jevrag
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.
- Stars
- 1
- Forks
- 0
- License
- MIT
- Last commit
- 2026-09-22
What Jev does here
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.
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.