You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/tests/unit_tests/test_document_transformers.py

16 lines
588 B
Python

"""Unit tests for document transformers."""
from langchain.document_transformers import _filter_similar_embeddings
from langchain.math_utils import cosine_similarity
def test__filter_similar_embeddings() -> None:
threshold = 0.79
embedded_docs = [[1.0, 2.0], [1.0, 2.0], [2.0, 1.0], [2.0, 0.5], [0.0, 0.0]]
expected = [1, 3, 4]
actual = _filter_similar_embeddings(embedded_docs, cosine_similarity, threshold)
assert expected == actual
def test__filter_similar_embeddings_empty() -> None:
assert len(_filter_similar_embeddings([], cosine_similarity, 0.0)) == 0