test_rate_limit_batch() — langchain Function Reference

Source Code

libs/core/tests/unit_tests/language_models/chat_models/test_rate_limiting.py lines 78–92

def test_rate_limit_batch() -> None:
    """Test that batch and stream calls work with rate limiters."""
    model = GenericFakeChatModel(
        messages=iter(["hello", "world", "!"]),
        rate_limiter=InMemoryRateLimiter(
            requests_per_second=20,
            check_every_n_seconds=0.01,
            max_bucket_size=10,
            # At 20 requests per second we see a refresh every 0.05 seconds
        ),
    )
    tic = time.time()
    model.batch(["foo", "foo"])
    toc = time.time()
    assert 0.1 < toc - tic < 0.2