Skip to content

[Feature Request]: Add "endpoint.invoke" option to VertexAIModelHandlerJSON #37132

@senim2

Description

@senim2

What would you like to happen?

There is a pre-GA feature in Vertex endpoint to use an arbitrary prediction routes and expose routes beyond /predict and /health. See docs

Is it possible to add support for this to VertexAIModelHandlerJSON?
Using VertexAIModelHandlerJSON with Vertex endpoint deployed with arbitrary prediction route currently results in error:

{
  "error": {
    "code": 400,
    "message": "Given request uri is not supported on this endpoint. Please use `/invoke${container_request_path}` to route the request to the container path. container_request_path must start with a forward slash.",
    "status": "INTERNAL"
  }
}

Thanks.

Issue Priority

Priority: 2 (default / most feature requests should be filed as P2)

Issue Components

  • Component: Python SDK
  • Component: Java SDK
  • Component: Go SDK
  • Component: Typescript SDK
  • Component: IO connector
  • Component: Beam YAML
  • Component: Beam examples
  • Component: Beam playground
  • Component: Beam katas
  • Component: Website
  • Component: Infrastructure
  • Component: Spark Runner
  • Component: Flink Runner
  • Component: Samza Runner
  • Component: Twister2 Runner
  • Component: Hazelcast Jet Runner
  • Component: Google Cloud Dataflow Runner

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions