Benchmark reference
Run retrieval and optional faithfulness benchmarks, gating CI on configurable thresholds. Supports custom query files and optional faithfulness scoring via --with-faithfulness.
Functions
| Function | Parameters | Returns | Description |
|---|---|---|---|
main |
argv: list[str] | None = None |
int |
Runs the benchmark suite and returns 0 on success. |
Source files
src/attune_rag/benchmark.py
Tags
benchmark, ci, precision, recall, quality