serverStreamingPredict method
Perform a server-side streaming online prediction request for Vertex LLM streaming.
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
Stream<StreamingPredictResponse> serverStreamingPredict(
StreamingPredictRequest request,
) {
final url = Uri.https(
_host,
'/v1beta1/${request.endpoint}:serverStreamingPredict',
);
return _client
.postStreaming(url, body: request)
.map(StreamingPredictResponse.fromJson);
}