mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-04 14:13:29 +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()
```
147 lines
4.3 KiB
Python
147 lines
4.3 KiB
Python
"""Util that calls DuckDuckGo Search.
|
|
|
|
No setup required. Free.
|
|
https://pypi.org/project/duckduckgo-search/
|
|
"""
|
|
|
|
from typing import Dict, List, Optional
|
|
|
|
from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
|
|
|
|
|
|
class DuckDuckGoSearchAPIWrapper(BaseModel):
|
|
"""Wrapper for DuckDuckGo Search API.
|
|
|
|
Free and does not require any setup.
|
|
"""
|
|
|
|
region: Optional[str] = "wt-wt"
|
|
"""
|
|
See https://pypi.org/project/duckduckgo-search/#regions
|
|
"""
|
|
safesearch: str = "moderate"
|
|
"""
|
|
Options: strict, moderate, off
|
|
"""
|
|
time: Optional[str] = "y"
|
|
"""
|
|
Options: d, w, m, y
|
|
"""
|
|
max_results: int = 5
|
|
backend: str = "api"
|
|
"""
|
|
Options: api, html, lite
|
|
"""
|
|
source: str = "text"
|
|
"""
|
|
Options: text, news
|
|
"""
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that python package exists in environment."""
|
|
try:
|
|
from duckduckgo_search import DDGS # noqa: F401
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import duckduckgo-search python package. "
|
|
"Please install it with `pip install -U duckduckgo-search`."
|
|
)
|
|
return values
|
|
|
|
def _ddgs_text(
|
|
self, query: str, max_results: Optional[int] = None
|
|
) -> List[Dict[str, str]]:
|
|
"""Run query through DuckDuckGo text search and return results."""
|
|
from duckduckgo_search import DDGS
|
|
|
|
with DDGS() as ddgs:
|
|
ddgs_gen = ddgs.text(
|
|
query,
|
|
region=self.region,
|
|
safesearch=self.safesearch,
|
|
timelimit=self.time,
|
|
max_results=max_results or self.max_results,
|
|
backend=self.backend,
|
|
)
|
|
if ddgs_gen:
|
|
return [r for r in ddgs_gen]
|
|
return []
|
|
|
|
def _ddgs_news(
|
|
self, query: str, max_results: Optional[int] = None
|
|
) -> List[Dict[str, str]]:
|
|
"""Run query through DuckDuckGo news search and return results."""
|
|
from duckduckgo_search import DDGS
|
|
|
|
with DDGS() as ddgs:
|
|
ddgs_gen = ddgs.news(
|
|
query,
|
|
region=self.region,
|
|
safesearch=self.safesearch,
|
|
timelimit=self.time,
|
|
max_results=max_results or self.max_results,
|
|
)
|
|
if ddgs_gen:
|
|
return [r for r in ddgs_gen]
|
|
return []
|
|
|
|
def run(self, query: str) -> str:
|
|
"""Run query through DuckDuckGo and return concatenated results."""
|
|
if self.source == "text":
|
|
results = self._ddgs_text(query)
|
|
elif self.source == "news":
|
|
results = self._ddgs_news(query)
|
|
else:
|
|
results = []
|
|
|
|
if not results:
|
|
return "No good DuckDuckGo Search Result was found"
|
|
return " ".join(r["body"] for r in results)
|
|
|
|
def results(
|
|
self, query: str, max_results: int, source: Optional[str] = None
|
|
) -> List[Dict[str, str]]:
|
|
"""Run query through DuckDuckGo and return metadata.
|
|
|
|
Args:
|
|
query: The query to search for.
|
|
max_results: The number of results to return.
|
|
source: The source to look from.
|
|
|
|
Returns:
|
|
A list of dictionaries with the following keys:
|
|
snippet - The description of the result.
|
|
title - The title of the result.
|
|
link - The link to the result.
|
|
"""
|
|
source = source or self.source
|
|
if source == "text":
|
|
results = [
|
|
{"snippet": r["body"], "title": r["title"], "link": r["href"]}
|
|
for r in self._ddgs_text(query, max_results=max_results)
|
|
]
|
|
elif source == "news":
|
|
results = [
|
|
{
|
|
"snippet": r["body"],
|
|
"title": r["title"],
|
|
"link": r["url"],
|
|
"date": r["date"],
|
|
"source": r["source"],
|
|
}
|
|
for r in self._ddgs_news(query, max_results=max_results)
|
|
]
|
|
else:
|
|
results = []
|
|
|
|
if results is None:
|
|
results = [{"Result": "No good DuckDuckGo Search Result was found"}]
|
|
|
|
return results
|