awesome jevDIRECTORYスポンサーStar on GitHub

jevrag

ajanm007

Replaces hardcoded RAG thresholds with explicit calibrated decision points. Five primitives (retrieval stopping, chunk splitting, context selection, answer abstention, cache trust) behind one swappable state → Decision → confidence → action interface, each evaluated on real datasets with a calibration harness that reports honestly.

GitHub リポジトリ ↗検索・絞り込み
ライセンス
MIT
GitHub Stars
7
ソース確認日
—

この項目での Jev の役割

jevrag/decision.py — the `ask(state, questions) -> DecisionResult` method calls `api.typesafe.ai/v1/systemone` via the Jev backend. All five primitives in `jevrag/primitives/` route through this method.

このプロジェクトの用途

Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.

確認の範囲

各項目の確認根拠をご覧ください。掲載は独立した実行検証を意味しません。

ソースと実装

同じカテゴリのプロジェクト