Evaluation

experimentalai

LLM and capability evaluation rubrics

pip install chp-adapter-evaluation

Auto-discovered through the chp.adapters entry point — no host config needed.

Capabilities

What this adapter exposes.

get_resultv0.1.0

Retrieve a past evaluation result by result ID.

chp.adapters.evaluation.get_result

list_evalsv0.1.0

List registered evaluation rubrics.

chp.adapters.evaluation.list_evals

register_evalv0.1.0

chp.adapters.evaluation.register_eval

run_evalv0.1.0

Run a registered rubric against inputs. Inputs and expected NEVER in evidence.

chp.adapters.evaluation.run_eval