Evaluators

def check_length(result):
    """Check if output meets minimum length."""
    length = len(result.output)
    return {
        "key": "length",
        "passed": length >= 50,
        "notes": f"Length: {length} characters"
    }

@eval(input="Explain recursion", dataset="demo", evaluators=[check_length])
async def test_response(ctx: EvalContext):
    ctx.output = await my_agent(ctx.input)

def check_format(result):
    is_json = result.output.startswith("{")
    return {"key": "format", "passed": is_json}

def check_keywords(result):
    keywords = ["therefore", "because", "however"]
    found = sum(1 for k in keywords if k in result.output.lower())
    return {
        "key": "reasoning",
        "value": found / len(keywords),
        "notes": f"Found {found}/{len(keywords)} reasoning words"
    }

def check_no_hallucination(result):
    # Your hallucination detection logic
    has_citation = "[source]" in result.output
    return {"key": "grounded", "passed": has_citation}

@eval(input="Why is the sky blue?", dataset="qa", evaluators=[check_format, check_keywords, check_no_hallucination])
async def test_answer(ctx: EvalContext):
    ctx.output = await my_agent(ctx.input)

def exact_match(result):
    """Check exact match with reference."""
    if result.reference is None:
        return None  # Skip if no reference

    matches = result.output.strip() == result.reference.strip()
    return {
        "key": "exact_match",
        "passed": matches,
        "notes": "Exact match" if matches else "Mismatch"
    }

def semantic_similarity(result):
    """Check semantic similarity using embeddings."""
    if result.reference is None:
        return None

    similarity = compute_similarity(result.output, result.reference)
    return {
        "key": "semantic",
        "value": similarity,
        "passed": similarity > 0.8,
        "notes": f"Similarity: {similarity:.2f}"
    }

async def llm_judge(result):
    """Use an LLM to evaluate quality."""
    prompt = f"""
    Rate this response on a scale of 1-10:

    Question: {result.input}
    Response: {result.output}

    Return just the number.
    """

    score = int(await call_llm(prompt))
    return {
        "key": "llm_quality",
        "value": score / 10,
        "passed": score >= 7,
        "notes": f"LLM score: {score}/10"
    }

def safety_check(result):
    """Check for harmful content."""
    unsafe_patterns = ["violence", "hate", "explicit"]
    found = [p for p in unsafe_patterns if p in result.output.lower()]

    return {
        "key": "safety",
        "passed": len(found) == 0,
        "notes": f"Flagged: {found}" if found else "Safe"
    }

import json

def json_valid(result):
    """Validate JSON output."""
    try:
        parsed = json.loads(result.output)
        return {
            "key": "json_valid",
            "passed": True,
            "notes": f"Valid JSON with {len(parsed)} keys"
        }
    except json.JSONDecodeError as e:
        return {
            "key": "json_valid",
            "passed": False,
            "notes": f"Invalid JSON: {e}"
        }

# evaluators.py

def make_length_checker(min_len, max_len):
    def check(result):
        length = len(result.output)
        return {
            "key": "length",
            "passed": min_len <= length <= max_len,
            "notes": f"Length {length}, expected {min_len}-{max_len}"
        }
    return check

# Standard evaluator sets
QA_EVALUATORS = [
    exact_match,
    semantic_similarity,
    make_length_checker(50, 500),
]

SAFETY_EVALUATORS = [
    safety_check,
    toxicity_check,
    bias_check,
]

CREATIVE_EVALUATORS = [
    make_length_checker(100, 2000),
    originality_check,
    engagement_score,
]

from evaluators import QA_EVALUATORS, SAFETY_EVALUATORS

@eval(dataset="qa", evaluators=QA_EVALUATORS + SAFETY_EVALUATORS)
async def test_factual_qa(ctx: EvalContext):
    ...

async def async_evaluator(result):
    """Async evaluator for API calls."""
    response = await external_api.check(result.output)
    return {
        "key": "external_check",
        "passed": response["approved"],
        "notes": response["reason"]
    }

def conditional_evaluator(result):
    if result.reference is None:
        return None  # No score added

    # ... evaluation logic
    return {"key": "comparison", "passed": True}