Skip to main content

Answer & Context Relevance judge & scorers

The judges.is_context_relevant() predefined judge assesses whether context either retrieved by your RAG system or generated by a tool call is relevant to the user's request. This is crucial for diagnosing quality issues - if context isn't relevant, the generation step cannot produce a helpful response.

This judge is available through two predefined scorers:

  • RelevanceToQuery: Evaluates if your app's response directly addresses the user's input
  • RetrievalRelevance: Evaluates if each document returned by your app's retriever(s) is relevant

API Signature​

For details, see mlflow.genai.judges.is_context_relevant().

Python
from mlflow.genai.judges import is_context_relevant

def is_context_relevant(
    *,
    request: str,               # User's question or query
    context: Any,               # Context to evaluate for relevance, can be any Python primitive or a JSON-seralizable dict
    name: Optional[str] = None  # Optional custom name for display in the MLflow UIs
) -> mlflow.entities.Feedback:
    """Returns Feedback with 'yes' or 'no' value and a rationale"""

Prerequisites for running the examples​

  1. Install MLflow and required packages

    Bash
    pip install --upgrade "mlflow[databricks]>=3.1.0" openai "databricks-connect>=16.1"

  2. Create an MLflow experiment by following the setup your environment quickstart.

Direct SDK Usage​

Python
from mlflow.genai.judges import is_context_relevant

# Example 1: Relevant context
feedback = is_context_relevant(
    request="What is the capital of France?",
    context="Paris is the capital of France."
)
print(feedback.value)  # "yes"
print(feedback.rationale)  # Explanation of relevance

# Example 2: Irrelevant context
feedback = is_context_relevant(
    request="What is the capital of France?",
    context="Paris is known for its Eiffel Tower."
)
print(feedback.value)  # "no"
print(feedback.rationale)  # Explanation of why it's not relevant

Using the prebuilt scorer​

The is_context_relevant judge is available through two prebuilt scorers:

1. RelevanceToQuery scorer​

This scorer evaluates if your app's response directly addresses the user's input without deviating into unrelated topics.

Requirements:

  • Trace requirements: inputs and outputs must be on the Trace's root span
Python
from mlflow.genai.scorers import RelevanceToQuery

eval_dataset = [
    {
        "inputs": {"query": "What is the capital of France?"},
        "outputs": {
            "response": "Paris is the capital of France. It's known for the Eiffel Tower and is a major European city."
        },
    },
    {
        "inputs": {"query": "What is the capital of France?"},
        "outputs": {
            "response": "France is a beautiful country with great wine and cuisine."
        },
    }
]

# Run evaluation with RelevanceToQuery scorer
eval_results = mlflow.genai.evaluate(
    data=eval_dataset,
    scorers=[RelevanceToQuery()]
)

2. RetrievalRelevance scorer​

This scorer evaluates if each document returned by your app's retriever(s) is relevant to the input request.

Requirements:

  • Trace requirements: The MLflow Trace must contain at least one span with span_type set to RETRIEVER
Python
import mlflow
from mlflow.genai.scorers import RetrievalRelevance
from mlflow.entities import Document
from typing import List

# Define a retriever function with proper span type
@mlflow.trace(span_type="RETRIEVER")
def retrieve_docs(query: str) -> List[Document]:
    # Simulated retrieval - in practice, this would query a vector database
    if "capital" in query.lower() and "france" in query.lower():
        return [
            Document(
                id="doc_1",
                page_content="Paris is the capital of France.",
                metadata={"source": "geography.txt"}
            ),
            Document(
                id="doc_2",
                page_content="The Eiffel Tower is located in Paris.",
                metadata={"source": "landmarks.txt"}
            )
        ]
    else:
        return [
            Document(
                id="doc_3",
                page_content="Python is a programming language.",
                metadata={"source": "tech.txt"}
            )
        ]

# Define your app that uses the retriever
@mlflow.trace
def rag_app(query: str):
    docs = retrieve_docs(query)
    # In practice, you would pass these docs to an LLM
    return {"response": f"Found {len(docs)} relevant documents."}

# Create evaluation dataset
eval_dataset = [
    {
        "inputs": {"query": "What is the capital of France?"}
    },
    {
        "inputs": {"query": "How do I use Python?"}
    }
]

# Run evaluation with RetrievalRelevance scorer
eval_results = mlflow.genai.evaluate(
    data=eval_dataset,
    predict_fn=rag_app,
    scorers=[RetrievalRelevance()]
)

Using in a custom scorer​

When evaluating applications with different data structures than the requirements the predefined scorer, wrap the judge in a custom scorer:

Python
from mlflow.genai.judges import is_context_relevant
from mlflow.genai.scorers import scorer
from typing import Dict, Any

eval_dataset = [
    {
        "inputs": {"query": "What are MLflow's main components?"},
        "outputs": {
            "retrieved_context": [
                {"content": "MLflow has four main components: Tracking, Projects, Models, and Registry."}
            ]
        }
    },
    {
        "inputs": {"query": "What are MLflow's main components?"},
        "outputs": {
            "retrieved_context": [
                {"content": "Python is a popular programming language."}
            ]
        }
    }
]

@scorer
def context_relevance_scorer(inputs: Dict[Any, Any], outputs: Dict[Any, Any]):
    # Extract first context chunk for evaluation
    context = outputs["retrieved_context"]
    return is_context_relevant(
        request=inputs["query"],
        context=context
    )

# Run evaluation
eval_results = mlflow.genai.evaluate(
    data=eval_dataset,
    scorers=[context_relevance_scorer]
)

Interpreting Results​

The judge returns a Feedback object with:

  • value: "yes" if context is relevant, "no" if not
  • rationale: Explanation of why the context was deemed relevant or irrelevant

Next Steps​

Last updated on