semantic_cache.py

def semantic_cached_prompt(prompt):
    """Retrieve a response from ScyllaDB or ask OpenAI if it's a new prompt.
    Args:
        prompt (str): The user prompt.
    Returns:
        str: The response to the prompt.
    """
    embedding = create_embedding(prompt)    
    cached_response = search_cache(embedding, threshold=0.80)
    if cached_response:
        print("Cache hit! Returning cached response...")
        return cached_response
    else:
        print("Cache miss... sending request to OpenAI!")
        response = ask_openai(prompt)
        insert_to_cache(prompt, embedding, response)
        return response