initial implementation of metric

Author: jjmachan

src/ragas/metrics/collections/__init__.py

@@ -3,6 +3,7 @@
 from ragas.metrics.collections._answer_relevancy import AnswerRelevancy
 from ragas.metrics.collections._answer_similarity import AnswerSimilarity
 from ragas.metrics.collections._bleu_score import BleuScore
+from ragas.metrics.collections._context_recall import ContextRecall
 from ragas.metrics.collections._rouge_score import RougeScore
 from ragas.metrics.collections._string import (
     DistanceMeasure,
@@ -17,6 +18,7 @@
     "AnswerRelevancy",
     "AnswerSimilarity",
     "BleuScore",
+    "ContextRecall",
     "DistanceMeasure",
     "ExactMatch",
     "NonLLMStringSimilarity",

src/ragas/metrics/collections/_context_recall.py

@@ -0,0 +1,124 @@
+"""Context Recall metric v2 - Class-based implementation with modern components."""
+
+import typing as t
+
+import numpy as np
+from pydantic import BaseModel
+
+from ragas.metrics.collections.base import BaseMetric
+from ragas.metrics.result import MetricResult
+from ragas.prompt.metrics.context_recall import context_recall_prompt
+
+if t.TYPE_CHECKING:
+    from ragas.llms.base import InstructorBaseRagasLLM
+
+
+class ContextRecallClassification(BaseModel):
+    """Structured output for a single statement classification."""
+
+    statement: str
+    reason: str
+    attributed: int
+
+
+class ContextRecallOutput(BaseModel):
+    """Structured output for context recall classifications."""
+
+    classifications: t.List[ContextRecallClassification]
+
+
+class ContextRecall(BaseMetric):
+    """
+    Evaluate context recall by classifying if statements can be attributed to context.
+
+    This implementation uses modern instructor LLMs with structured output.
+    Only supports modern components - legacy wrappers are rejected with clear error messages.
+
+    Usage:
+        >>> import instructor
+        >>> from openai import AsyncOpenAI
+        >>> from ragas.llms.base import instructor_llm_factory
+        >>> from ragas.metrics.collections import ContextRecall
+        >>>
+        >>> # Setup dependencies
+        >>> client = AsyncOpenAI()
+        >>> llm = instructor_llm_factory("openai", client=client, model="gpt-4o-mini")
+        >>>
+        >>> # Create metric instance
+        >>> metric = ContextRecall(llm=llm)
+        >>>
+        >>> # Single evaluation
+        >>> result = await metric.ascore(
+        ...     user_input="What is the capital of France?",
+        ...     retrieved_contexts=["Paris is the capital of France."],
+        ...     reference="Paris is the capital and largest city of France."
+        ... )
+        >>> print(f"Score: {result.value}")
+        >>>
+        >>> # Batch evaluation
+        >>> results = await metric.abatch_score([
+        ...     {"user_input": "Q1", "retrieved_contexts": ["C1"], "reference": "A1"},
+        ...     {"user_input": "Q2", "retrieved_contexts": ["C2"], "reference": "A2"},
+        ... ])
+
+    Attributes:
+        llm: Modern instructor-based LLM for classification
+        name: The metric name
+        allowed_values: Score range (0.0 to 1.0)
+    """
+
+    # Type hints for linter (attributes are set in __init__)
+    llm: "InstructorBaseRagasLLM"
+
+    def __init__(
+        self,
+        llm: "InstructorBaseRagasLLM",
+        name: str = "context_recall",
+        **kwargs,
+    ):
+        """Initialize ContextRecall metric with required components."""
+        # Set attributes explicitly before calling super()
+        self.llm = llm
+
+        # Call super() for validation
+        super().__init__(name=name, **kwargs)
+
+    async def ascore(
+        self,
+        user_input: str,
+        retrieved_contexts: t.List[str],
+        reference: str,
+    ) -> MetricResult:
+        """
+        Calculate context recall score asynchronously.
+
+        Components are guaranteed to be validated and non-None by the base class.
+
+        Args:
+            user_input: The original question
+            retrieved_contexts: List of retrieved context strings
+            reference: The reference answer to evaluate
+
+        Returns:
+            MetricResult with recall score (0.0-1.0)
+        """
+        # Combine contexts into a single string
+        context = "\n".join(retrieved_contexts) if retrieved_contexts else ""
+
+        # Generate prompt
+        prompt = context_recall_prompt(
+            question=user_input, context=context, answer=reference
+        )
+
+        # Get classifications from LLM
+        result = await self.llm.agenerate(prompt, ContextRecallOutput)
+
+        # Calculate score
+        if not result.classifications:
+            return MetricResult(value=np.nan)
+
+        # Count attributions
+        attributions = [c.attributed for c in result.classifications]
+        score = sum(attributions) / len(attributions) if attributions else np.nan
+
+        return MetricResult(value=float(score))

