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()
```
90 lines
2.6 KiB
Python
90 lines
2.6 KiB
Python
"""Logic for converting internal query language to a valid Chroma query."""
|
|
|
|
from typing import Tuple, Union
|
|
|
|
from langchain_core.structured_query import (
|
|
Comparator,
|
|
Comparison,
|
|
Operation,
|
|
Operator,
|
|
StructuredQuery,
|
|
Visitor,
|
|
)
|
|
|
|
COMPARATOR_TO_TQL = {
|
|
Comparator.EQ: "==",
|
|
Comparator.GT: ">",
|
|
Comparator.GTE: ">=",
|
|
Comparator.LT: "<",
|
|
Comparator.LTE: "<=",
|
|
}
|
|
|
|
|
|
OPERATOR_TO_TQL = {
|
|
Operator.AND: "and",
|
|
Operator.OR: "or",
|
|
Operator.NOT: "NOT",
|
|
}
|
|
|
|
|
|
def can_cast_to_float(string: str) -> bool:
|
|
"""Check if a string can be cast to a float."""
|
|
try:
|
|
float(string)
|
|
return True
|
|
except ValueError:
|
|
return False
|
|
|
|
|
|
class DeepLakeTranslator(Visitor):
|
|
"""Translate `DeepLake` internal query language elements to valid filters."""
|
|
|
|
allowed_operators = [Operator.AND, Operator.OR, Operator.NOT]
|
|
"""Subset of allowed logical operators."""
|
|
allowed_comparators = [
|
|
Comparator.EQ,
|
|
Comparator.GT,
|
|
Comparator.GTE,
|
|
Comparator.LT,
|
|
Comparator.LTE,
|
|
]
|
|
"""Subset of allowed logical comparators."""
|
|
|
|
def _format_func(self, func: Union[Operator, Comparator]) -> str:
|
|
self._validate_func(func)
|
|
if isinstance(func, Operator):
|
|
value = OPERATOR_TO_TQL[func.value] # type: ignore
|
|
elif isinstance(func, Comparator):
|
|
value = COMPARATOR_TO_TQL[func.value] # type: ignore
|
|
return f"{value}"
|
|
|
|
def visit_operation(self, operation: Operation) -> str:
|
|
args = [arg.accept(self) for arg in operation.arguments]
|
|
operator = self._format_func(operation.operator)
|
|
return "(" + (" " + operator + " ").join(args) + ")"
|
|
|
|
def visit_comparison(self, comparison: Comparison) -> str:
|
|
comparator = self._format_func(comparison.comparator)
|
|
values = comparison.value
|
|
if isinstance(values, list):
|
|
tql = []
|
|
for value in values:
|
|
comparison.value = value
|
|
tql.append(self.visit_comparison(comparison))
|
|
|
|
return "(" + (" or ").join(tql) + ")"
|
|
|
|
if not can_cast_to_float(comparison.value):
|
|
values = f"'{values}'"
|
|
return f"metadata['{comparison.attribute}'] {comparator} {values}"
|
|
|
|
def visit_structured_query(
|
|
self, structured_query: StructuredQuery
|
|
) -> Tuple[str, dict]:
|
|
if structured_query.filter is None:
|
|
kwargs = {}
|
|
else:
|
|
tqL = f"SELECT * WHERE {structured_query.filter.accept(self)}"
|
|
kwargs = {"tql": tqL}
|
|
return structured_query.query, kwargs
|