apache / apache/beam

[Java] PTransform that integrates Cloud AI Prediction functionality

Open
#20,001 0 comments 0 reactions 0 assignees View on GitHub
gcp io java P3 sub-task
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.