mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
24 lines
773 B
Python
24 lines
773 B
Python
"""Test text splitters that require an integration."""
|
|
|
|
import pytest
|
|
|
|
from langchain.text_splitter import CharacterTextSplitter
|
|
|
|
|
|
def test_huggingface_type_check() -> None:
|
|
"""Test that type checks are done properly on input."""
|
|
with pytest.raises(ValueError):
|
|
CharacterTextSplitter.from_huggingface_tokenizer("foo")
|
|
|
|
|
|
def test_huggingface_tokenizer() -> None:
|
|
"""Test text splitter that uses a HuggingFace tokenizer."""
|
|
from transformers import GPT2TokenizerFast
|
|
|
|
tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")
|
|
text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(
|
|
tokenizer, separator=" ", chunk_size=1, chunk_overlap=0
|
|
)
|
|
output = text_splitter.split_text("foo bar")
|
|
assert output == ["foo", "bar"]
|