from tenacity import retry, stop_after_attempt, wait_exponential

def before_sleep(retry_state):
    print(f"(Tenacity) Retry, error that caused it: {retry_state.outcome.exception()}")

def retry_error_callback(retry_state):
    exception = retry_state.outcome.exception()
    exception_str = str(exception)
    if "prompt is too long" in exception_str and "400" in exception_str:
        raise exception
    return 'No error that requires us to exit early.'

@retry(stop=stop_after_attempt(20), wait=wait_exponential(multiplier=2, max=256), 
       before_sleep=before_sleep, retry_error_callback=retry_error_callback)
def call_to_anthropic_client_api_with_retry(gen: AnthropicGenerator, prompt: str) -> dict:
    response = gen.llm.messages.create(
        model=gen.model,
        max_tokens=gen.sampling_params.max_tokens,
        system=gen.system_prompt,
        messages=[
            {"role": "user", "content": [{"type": "text", "text": prompt}]}
        ],
        temperature=gen.sampling_params.temperature,
        top_p=gen.sampling_params.top_p,
        n=gen.sampling_params.n,  # Intended to generate multiple completions
        stop_sequences=gen.sampling_params.stop[:3],
    )
    return response