mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-29 04:16:02 +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()
```
23 lines
733 B
Python
23 lines
733 B
Python
"""Unit tests for document transformers."""
|
|
|
|
import pytest
|
|
|
|
pytest.importorskip("langchain_community")
|
|
|
|
from langchain_community.document_transformers.embeddings_redundant_filter import ( # noqa: E402
|
|
_filter_similar_embeddings,
|
|
)
|
|
from langchain_community.utils.math import cosine_similarity # noqa: E402
|
|
|
|
|
|
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
|