mlflow-llm-as-a-judge-example

gistfile1.txt

professionalism = mlflow.metrics.genai.make_genai_metric(
    name="professionalism",
    definition=(
        "Professionalism refers to the use of a formal, respectful, and appropriate style of communication that is "
        "tailored to the context and audience. It often involves avoiding overly casual language, slang, or "
        "colloquialisms, and instead using clear, concise, and respectful language."
    ),
    grading_prompt=(
        "Professionalism: If the answer is written using a professional tone, below are the details for different scores: "
        "- Score 0: Language is extremely casual, informal, and may include slang or colloquialisms. Not suitable for "
        "professional contexts."
        "- Score 1: Language is casual but generally respectful and avoids strong informality or slang. Acceptable in "
        "some informal professional settings."
        "- Score 2: Language is overall formal but still have casual words/phrases. Borderline for professional contexts."
        "- Score 3: Language is balanced and avoids extreme informality or formality. Suitable for most professional contexts. "
        "- Score 4: Language is noticeably formal, respectful, and avoids casual elements. Appropriate for formal "
        "business or academic settings. "
    ),
    examples=[professionalism_example_score_2, professionalism_example_score_4],
    model="openai:/gpt-4o-mini",
    parameters={"temperature": 0.0},
    aggregations=["mean", "variance"],
    greater_is_better=True,
)