mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-27 11:41:51 +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()
```
55 lines
1.7 KiB
Python
55 lines
1.7 KiB
Python
"""Base interface for loading large language model APIs."""
|
|
|
|
import json
|
|
from pathlib import Path
|
|
from typing import Any, Union
|
|
|
|
import yaml
|
|
from langchain_core.language_models.llms import BaseLLM
|
|
|
|
from langchain_community.llms import get_type_to_cls_dict
|
|
|
|
_ALLOW_DANGEROUS_DESERIALIZATION_ARG = "allow_dangerous_deserialization"
|
|
|
|
|
|
def load_llm_from_config(config: dict, **kwargs: Any) -> BaseLLM:
|
|
"""Load LLM from Config Dict."""
|
|
if "_type" not in config:
|
|
raise ValueError("Must specify an LLM Type in config")
|
|
config_type = config.pop("_type")
|
|
|
|
type_to_cls_dict = get_type_to_cls_dict()
|
|
|
|
if config_type not in type_to_cls_dict:
|
|
raise ValueError(f"Loading {config_type} LLM not supported")
|
|
|
|
llm_cls = type_to_cls_dict[config_type]()
|
|
|
|
load_kwargs = {}
|
|
if _ALLOW_DANGEROUS_DESERIALIZATION_ARG in llm_cls.__fields__:
|
|
load_kwargs[_ALLOW_DANGEROUS_DESERIALIZATION_ARG] = kwargs.get(
|
|
_ALLOW_DANGEROUS_DESERIALIZATION_ARG, False
|
|
)
|
|
|
|
return llm_cls(**config, **load_kwargs)
|
|
|
|
|
|
def load_llm(file: Union[str, Path], **kwargs: Any) -> BaseLLM:
|
|
"""Load LLM from a file."""
|
|
# Convert file to Path object.
|
|
if isinstance(file, str):
|
|
file_path = Path(file)
|
|
else:
|
|
file_path = file
|
|
# Load from either json or yaml.
|
|
if file_path.suffix == ".json":
|
|
with open(file_path) as f:
|
|
config = json.load(f)
|
|
elif file_path.suffix.endswith((".yaml", ".yml")):
|
|
with open(file_path, "r") as f:
|
|
config = yaml.safe_load(f)
|
|
else:
|
|
raise ValueError("File type must be json or yaml")
|
|
# Load the LLM from the config now.
|
|
return load_llm_from_config(config, **kwargs)
|