mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
d3ec00b566
Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
16 lines
524 B
Python
16 lines
524 B
Python
"""Test formatting functionality."""
|
|
|
|
from langchain.base_language import _get_num_tokens_default_method
|
|
|
|
|
|
class TestTokenCountingWithGPT2Tokenizer:
|
|
def test_empty_token(self) -> None:
|
|
assert _get_num_tokens_default_method("") == 0
|
|
|
|
def test_multiple_tokens(self) -> None:
|
|
assert _get_num_tokens_default_method("a b c") == 3
|
|
|
|
def test_special_tokens(self) -> None:
|
|
# test for consistency when the default tokenizer is changed
|
|
assert _get_num_tokens_default_method("a:b_c d") == 6
|