[Java] PTransform that integrates Cloud AI Prediction functionality
- Dominant language
- Java
- Stars
- 8.7k
- Forks
- 4.7k
- Avg merge
- 1d 20h
- Merged PRs (30d)
- 196
Description
The goal is to create a PTransform that integrates Google Cloud AI Platform Prediction functionality [1] for Java SDK. The transform should work both in batch and streaming mode.
One possible solution is to utilize a `tfx_bsl` library [2] which offers a `RunInference` Beam's PTransform[2] able to get predictions from Google Cloud AI Platform Prediction via cross-language.
[1] [https://cloud.google.com/ai-platform/prediction/docs/](https://cloud.google.com/ai-platform/prediction/docs/)
[2] [https://github.com/tensorflow/tfx-bsl/blob/ecec31b2152fc73f4c26f5a5db86173cfcf25c99/tfx_bsl/beam/run_inference.py#L99](https://github.com/tensorflow/tfx-bsl/blob/ecec31b2152fc73f4c26f5a5db86173cfcf25c99/tfx_bsl/beam/run_inference.py#L99)
Imported from Jira [BEAM-9501](https://issues.apache.org/jira/browse/BEAM-9501). Original Jira may contain additional context.
Reported by: kamilwu.
Subtask of issue #20000
Contributor guide
Assessment
This issue has not been assessed yet.