LLM-based Context Precision

Definition

Context Precision is used to measure information density.

while

Example Usage

Required data items: question, retrieved_context

from continuous_eval.metrics.retrieval import ContextPrecision

datum = {
    "question": "What is the capital of France?",
    "retrieved_context": [
        "Paris is the capital of France and also the largest city in the country.",
        "Lyon is a major city in France.",
    ],
}

metric = ContextPrecision()
print(metric(**datum))

Sample Output

{
    "percentage_relevant": 0.5,
    "context_precision": 0.5000000000746547,
    "context_mean_average_precision": 1.0,
}