Method: invoke.invoke
Stay organized with collections
Save and categorize content based on your preferences.
Full name: projects.locations.endpoints.deployedModels.invoke.invoke
Forwards arbitrary HTTP requests for both streaming and non-streaming cases. To use this method, [invokeRoutePrefix][Model.container_spec.invoke_route_prefix] must be set to allow the paths that will be specified in the request.
Endpoint
posthttps://aiplatform.googleapis.com/v1beta1/{endpoint}/deployedModels/{deployedModelId}/invoke/**
Path parameters
endpoint
string
Required. The name of the Endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
deployedModelId
string
id of the DeployedModel that serves the invoke request.
Request body
The request body contains data with the following structure:
httpBody
object (HttpBody )
The invoke method input. Supports HTTP headers and arbitrary data payload.
Response body
If successful, the response is a generic HTTP response whose format is defined by the method.