Would like to put in a feature request for onnx support. This could solve a lot of requests for support of different model types in one go, e.g. xgboost vs lightgbm becomes user's choice, not an elastic ltr constraint.
Thanks.
Contributor guide
Tech stack
java
Domain
backendsearchmachine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
5
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Understanding of ONNX formatElasticsearch plugin developmentJava
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
10
Research direction
Investigate the elasticsearch learning to rank plugin architecture, particularly how model loaders are implemented for different model types (e.g., XGBoost, LightGBM). Explore the ONNX Runtime Java API to understand integration possibilities. Review existing code in the repository to identify where a new model loader would be added, likely in a package related to model inference. No linked PRs or comments provide additional context.
