Method: endpoints.directRawPredict
Stay organized with collections
Save and categorize content based on your preferences.
Full name: projects.locations.endpoints.directRawPredict
Perform an unary online prediction request to a gRPC model server for custom containers.
Endpoint
posthttps://{service-endpoint}/v1/{endpoint}:directRawPredict
Where {service-endpoint} is one of the supported service endpoints.
Path parameters
endpointstring
Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
Request body
The request body contains data with the following structure:
methodNamestring
Fully qualified name of the API method being invoked to perform predictions.
Format: /namespace.Service/method/ Example: /tensorflow.serving.PredictionService/endpoints.predict
The prediction input.
A base64-encoded string.
Response body
Response message for PredictionService.DirectRawPredict .
If successful, the response body contains data with the following structure:
The prediction output.
A base64-encoded string.
| JSON representation |
|---|
{ "output": string } |