Cache LLM Completions by Hashing the Prompt in Python

import hashlib
import json

class PromptCache:
    def __init__(self):
        self.cache = {}

    def _hash_prompt(self, prompt: str) -> str:
        return hashlib.sha256(prompt.encode("utf-8")).hexdigest()

    def get(self, prompt: str) -> str | None:
        key = self._hash_prompt(prompt)
        return self.cache.get(key)

    def set(self, prompt: str, completion: str) -> None:
        key = self._hash_prompt(prompt)
        self.cache[key] = completion

    def stats(self) -> dict:
        return {
            "cache_size": len(self.cache),
            "keys": list(self.cache.keys()),
        }


if __name__ == "__main__":
    cache = PromptCache()
    prompt = "Explain quantum computing in one sentence."
    completion = "Quantum computing uses qubits to process information in superposition."

    cache.set(prompt, completion)
    retrieved = cache.get(prompt)
    miss = cache.get("Different prompt entirely")

    print("Retrieved:", retrieved)
    print("Miss result:", miss)
    print("Stats:", json.dumps(cache.stats(), indent=2))