Hanzo
CLIEval

Eval

16 `hanzo` commands for Eval, each calling one operation on api.hanzo.ai.

Package eval is scoring a model on your own data, with a judge you choose.

16 commands · API reference →

CommandCallsWhat it does
hanzo evals datasets items get <name>GET /v1/eval/datasets/{name}/itemsIs the examples in one of your datasets — the set is named in the path, because this collection only exists inside one.
hanzo evals datasets items create <name>POST /v1/eval/datasets/{name}/itemsWrites one graded example — its input, its expected output, free-form metadata and a status — into the dataset named in…
hanzo evals datasets get <name>GET /v1/eval/datasets/{name}Returns one dataset of the caller's org by name, together with its live item count — the one read that answers how big…
hanzo evals datasets rm <name>DELETE /v1/eval/datasets/{name}Removes the named dataset of the caller's org AND all of its examples, in one transaction.
hanzo evals datasets listGET /v1/eval/datasetsIs the datasets your org has, each with its name, description, metadata and timestamps.
hanzo evals datasets create --name <name>POST /v1/eval/datasetsWrites a dataset — the named set of graded examples a run scores a model against — under the caller's org and answers…
hanzo evals evaluators getGET /v1/eval/evaluatorsIs the judges your org has defined, each with its judge model, criteria and the score name it writes under.
hanzo evals evaluators create --name <name>POST /v1/eval/evaluatorsSaves a reusable judge for the caller's org — the judge model and the written criteria it grades against — and answers…
hanzo evals metricsGET /v1/eval/metricsIs your org's AI overview board over a window: totals (generations, prompt and completion tokens, cost in cents,…
hanzo evals rubrics getGET /v1/eval/rubricsIs the score shapes your org has declared — each name's data type, its numeric bounds and its allowed categories.
hanzo evals rubrics create --name <name>POST /v1/eval/rubricsDefines the shape of one score name for the caller's org and answers 201 with it.
hanzo evals runs getGET /v1/eval/runsIs your past runs and how they scored — the dataset and model, the judge model, how many examples were attempted and…
hanzo evals runs create --dataset <dataset> --model <model>POST /v1/eval/runsRuns a real evaluation and answers the summary when it is finished — this is synchronous work, not a job id.
hanzo evals scores getGET /v1/eval/scoresIs the score events your org has recorded, narrowed by any of name, runName and traceId.
hanzo evals scores create --name <name>POST /v1/eval/scoresFiles one score event for the caller's org and answers 201 with it.
hanzo evals tracesGET /v1/eval/tracesIs the traces behind your evaluations — one per model call an evaluation made, carrying its input, output, model and…

How is this guide?