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.
貢獻者指南
技術棧
java
領域
backendsearchmachine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
5
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
over 1 week
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
clear
前置要求
Understanding of ONNX formatElasticsearch plugin developmentJava
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
10
研究方向
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.
