mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-22 15:58:15 +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()
```
131 lines
5.1 KiB
Python
131 lines
5.1 KiB
Python
"""Util that calls Google Scholar Search."""
|
|
|
|
from typing import Dict, Optional
|
|
|
|
from langchain_core.pydantic_v1 import BaseModel, Extra, root_validator
|
|
from langchain_core.utils import get_from_dict_or_env
|
|
|
|
|
|
class GoogleScholarAPIWrapper(BaseModel):
|
|
"""Wrapper for Google Scholar API
|
|
|
|
You can create serpapi key by signing up at: https://serpapi.com/users/sign_up.
|
|
|
|
The wrapper uses the serpapi python package:
|
|
https://serpapi.com/integrations/python#search-google-scholar
|
|
|
|
To use, you should have the environment variable ``SERP_API_KEY``
|
|
set with your API key, or pass `serp_api_key` as a named parameter
|
|
to the constructor.
|
|
|
|
Attributes:
|
|
top_k_results: number of results to return from google-scholar query search.
|
|
By default it returns top 10 results.
|
|
hl: attribute defines the language to use for the Google Scholar search.
|
|
It's a two-letter language code.
|
|
(e.g., en for English, es for Spanish, or fr for French). Head to the
|
|
Google languages page for a full list of supported Google languages:
|
|
https://serpapi.com/google-languages
|
|
|
|
lr: attribute defines one or multiple languages to limit the search to.
|
|
It uses lang_{two-letter language code} to specify languages
|
|
and | as a delimiter. (e.g., lang_fr|lang_de will only search French
|
|
and German pages). Head to the Google lr languages for a full
|
|
list of supported languages: https://serpapi.com/google-lr-languages
|
|
|
|
Example:
|
|
.. code-block:: python
|
|
|
|
from langchain_community.utilities import GoogleScholarAPIWrapper
|
|
google_scholar = GoogleScholarAPIWrapper()
|
|
google_scholar.run('langchain')
|
|
"""
|
|
|
|
top_k_results: int = 10
|
|
hl: str = "en"
|
|
lr: str = "lang_en"
|
|
serp_api_key: Optional[str] = None
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that api key and python package exists in environment."""
|
|
serp_api_key = get_from_dict_or_env(values, "serp_api_key", "SERP_API_KEY")
|
|
values["SERP_API_KEY"] = serp_api_key
|
|
|
|
try:
|
|
from serpapi import GoogleScholarSearch
|
|
|
|
except ImportError:
|
|
raise ImportError(
|
|
"google-search-results is not installed. "
|
|
"Please install it with `pip install google-search-results"
|
|
">=2.4.2`"
|
|
)
|
|
GoogleScholarSearch.SERP_API_KEY = serp_api_key
|
|
values["google_scholar_engine"] = GoogleScholarSearch
|
|
|
|
return values
|
|
|
|
def run(self, query: str) -> str:
|
|
"""Run query through GoogleSearchScholar and parse result"""
|
|
total_results = []
|
|
page = 0
|
|
while page < max((self.top_k_results - 20), 1):
|
|
# We are getting 20 results from every page
|
|
# which is the max in order to reduce the number of API CALLS.
|
|
# 0 is the first page of results, 20 is the 2nd page of results,
|
|
# 40 is the 3rd page of results, etc.
|
|
results = (
|
|
self.google_scholar_engine( # type: ignore
|
|
{
|
|
"q": query,
|
|
"start": page,
|
|
"hl": self.hl,
|
|
"num": min(
|
|
self.top_k_results, 20
|
|
), # if top_k_result is less than 20.
|
|
"lr": self.lr,
|
|
}
|
|
)
|
|
.get_dict()
|
|
.get("organic_results", [])
|
|
)
|
|
total_results.extend(results)
|
|
if not results: # No need to search for more pages if current page
|
|
# has returned no results
|
|
break
|
|
page += 20
|
|
if (
|
|
self.top_k_results % 20 != 0 and page > 20 and total_results
|
|
): # From the last page we would only need top_k_results%20 results
|
|
# if k is not divisible by 20.
|
|
results = (
|
|
self.google_scholar_engine( # type: ignore
|
|
{
|
|
"q": query,
|
|
"start": page,
|
|
"num": self.top_k_results % 20,
|
|
"hl": self.hl,
|
|
"lr": self.lr,
|
|
}
|
|
)
|
|
.get_dict()
|
|
.get("organic_results", [])
|
|
)
|
|
total_results.extend(results)
|
|
if not total_results:
|
|
return "No good Google Scholar Result was found"
|
|
docs = [
|
|
f"Title: {result.get('title','')}\n"
|
|
f"Authors: {','.join([author.get('name') for author in result.get('publication_info',{}).get('authors',[])])}\n" # noqa: E501
|
|
f"Summary: {result.get('publication_info',{}).get('summary','')}\n"
|
|
f"Total-Citations: {result.get('inline_links',{}).get('cited_by',{}).get('total','')}" # noqa: E501
|
|
for result in total_results
|
|
]
|
|
return "\n\n".join(docs)
|