# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: Test Databricks Foundation Model APIs

prompts:
  - 'You are a helpful AI assistant. Answer the following: {{question}}'

providers:
  # Databricks pay-per-token endpoint for Llama 4
  - id: databricks:databricks-meta-llama-4-scout-instruct
    config:
      isPayPerToken: true
      temperature: 0.7
      max_tokens: 500
      # Replace with your workspace URL
      workspaceUrl: https://your-workspace.cloud.databricks.com
      # Track usage for cost attribution
      usageContext:
        project: 'promptfoo-example'
        team: 'engineering'

tests:
  - description: 'Test with a programming joke'
    vars:
      question: 'Why do programmers prefer dark mode?'
    assert:
      - type: contains-any
        value: ['light', 'eyes', 'bright', 'see', 'bugs']
      - type: llm-rubric
        value: 'Is this a funny response to a programming joke?'

  - description: 'Test creative writing'
    vars:
      question: 'Write a haiku about debugging code'
    assert:
      - type: javascript
        value: |
          // Check if it's roughly haiku format (3 lines)
          const lines = output.split('\n').filter(l => l.trim());
          return lines.length >= 3 ? 'pass' : 'fail';
      - type: llm-rubric
        value: 'Is this a valid haiku about debugging?'

  - description: 'Test knowledge about Databricks'
    vars:
      question: 'What is a Databricks Lakehouse in one sentence?'
    assert:
      - type: contains-any
        value: ['unified', 'data', 'analytics', 'warehouse', 'lake']
      - type: max-length
        value: 200