Response message for PredictionService.Predict.
The predictions that are the output of the predictions call. The schema of each prediction depends on the type of request.
- For a generative AI request to a Text Embedding model, see
TextEmbeddingPredictionResult - For a generative AI request to a Multimodal Embedding model, see
VisionEmbeddingModelResult - For a video generation request to a Veo model, see
VideoGenerationModelResult - For a traditional machine learning request to a deployed custom model, the schema of each prediction is defined by the model's
predictionSchemaUri.
deployedModelIdstring
id of the Endpoint's DeployedModel that served this prediction.
modelstring
Output only. The resource name of the Model which is deployed as the DeployedModel that this prediction hits.
modelVersionIdstring
Output only. The version id of the Model which is deployed as the DeployedModel that this prediction hits.
modelDisplayNamestring
Output only. The display name of the Model which is deployed as the DeployedModel that this prediction hits.
Output only. Request-level metadata returned by the model. The metadata type will be dependent upon the model implementation.
| JSON representation |
|---|
{ "predictions": [ value ], "deployedModelId": string, "model": string, "modelVersionId": string, "modelDisplayName": string, "metadata": value } |