mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-08 16:48:49 +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()
```
52 lines
1.6 KiB
Python
52 lines
1.6 KiB
Python
"""Simple in memory docstore in the form of a dict."""
|
|
|
|
from typing import Dict, List, Optional, Union
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.docstore.base import AddableMixin, Docstore
|
|
|
|
|
|
class InMemoryDocstore(Docstore, AddableMixin):
|
|
"""Simple in memory docstore in the form of a dict."""
|
|
|
|
def __init__(self, _dict: Optional[Dict[str, Document]] = None):
|
|
"""Initialize with dict."""
|
|
self._dict = _dict if _dict is not None else {}
|
|
|
|
def add(self, texts: Dict[str, Document]) -> None:
|
|
"""Add texts to in memory dictionary.
|
|
|
|
Args:
|
|
texts: dictionary of id -> document.
|
|
|
|
Returns:
|
|
None
|
|
"""
|
|
overlapping = set(texts).intersection(self._dict)
|
|
if overlapping:
|
|
raise ValueError(f"Tried to add ids that already exist: {overlapping}")
|
|
self._dict = {**self._dict, **texts}
|
|
|
|
def delete(self, ids: List) -> None:
|
|
"""Deleting IDs from in memory dictionary."""
|
|
overlapping = set(ids).intersection(self._dict)
|
|
if not overlapping:
|
|
raise ValueError(f"Tried to delete ids that does not exist: {ids}")
|
|
for _id in ids:
|
|
self._dict.pop(_id)
|
|
|
|
def search(self, search: str) -> Union[str, Document]:
|
|
"""Search via direct lookup.
|
|
|
|
Args:
|
|
search: id of a document to search for.
|
|
|
|
Returns:
|
|
Document if found, else error message.
|
|
"""
|
|
if search not in self._dict:
|
|
return f"ID {search} not found."
|
|
else:
|
|
return self._dict[search]
|