Response message for PredictionService.Predict
.
The format of each prediction is model-dependent. For Vertex AI Generative AI models, the prediction schema can be one of the following types:
- Text Embedding:
TextEmbeddingPredictionResult
- Multimodal Embedding:
VisionEmbeddingModelResult
- Imagen for image generation and editing:
VisionGenerativeModelResult
- Imagen for virtual try-on:
VirtualTryOnModelResultProto
- Imagen for visual question answering (VQA):
VisionReasoningModelResult
- Veo for video generation:
VideoGenerationModelResult
deployedModelId
string
id of the Endpoint's DeployedModel that served this prediction.
model
string
Output only. The resource name of the Model which is deployed as the DeployedModel that this prediction hits.
modelVersionId
string
Output only. The version id of the Model which is deployed as the DeployedModel that this prediction hits.
modelDisplayName
string
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 } |