jrmccluskey opened a new issue, #36253: URL: https://github.com/apache/beam/issues/36253
### What would you like to happen? With the introduction of remote inference in the Python SDK (making requests to an external service for machine learning inference rather than performing that work on-worker) there has been an increasing interest in providing this in a native Java format. RunInference is currently enabled in Java via cross-language; however, because remote inference is not on-worker, there is no real requirement to have the pipeline code operate in Java. A native Java implementation of the RemoteModelHandler class, which accepts arbitrary clients and request code, would fulfill this need. ### Issue Priority Priority: 2 (default / most feature requests should be filed as P2) ### Issue Components - [ ] Component: Python SDK - [x] 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 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
