowledgebases. No request body is used.

Parameters:

  • action (str) – Operation mode; must be repair and paired with resource=knowledgebases. (required)

  • resource (str) – Target resource type; only knowledgebases is supported. (required)

  • role_id (str) – User role id (required)

  • _request_timeout (int, tuple(int, int), optional) – timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of (connection, read) timeouts.

  • _request_auth (dict, optional) – set to override the auth_settings for an a single request; this effectively ignores the authentication in the spec for a single request.

  • _content_type (str, Optional) – force content-type for the request.

  • _headers (dict, optional) – set to override the headers for a single request; this effectively ignores the headers in the spec for a single request.

  • _host_index (int, optional) – set to override the host_index for a single request; this effectively ignores the host_index in the spec for a single request.

Return type:

MigrateRagEngineResponse

Returns:

Returns the result object.

Request and Response Examples

HTTP: POST /ai

Success (HTTP 200)

RAG engine migration initiated.

Request / response example

{
  "message": "RAG engine migration initiated successfully. A detailed report will be sent to the user email notifications if SQLAI or Jobs services are enabled."
}

Errors

Documented error codes: IPV-1001, GE-1034, GE-1008.

HTTP 400

Invalid input

action or resource missing or unrecognised

{
  "Message": "IPV-1001 - Invalid or missing action/resource; expected 'configurations' or 'repair' and 'knowledgebases'"
}

HTTP 500

Something went wrong at backend. A migration rejected because another is already running, and AI services being disabled for the application, are also reported here.

Another SQL AI knowledge base operation is running

{
  "Message": "GE-1034 - A SQLAI knowledge base operation is already in progress. Please wait for it to complete before starting a new one."
}

Unexpected backend failure

{
  "Message": "GE-1008 - Could not complete the request. Please try again."
}