Skip to content

docs: map OpenAI Evals modelgraded YAML to waza graders#280

Merged
github-actions[bot] merged 1 commit into
mainfrom
spboyer/fix-issue-14
May 23, 2026
Merged

docs: map OpenAI Evals modelgraded YAML to waza graders#280
github-actions[bot] merged 1 commit into
mainfrom
spboyer/fix-issue-14

Conversation

@spboyer

@spboyer spboyer commented May 23, 2026

Copy link
Copy Markdown
Member

This clarifies how OpenAI Evals modelgraded specs translate into Waza's grader model, so users can migrate existing eval YAML without guessing at the mapping.

What changed

  • Added a field-by-field mapping table for modelgraded -> Waza grader equivalents.
  • Added concrete translation examples for fact.yaml, closedqa.yaml, and battle.yaml.
  • Added a short cross-reference from the prompt-grader guide.

Validation

  • go test ./...
  • cd site && npm run build

Docs impact

  • Updated site/src/content/docs/guides/eval-yaml.mdx
  • Updated site/src/content/docs/guides/graders.mdx

Closes #14

Copilot AI review requested due to automatic review settings May 23, 2026 00:41
@github-actions github-actions Bot enabled auto-merge (squash) May 23, 2026 00:43

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds documentation to help users migrate OpenAI Evals modelgraded YAML specs to Waza eval/grader configuration, primarily by explaining how modelgraded fields map onto Waza’s prompt grader and task definitions.

Changes:

  • Added a field-by-field mapping table for OpenAI Evals modelgraded → Waza equivalents.
  • Added three translation examples (fact.yaml, closedqa.yaml, battle.yaml) in the eval YAML guide.
  • Added a short cross-reference in the prompt grader docs pointing readers to the eval YAML guide.
Show a summary per file
File Description
site/src/content/docs/guides/graders.mdx Adds a cross-reference noting the prompt grader is closest to OpenAI Evals modelgraded.
site/src/content/docs/guides/eval-yaml.mdx Introduces a modelgraded mapping section with a mapping table and three translation examples.

Copilot's findings

  • Files reviewed: 2/2 changed files
  • Comments generated: 6

Comment thread site/src/content/docs/guides/eval-yaml.mdx
Comment thread site/src/content/docs/guides/eval-yaml.mdx
Comment thread site/src/content/docs/guides/eval-yaml.mdx
Comment thread site/src/content/docs/guides/eval-yaml.mdx
Comment thread site/src/content/docs/guides/eval-yaml.mdx
Comment thread site/src/content/docs/guides/eval-yaml.mdx
@github-actions github-actions Bot merged commit 791bc17 into main May 23, 2026
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

feat: Map OpenAI Evals YAML format → waza graders

3 participants