Share via

Logging assessments

Assessments attach structured feedback, scores, or ground truth to traces and spans for quality evaluation and improvement in MLflow.

MLflow provides two APIs:

  • mlflow.log_feedback() - Logs Feedback that evaluates your app's actual outputs or intermediate steps (e.g., "Was the response good?", ratings, comments)
  • mlflow.log_assessment() - General API for any assessment type, including Expectations that define the desired or correct outcome (ground truth) your app should have produced

This reference provides comprehensive examples of how to use these APIs.

Refer to the tracing data model for more detail about the Feedback and Expectation data models.

Examples

Running the below example will result in a trace as shown below.

View assessments in the summary

import mlflow
from mlflow.entities.assessment import (
    AssessmentSource,
    AssessmentSourceType,
    AssessmentError,
)


@mlflow.trace
def my_app(input: str) -> str:
    return input + "_output"


# Create a sample trace to demonstrate assessment logging
my_app(input="hello")

trace_id = mlflow.get_last_active_trace_id()

# Handle case where trace_id might be None
if trace_id is None:
    raise ValueError("No active trace found. Make sure to run a traced function first.")

print(f"Using trace_id: {trace_id}")


# =============================================================================
# LOG_FEEDBACK - Evaluating actual outputs and performance
# =============================================================================

# Example 1: Human rating (integer scale)
# Use case: Domain experts rating response quality on a 1-5 scale
mlflow.log_feedback(
    trace_id=trace_id,
    name="human_rating",
    value=4,  # int - rating scale feedback
    rationale="Human evaluator rating",
    source=AssessmentSource(
        source_type=AssessmentSourceType.HUMAN,
        source_id="evaluator@company.com",
    ),
)

# Example 2: LLM judge score (float for precise scoring)
# Use case: Automated quality assessment using LLM-as-a-judge
mlflow.log_feedback(
    trace_id=trace_id,
    name="llm_judge_score",
    value=0.85,  # float - precise scoring from 0.0 to 1.0
    rationale="LLM judge evaluation",
    source=AssessmentSource(
        source_type=AssessmentSourceType.LLM_JUDGE,
        source_id="gpt-4o-mini",
    ),
    metadata={"temperature": "0.1", "model_version": "2024-01"},
)

# Example 3: Binary feedback (boolean for yes/no assessments)
# Use case: Simple thumbs up/down or correct/incorrect evaluations
mlflow.log_feedback(
    trace_id=trace_id,
    name="is_helpful",
    value=True,  # bool - binary assessment
    rationale="Boolean assessment of helpfulness",
    source=AssessmentSource(
        source_type=AssessmentSourceType.HUMAN,
        source_id="reviewer@company.com",
    ),
)

# Example 4: Multi-category feedback (list for multiple classifications)
# Use case: Automated categorization or multi-label classification
mlflow.log_feedback(
    trace_id=trace_id,
    name="automated_categories",
    value=["helpful", "accurate", "concise"],  # list - multiple categories
    rationale="Automated categorization",
    source=AssessmentSource(
        source_type=AssessmentSourceType.CODE,
        source_id="classifier_v1.2",
    ),
)

# Example 5: Complex analysis with metadata (when you need structured context)
# Use case: Detailed automated analysis with multiple dimensions stored in metadata
mlflow.log_feedback(
    trace_id=trace_id,
    name="response_analysis_score",
    value=4.2,  # single score instead of dict - keeps value simple
    rationale="Analysis: 150 words, positive sentiment, includes examples, confidence 0.92",
    source=AssessmentSource(
        source_type=AssessmentSourceType.CODE,
        source_id="analyzer_v2.1",
    ),
    metadata={  # Use metadata for structured details
        "word_count": "150",
        "sentiment": "positive",
        "has_examples": "true",
        "confidence": "0.92",
    },
)

# Example 6: Error handling when evaluation fails
# Use case: Logging when automated evaluators fail due to API limits, timeouts, etc.
mlflow.log_feedback(
    trace_id=trace_id,
    name="failed_evaluation",
    source=AssessmentSource(
        source_type=AssessmentSourceType.LLM_JUDGE,
        source_id="gpt-4o",
    ),
    error=AssessmentError(  # Use error field when evaluation fails
        error_code="RATE_LIMIT_EXCEEDED",
        error_message="API rate limit exceeded during evaluation",
    ),
    metadata={"retry_count": "3", "error_timestamp": "2024-01-15T10:30:00Z"},
)

# =============================================================================
# LOG_EXPECTATION - Defining ground truth and desired outcomes
# =============================================================================

# Example 1: Simple text expectation (most common pattern)
# Use case: Defining the ideal response for factual questions
mlflow.log_expectation(
    trace_id=trace_id,
    name="expected_response",
    value="The capital of France is Paris.",  # Simple string - the "correct" answer
    source=AssessmentSource(
        source_type=AssessmentSourceType.HUMAN,
        source_id="content_curator@example.com",
    ),
)

# Example 2: Complex structured expectation (advanced pattern)
# Use case: Defining detailed requirements for response structure and content
mlflow.log_expectation(
    trace_id=trace_id,
    name="expected_response_structure",
    value={  # Complex dict - detailed specification of ideal response
        "entities": {
            "people": ["Marie Curie", "Pierre Curie"],
            "locations": ["Paris", "France"],
            "dates": ["1867", "1934"],
        },
        "key_facts": [
            "First woman to win Nobel Prize",
            "Won Nobel Prizes in Physics and Chemistry",
            "Discovered radium and polonium",
        ],
        "response_requirements": {
            "tone": "informative",
            "length_range": {"min": 100, "max": 300},
            "include_examples": True,
            "citations_required": False,
        },
    },
    source=AssessmentSource(
        source_type=AssessmentSourceType.HUMAN,
        source_id="content_strategist@example.com",
    ),
    metadata={
        "content_type": "biographical_summary",
        "target_audience": "general_public",
        "fact_check_date": "2024-01-15",
    },
)

# Example 3: Multiple acceptable answers (list pattern)
# Use case: When there are several valid ways to express the same fact
mlflow.log_expectation(
    trace_id=trace_id,
    name="expected_facts",
    value=[  # List of acceptable variations of the correct answer
        "Paris is the capital of France",
        "The capital city of France is Paris",
        "France's capital is Paris",
    ],
    source=AssessmentSource(
        source_type=AssessmentSourceType.HUMAN,
        source_id="qa_team@example.com",
    ),
)

Next Steps