Skip to content

Latest commit

 

History

History

README.md

Configuration Presets

Config Prompts Judge Use case
default.yaml All Enabled Standard evaluation
quick_test.yaml 5 Disabled Fast smoke test
large_scale.yaml All Enabled 1000+ prompts (higher concurrency, longer timeouts)
foundry.yaml Foundry cloud eval settings (graders, thresholds)

Edit default.yaml to set your endpoint URLs, baseline model, and pricing. Environment variables (${VAR}) are resolved from .env.

Prompt Templates

  • judge_prompts/ — Local LLM-as-judge prompt templates (absolute and pairwise)
  • grader_prompts/ — Foundry cloud grader prompt templates (quality_absolute and quality_pairwise)