mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-15 03:59:08 +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()
```
47 lines
1.4 KiB
Python
47 lines
1.4 KiB
Python
"""Wrapper around wikipedia API."""
|
|
|
|
from typing import Union
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.docstore.base import Docstore
|
|
|
|
|
|
class Wikipedia(Docstore):
|
|
"""Wikipedia API."""
|
|
|
|
def __init__(self) -> None:
|
|
"""Check that wikipedia package is installed."""
|
|
try:
|
|
import wikipedia # noqa: F401
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import wikipedia python package. "
|
|
"Please install it with `pip install wikipedia`."
|
|
)
|
|
|
|
def search(self, search: str) -> Union[str, Document]:
|
|
"""Try to search for wiki page.
|
|
|
|
If page exists, return the page summary, and a PageWithLookups object.
|
|
If page does not exist, return similar entries.
|
|
|
|
Args:
|
|
search: search string.
|
|
|
|
Returns: a Document object or error message.
|
|
"""
|
|
import wikipedia
|
|
|
|
try:
|
|
page_content = wikipedia.page(search).content
|
|
url = wikipedia.page(search).url
|
|
result: Union[str, Document] = Document(
|
|
page_content=page_content, metadata={"page": url}
|
|
)
|
|
except wikipedia.PageError:
|
|
result = f"Could not find [{search}]. Similar: {wikipedia.search(search)}"
|
|
except wikipedia.DisambiguationError:
|
|
result = f"Could not find [{search}]. Similar: {wikipedia.search(search)}"
|
|
return result
|