mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-04 14:48:07 +00:00
a0c2281540
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path
import toml
import subprocess
import re
ROOT_DIR = Path(__file__).parents[1]
def main():
for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
print(path)
with open(path, "rb") as f:
pyproject = tomllib.load(f)
try:
pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
"^1.10"
)
pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
"^0.5"
)
except KeyError:
continue
with open(path, "w") as f:
toml.dump(pyproject, f)
cwd = "/".join(path.split("/")[:-1])
completed = subprocess.run(
"poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
logs = completed.stdout.split("\n")
to_ignore = {}
for l in logs:
if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
path, line_no, error_type = re.match(
"^(.*)\:(\d+)\: error:.*\[(.*)\]", l
).groups()
if (path, line_no) in to_ignore:
to_ignore[(path, line_no)].append(error_type)
else:
to_ignore[(path, line_no)] = [error_type]
print(len(to_ignore))
for (error_path, line_no), error_types in to_ignore.items():
all_errors = ", ".join(error_types)
full_path = f"{cwd}/{error_path}"
try:
with open(full_path, "r") as f:
file_lines = f.readlines()
except FileNotFoundError:
continue
file_lines[int(line_no) - 1] = (
file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n"
)
with open(full_path, "w") as f:
f.write("".join(file_lines))
subprocess.run(
"poetry run ruff format .; poetry run ruff --select I --fix .",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
if __name__ == "__main__":
main()
```
97 lines
3.1 KiB
Python
97 lines
3.1 KiB
Python
"""Test math utility functions."""
|
|
|
|
import importlib
|
|
from typing import List
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
from langchain_community.utils.math import cosine_similarity, cosine_similarity_top_k
|
|
|
|
|
|
@pytest.fixture
|
|
def X() -> List[List[float]]:
|
|
return [[1.0, 2.0, 3.0], [0.0, 1.0, 0.0], [1.0, 2.0, 0.0]]
|
|
|
|
|
|
@pytest.fixture
|
|
def Y() -> List[List[float]]:
|
|
return [[0.5, 1.0, 1.5], [1.0, 0.0, 0.0], [2.0, 5.0, 2.0], [0.0, 0.0, 0.0]]
|
|
|
|
|
|
def test_cosine_similarity_zero() -> None:
|
|
X = np.zeros((3, 3))
|
|
Y = np.random.random((3, 3))
|
|
expected = np.zeros((3, 3))
|
|
actual = cosine_similarity(X, Y)
|
|
assert np.allclose(expected, actual)
|
|
|
|
|
|
def test_cosine_similarity_identity() -> None:
|
|
X = np.random.random((4, 4))
|
|
expected = np.ones(4)
|
|
actual = np.diag(cosine_similarity(X, X))
|
|
assert np.allclose(expected, actual)
|
|
|
|
|
|
def test_cosine_similarity_empty() -> None:
|
|
empty_list: List[List[float]] = []
|
|
assert len(cosine_similarity(empty_list, empty_list)) == 0
|
|
assert len(cosine_similarity(empty_list, np.random.random((3, 3)))) == 0
|
|
|
|
|
|
def test_cosine_similarity(X: List[List[float]], Y: List[List[float]]) -> None:
|
|
expected = [
|
|
[1.0, 0.26726124, 0.83743579, 0.0],
|
|
[0.53452248, 0.0, 0.87038828, 0.0],
|
|
[0.5976143, 0.4472136, 0.93419873, 0.0],
|
|
]
|
|
actual = cosine_similarity(X, Y)
|
|
assert np.allclose(expected, actual)
|
|
|
|
|
|
def test_cosine_similarity_top_k(X: List[List[float]], Y: List[List[float]]) -> None:
|
|
expected_idxs = [(0, 0), (2, 2), (1, 2), (0, 2), (2, 0)]
|
|
expected_scores = [1.0, 0.93419873, 0.87038828, 0.83743579, 0.5976143]
|
|
actual_idxs, actual_scores = cosine_similarity_top_k(X, Y)
|
|
assert actual_idxs == expected_idxs
|
|
assert np.allclose(expected_scores, actual_scores)
|
|
|
|
|
|
def test_cosine_similarity_score_threshold(
|
|
X: List[List[float]], Y: List[List[float]]
|
|
) -> None:
|
|
expected_idxs = [(0, 0), (2, 2)]
|
|
expected_scores = [1.0, 0.93419873]
|
|
actual_idxs, actual_scores = cosine_similarity_top_k(
|
|
X, Y, top_k=None, score_threshold=0.9
|
|
)
|
|
assert actual_idxs == expected_idxs
|
|
assert np.allclose(expected_scores, actual_scores)
|
|
|
|
|
|
def invoke_cosine_similarity_top_k_score_threshold(
|
|
X: List[List[float]], Y: List[List[float]]
|
|
) -> None:
|
|
expected_idxs = [(0, 0), (2, 2), (1, 2), (0, 2)]
|
|
expected_scores = [1.0, 0.93419873, 0.87038828, 0.83743579]
|
|
actual_idxs, actual_scores = cosine_similarity_top_k(X, Y, score_threshold=0.8)
|
|
assert actual_idxs == expected_idxs
|
|
assert np.allclose(expected_scores, actual_scores)
|
|
|
|
|
|
def test_cosine_similarity_top_k_and_score_threshold(
|
|
X: List[List[float]], Y: List[List[float]]
|
|
) -> None:
|
|
if importlib.util.find_spec("simsimd"):
|
|
raise ValueError("test should be run without simsimd installed.")
|
|
invoke_cosine_similarity_top_k_score_threshold(X, Y)
|
|
|
|
|
|
@pytest.mark.requires("simsimd")
|
|
def test_cosine_similarity_top_k_and_score_threshold_with_simsimd(
|
|
X: List[List[float]], Y: List[List[float]]
|
|
) -> None:
|
|
# Same test, but ensuring simsimd is available in the project through the import.
|
|
invoke_cosine_similarity_top_k_score_threshold(X, Y)
|