How to Build a Simple Semantic Cache for Similar Prompts in Python

prompt_cache = [
    "What is the capital of France?",
    "How does recursion work?",
    "Best practices for Python logging?",
    "Explain binary search in one line.",
    "How to reverse a string in Python?"
]

def normalize(text):
    return " ".join(text.lower().split())

def similarity(a, b):
    a_words = set(normalize(a).split())
    b_words = set(normalize(b).split())
    if not a_words or not b_words:
        return 0.0
    return len(a_words & b_words) / max(len(a_words), len(b_words))

def semantic_lookup(query, threshold=0.4):
    query_norm = normalize(query)
    best_match = None
    best_score = 0.0
    for cached in prompt_cache:
        score = similarity(query_norm, cached)
        if score > best_score:
            best_score = score
            best_match = cached
    if best_score >= threshold:
        return best_match, best_score
    return None, 0.0

if __name__ == "__main__":
    test_query = "What is the capital city of France?"
    match, score = semantic_lookup(test_query)
    print(f"Query: {test_query!r}")
    print(f"Best match: {match!r}")
    print(f"Similarity score: {score:.2f}")