# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: Compare facts about a topic with llm-rubric and similar assertions

prompts:
  - 'What are three concise facts about {{topic}}?'

providers:
  - id: docker:ai/llama3.2:3B-Q4_K_M
  - id: docker:ai/gemma3:4B-Q4_K_M
  - id: docker:ai/phi4:14B-Q4_K_M
  - id: docker:ai/deepseek-r1-distill-llama:8B-Q4_K_M
    config:
      temperature: 0.1
      max_tokens: 512

tests:
  - vars:
      topic: 'whales'
    assert:
      - type: llm-rubric
        value: 'Provide at least two of these three facts: Whales are (a) mammals, (b) live in the ocean, and (c) communicate with sound.'
      - type: similar
        value: 'whales are the largest animals in the world'
        threshold: 0.6

# Use local models for grading and embeddings for similarity instead of OpenAI
defaultTest:
  options:
    provider:
      id: docker:ai/smollm3:Q4_K_M
      embedding:
        id: docker:embeddings:ai/mxbai-embed-large:335M-F16