mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-29 07:19:59 +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()
```
90 lines
2.7 KiB
Python
90 lines
2.7 KiB
Python
"""Utils for interacting with the Semantic Scholar API."""
|
|
|
|
import logging
|
|
from typing import Any, Dict, Optional
|
|
|
|
from langchain_core.pydantic_v1 import BaseModel, root_validator
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class SemanticScholarAPIWrapper(BaseModel):
|
|
"""Wrapper around semanticscholar.org API.
|
|
https://github.com/danielnsilva/semanticscholar
|
|
|
|
You should have this library installed.
|
|
|
|
`pip install semanticscholar`
|
|
|
|
Semantic Scholar API can conduct searches and fetch document metadata
|
|
like title, abstract, authors, etc.
|
|
|
|
Attributes:
|
|
top_k_results: number of the top-scored document used for the Semantic Scholar tool
|
|
load_max_docs: a limit to the number of loaded documents
|
|
|
|
Example:
|
|
.. code-block:: python
|
|
|
|
from langchain_community.utilities.semanticscholar import SemanticScholarAPIWrapper
|
|
ss = SemanticScholarAPIWrapper(
|
|
top_k_results = 3,
|
|
load_max_docs = 3
|
|
)
|
|
ss.run("biases in large language models")
|
|
"""
|
|
|
|
semanticscholar_search: Any #: :meta private:
|
|
top_k_results: int = 5
|
|
S2_MAX_QUERY_LENGTH: int = 300
|
|
load_max_docs: int = 100
|
|
doc_content_chars_max: Optional[int] = 4000
|
|
returned_fields = [
|
|
"title",
|
|
"abstract",
|
|
"venue",
|
|
"year",
|
|
"paperId",
|
|
"citationCount",
|
|
"openAccessPdf",
|
|
"authors",
|
|
"externalIds",
|
|
]
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that the python package exists in environment."""
|
|
try:
|
|
from semanticscholar import SemanticScholar
|
|
|
|
sch = SemanticScholar()
|
|
values["semanticscholar_search"] = sch.search_paper
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import Semanticscholar python package. "
|
|
"Please install it with `pip install semanticscholar`."
|
|
)
|
|
return values
|
|
|
|
def run(self, query: str) -> str:
|
|
"""Run the Semantic Scholar API."""
|
|
results = self.semanticscholar_search(
|
|
query, limit=self.load_max_docs, fields=self.returned_fields
|
|
)
|
|
documents = []
|
|
for item in results[: self.top_k_results]:
|
|
authors = ", ".join(
|
|
author["name"] for author in getattr(item, "authors", [])
|
|
)
|
|
documents.append(
|
|
f"Published year: {getattr(item, 'year', None)}\n"
|
|
f"Title: {getattr(item, 'title', None)}\n"
|
|
f"Authors: {authors}\n"
|
|
f"Astract: {getattr(item, 'abstract', None)}\n"
|
|
)
|
|
|
|
if documents:
|
|
return "\n\n".join(documents)[: self.doc_content_chars_max]
|
|
else:
|
|
return "No results found."
|