src/ragas/prompt/metrics/context_recall.py

@@ -0,0 +1,64 @@
+"""Context Recall prompt for classifying statement attributions."""
+
+import json
+
+
+def context_recall_prompt(question: str, context: str, answer: str) -> str:
+    """
+    Generate the prompt for context recall evaluation.
+
+    Args:
+        question: The original question
+        context: The retrieved context to evaluate against
+        answer: The reference answer containing statements to classify
+
+    Returns:
+        Formatted prompt string for the LLM
+    """
+    # Use json.dumps() to safely escape the strings
+    safe_question = json.dumps(question)
+    safe_context = json.dumps(context)
+    safe_answer = json.dumps(answer)
+
+    return f"""Given a context, and an answer, analyze each sentence in the answer and classify if the sentence can be attributed to the given context or not. Use only 'Yes' (1) or 'No' (0) as a binary classification. Output json with reason.
+
+--------EXAMPLES-----------
+Example 1
+Input: {{
+    "question": "What can you tell me about Albert Einstein?",
+    "context": "Albert Einstein (14 March 1879 - 18 April 1955) was a German-born theoretical physicist, widely held to be one of the greatest and most influential scientists of all time. Best known for developing the theory of relativity, he also made important contributions to quantum mechanics, and was thus a central figure in the revolutionary reshaping of the scientific understanding of nature that modern physics accomplished in the first decades of the twentieth century. His mass-energy equivalence formula E = mc2, which arises from relativity theory, has been called 'the world's most famous equation'. He received the 1921 Nobel Prize in Physics 'for his services to theoretical physics, and especially for his discovery of the law of the photoelectric effect', a pivotal step in the development of quantum theory. His work is also known for its influence on the philosophy of science. In a 1999 poll of 130 leading physicists worldwide by the British journal Physics World, Einstein was ranked the greatest physicist of all time. His intellectual achievements and originality have made Einstein synonymous with genius.",
+    "answer": "Albert Einstein, born on 14 March 1879, was a German-born theoretical physicist, widely held to be one of the greatest and most influential scientists of all time. He received the 1921 Nobel Prize in Physics for his services to theoretical physics. He published 4 papers in 1905. Einstein moved to Switzerland in 1895."
+}}
+Output: {{
+    "classifications": [
+        {{
+            "statement": "Albert Einstein, born on 14 March 1879, was a German-born theoretical physicist, widely held to be one of the greatest and most influential scientists of all time.",
+            "reason": "The date of birth of Einstein is mentioned clearly in the context.",
+            "attributed": 1
+        }},
+        {{
+            "statement": "He received the 1921 Nobel Prize in Physics for his services to theoretical physics.",
+            "reason": "The exact sentence is present in the given context.",
+            "attributed": 1
+        }},
+        {{
+            "statement": "He published 4 papers in 1905.",
+            "reason": "There is no mention about papers he wrote in the given context.",
+            "attributed": 0
+        }},
+        {{
+            "statement": "Einstein moved to Switzerland in 1895.",
+            "reason": "There is no supporting evidence for this in the given context.",
+            "attributed": 0
+        }}
+    ]
+}}
+-----------------------------
+
+Now perform the same with the following input
+Input: {{
+    "question": {safe_question},
+    "context": {safe_context},
+    "answer": {safe_answer}
+}}
+Output: """