mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-23 17:06:54 +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()
```
99 lines
3.2 KiB
Python
99 lines
3.2 KiB
Python
"""Chain that hits a URL and then uses an LLM to parse results."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
from langchain.chains import LLMChain
|
|
from langchain.chains.base import Chain
|
|
from langchain_core.callbacks import CallbackManagerForChainRun
|
|
from langchain_core.pydantic_v1 import Extra, Field, root_validator
|
|
|
|
from langchain_community.utilities.requests import TextRequestsWrapper
|
|
|
|
DEFAULT_HEADERS = {
|
|
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36" # noqa: E501
|
|
}
|
|
|
|
|
|
class LLMRequestsChain(Chain):
|
|
"""Chain that requests a URL and then uses an LLM to parse results.
|
|
|
|
**Security Note**: This chain can make GET requests to arbitrary URLs,
|
|
including internal URLs.
|
|
|
|
Control access to who can run this chain and what network access
|
|
this chain has.
|
|
|
|
See https://python.langchain.com/docs/security for more information.
|
|
"""
|
|
|
|
llm_chain: LLMChain # type: ignore[valid-type]
|
|
requests_wrapper: TextRequestsWrapper = Field(
|
|
default_factory=lambda: TextRequestsWrapper(headers=DEFAULT_HEADERS),
|
|
exclude=True,
|
|
)
|
|
text_length: int = 8000
|
|
requests_key: str = "requests_result" #: :meta private:
|
|
input_key: str = "url" #: :meta private:
|
|
output_key: str = "output" #: :meta private:
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
arbitrary_types_allowed = True
|
|
|
|
@property
|
|
def input_keys(self) -> List[str]:
|
|
"""Will be whatever keys the prompt expects.
|
|
|
|
:meta private:
|
|
"""
|
|
return [self.input_key]
|
|
|
|
@property
|
|
def output_keys(self) -> List[str]:
|
|
"""Will always return text key.
|
|
|
|
:meta private:
|
|
"""
|
|
return [self.output_key]
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that api key and python package exists in environment."""
|
|
try:
|
|
from bs4 import BeautifulSoup # noqa: F401
|
|
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import bs4 python package. "
|
|
"Please install it with `pip install bs4`."
|
|
)
|
|
return values
|
|
|
|
def _call(
|
|
self,
|
|
inputs: Dict[str, Any],
|
|
run_manager: Optional[CallbackManagerForChainRun] = None,
|
|
) -> Dict[str, Any]:
|
|
from bs4 import BeautifulSoup
|
|
|
|
_run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
|
|
# Other keys are assumed to be needed for LLM prediction
|
|
other_keys = {k: v for k, v in inputs.items() if k != self.input_key}
|
|
url = inputs[self.input_key]
|
|
res = self.requests_wrapper.get(url)
|
|
# extract the text from the html
|
|
soup = BeautifulSoup(res, "html.parser")
|
|
other_keys[self.requests_key] = soup.get_text()[: self.text_length]
|
|
result = self.llm_chain.predict( # type: ignore[attr-defined]
|
|
callbacks=_run_manager.get_child(), **other_keys
|
|
)
|
|
return {self.output_key: result}
|
|
|
|
@property
|
|
def _chain_type(self) -> str:
|
|
return "llm_requests_chain"
|