plano/demos/advanced/model_choice_test_harness/evals_summarize.yaml

11 lines
283 B
YAML

# evals_summarize.yaml
task: summarize
fixtures:
- id: sum-001
input: "Thread about a billing dispute…"
must_include: ["invoice"]
schema: SummarizeOut
- id: sum-002
input: "Thread about a shipping delay…"
must_include: ["status"]
schema: SummarizeOut