rawPredict method
Perform an online prediction with an arbitrary HTTP payload.
The response includes the following HTTP headers:
-
X-Vertex-AI-Endpoint-Id: ID of theEndpointthat served this prediction. -
X-Vertex-AI-Deployed-Model-Id: ID of the Endpoint'sDeployedModelthat served this prediction.
Throws a http.ClientException if there were problems communicating with
the API service. Throws a StatusException if the API failed with a
Status message. Throws a ServiceException for any other failure.
Implementation
Future<HttpBody> rawPredict(RawPredictRequest request) async {
final url = Uri.https(_host, '/v1beta1/${request.endpoint}:rawPredict');
final response = await _client.post(url, body: request);
return HttpBody.fromJson(response);
}