# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: Evaluating RAG responses using multiple quality metrics

prompts:
  - |
    You are an internal corporate chatbot.
    Respond to this query: {{query}}
    Here is some context that you can use to write your response: {{context}}
providers:
  - openai:gpt-4.1-mini
tests:
  - vars:
      query: What is the max purchase that doesn't require approval?
      context: file://docs/reimbursement.md
    assert:
      - type: contains
        value: '$500'
      - type: factuality
        value: the employee's manager is responsible for approvals
      - type: answer-relevance
        threshold: 0.9
      - type: context-recall
        threshold: 0.9
        value: max purchase price without approval is $500. Talk to Fred before submitting anything.
      - type: context-relevance
        threshold: 0.9
      - type: context-faithfulness
        threshold: 0.9
  - vars:
      query: How many weeks is maternity leave?
      context: file://docs/maternity.md
    assert:
      - type: factuality
        value: maternity leave is 4 months
      - type: answer-relevance
        threshold: 0.9
      - type: context-recall
        threshold: 0.9
        value: The company offers 4 months of maternity leave, unless you are an elephant, in which case you get 22 months of maternity leave.
      - type: context-relevance
        threshold: 0.9
      - type: context-faithfulness
        threshold: 0.9