mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-24 03:52:08 +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
"""
|
|
Adapted from https://github.com/venuv/langchain_yt_tools
|
|
|
|
CustomYTSearchTool searches YouTube videos related to a person
|
|
and returns a specified number of video URLs.
|
|
Input to this tool should be a comma separated list,
|
|
- the first part contains a person name
|
|
- and the second(optional) a number that is the
|
|
maximum number of video results to return
|
|
"""
|
|
|
|
import json
|
|
from typing import Optional
|
|
|
|
from langchain_core.callbacks import CallbackManagerForToolRun
|
|
|
|
from langchain_community.tools import BaseTool
|
|
|
|
|
|
class YouTubeSearchTool(BaseTool):
|
|
"""Tool that queries YouTube."""
|
|
|
|
name: str = "youtube_search"
|
|
description: str = (
|
|
"search for youtube videos associated with a person. "
|
|
"the input to this tool should be a comma separated list, "
|
|
"the first part contains a person name and the second a "
|
|
"number that is the maximum number of video results "
|
|
"to return aka num_results. the second part is optional"
|
|
)
|
|
|
|
def _search(self, person: str, num_results: int) -> str:
|
|
from youtube_search import YoutubeSearch
|
|
|
|
results = YoutubeSearch(person, num_results).to_json()
|
|
data = json.loads(results)
|
|
url_suffix_list = [
|
|
"https://www.youtube.com" + video["url_suffix"] for video in data["videos"]
|
|
]
|
|
return str(url_suffix_list)
|
|
|
|
def _run(
|
|
self,
|
|
query: str,
|
|
run_manager: Optional[CallbackManagerForToolRun] = None,
|
|
) -> str:
|
|
"""Use the tool."""
|
|
values = query.split(",")
|
|
person = values[0]
|
|
if len(values) > 1:
|
|
num_results = int(values[1])
|
|
else:
|
|
num_results = 2
|
|
return self._search(person, num_results)
|