generateContent method

Generate content with multimodal inputs.

request - The metadata request object.

Request parameters:

model - Required. The name of the publisher model requested to serve the prediction. Format: `projects/{project}/locations/{location}/publishers /

  • /models / * Value must have pattern^projects/[^/]+/locations/[^/]+/publishers/[^/]+/models/[^/]+$`.

$fields - Selector specifying which fields to include in a partial response.

Completes with a GoogleCloudAiplatformV1GenerateContentResponse.

Completes with a commons.ApiRequestError if the API endpoint returned an error.

If the used http.Client completes with an error when making a REST call, this method will complete with the same error.

Implementation

async.Future<GoogleCloudAiplatformV1GenerateContentResponse> generateContent(
  GoogleCloudAiplatformV1GenerateContentRequest request,
  core.String model, {
  core.String? $fields,
}) async {
  final body_ = convert.json.encode(request);
  final queryParams_ = <core.String, core.List<core.String>>{
    if ($fields != null) 'fields': [$fields],
  };

  final url_ = 'v1/' + core.Uri.encodeFull('$model') + ':generateContent';

  final response_ = await _requester.request(
    url_,
    'POST',
    body: body_,
    queryParams: queryParams_,
  );
  return GoogleCloudAiplatformV1GenerateContentResponse.fromJson(
      response_ as core.Map<core.String, core.dynamic>);
}