promptfoo-evaluation

A promptfooconfig.yaml declares providers (LLMs under test), prompts (templates with {{var}} placeholders), tests (input variables + assertions); promptfoo eval runs the cross-product (per pf-config).

When to use

• The repo has a promptfooconfig.yaml or the user wants to author one.
• The user needs prompt regression suites - same inputs, multiple providers, fail-on-diff.
• A CI workflow needs an eval gate on prompt or model changes.
• The team prefers vendor-neutral eval (vs OpenAI Evals' OpenAI-first posture).

Step 1 - Install

Per github.com/promptfoo/promptfoo:

npm install -g promptfoo
# or
brew install promptfoo
# or one-off
npx promptfoo@latest

Per pf-gh: "Node.js 20.20+ or 22.22+ is required for npm and npx usage."

Step 2 - First eval

Initialize from a built-in example, then run:

promptfoo init --example getting-started
cd getting-started
promptfoo eval
promptfoo view  # opens HTML report

(Commands per pf-gh.)

A minimal promptfooconfig.yaml per pf-config:

prompts:
  - file://prompt1.txt

providers:
  - openai:gpt-5-mini
  - anthropic:claude-haiku-4-5

tests:
  - vars:
      language: French
      input: Hello world
    assert:
      - type: contains-json

Provider syntax <vendor>:<model> works for OpenAI, Anthropic, Vertex (vertex:gemini-2.0-flash-exp), Ollama (ollama:llama2), and 30+ others (per pf-config).

Step 3 - Variable interpolation

Vars interpolate into prompts using {{variable}}. Arrays create combinations (per pf-config):

tests:
  - vars:
      language: [French, German, Spanish]
      input: [Hello world, Good morning]

This generates 6 test rows (3 languages × 2 inputs). Vars can also load from files:

tests:
  - vars:
      var3: file://path/to/var3.txt
      context: file://fetch_from_vector_database.py

Step 4 - Assertion catalog

Per promptfoo.dev/docs/configuration/expected-outputs/:

Deterministic (string + structure):

Custom logic:

- type: javascript
  value: 'output.length > 10'
- type: python
  value: 'file://script.py'

Text-quality metrics (default thresholds per pf-asserts):

Performance + cost:

- type: latency
  threshold: 200    # milliseconds
- type: cost
  threshold: 0.001  # dollars per response

Model-graded (LLM-as-judge):

Semantic similarity:

- type: similar
  value: 'reference text'
  threshold: 0.8   # cosine similarity via embeddings

Negation: all deterministic assertions support a not- prefix (not-equals, not-contains, not-regex, etc.) per pf-asserts.

Step 5 - defaultTest pattern

Shared assertions/vars across all tests:

defaultTest:
  vars:
    shared_var: 'shared content'
  assert:
    - type: llm-rubric
      value: does not describe self as AI
  options:
    provider: openai:gpt-5-mini-0613

tests:
  - vars:
      unique_var: value1

(Per pf-config.)

Step 6 - Output transforms

Modify LLM output before assertions execute (per pf-config):

tests:
  - vars:
      body: Hello world
    options:
      transform: output.toUpperCase()

Or load from a file:

options:
  transform: file://transform.js:customTransform

Step 7 - assert-set grouping

Group assertions and require a threshold percentage to pass (per pf-asserts):

assert:
  - type: assert-set
    threshold: 0.5   # 50% of grouped asserts must pass
    assert:
      - type: cost
        threshold: 0.001
      - type: latency
        threshold: 200

Step 8 - CI integration

Provider API keys via env vars (per pf-gh: export OPENAI_API_KEY=sk-abc123).

GitHub Actions pattern (per promptfoo.dev/docs/integrations/github-action):

- uses: promptfoo/promptfoo-action@v2
  with:
    openai-api-key: ${{ secrets.OPENAI_API_KEY }}
    config: 'promptfooconfig.yaml'
    cache-path: '~/.cache/promptfoo'
    use-config-prompts: false
    no-share: true
    promptfoo-version: 'latest'

The action posts a PR comment with regression diff vs the base branch. Caching reuses LLM responses for unchanged tests (per promptfoo.dev/docs/configuration/caching/).

Anti-patterns

Limitations

• Model-graded assertions invoke a judge LLM per test row → cost per test ≈ 2× a deterministic-only eval.
• Even seeded LLMs drift between provider model updates; pin model versions in CI to bound the regression surface.
• Promptfoo ships HTML + JSON + JUnit reporters; no native Markdown PR-comment formatter (use the GHA action for that).

References

• pf-intro - overview
• pf-config - full configuration guide
• pf-asserts - assertion catalog
• pf-gha - GitHub Action
• pf-cache - caching mechanics
• pf-gh - install commands
• openai-evals, deepeval-evaluation, ragas-evaluation - sister tools (different framework styles)
• prompt-eval-reviewer - adversarial reviewer for any of the above