mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-20 20:48:16 +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()
```
127 lines
4.2 KiB
Python
127 lines
4.2 KiB
Python
"""Util that calls Wikipedia."""
|
|
|
|
import logging
|
|
from typing import Any, Dict, Iterator, List, Optional
|
|
|
|
from langchain_core.documents import Document
|
|
from langchain_core.pydantic_v1 import BaseModel, root_validator
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
WIKIPEDIA_MAX_QUERY_LENGTH = 300
|
|
|
|
|
|
class WikipediaAPIWrapper(BaseModel):
|
|
"""Wrapper around WikipediaAPI.
|
|
|
|
To use, you should have the ``wikipedia`` python package installed.
|
|
This wrapper will use the Wikipedia API to conduct searches and
|
|
fetch page summaries. By default, it will return the page summaries
|
|
of the top-k results.
|
|
It limits the Document content by doc_content_chars_max.
|
|
"""
|
|
|
|
wiki_client: Any #: :meta private:
|
|
top_k_results: int = 3
|
|
lang: str = "en"
|
|
load_all_available_meta: bool = False
|
|
doc_content_chars_max: int = 4000
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that the python package exists in environment."""
|
|
try:
|
|
import wikipedia
|
|
|
|
lang = values.get("lang", "en")
|
|
wikipedia.set_lang(lang)
|
|
values["wiki_client"] = wikipedia
|
|
except ImportError:
|
|
raise ImportError(
|
|
"Could not import wikipedia python package. "
|
|
"Please install it with `pip install wikipedia`."
|
|
)
|
|
return values
|
|
|
|
def run(self, query: str) -> str:
|
|
"""Run Wikipedia search and get page summaries."""
|
|
page_titles = self.wiki_client.search(
|
|
query[:WIKIPEDIA_MAX_QUERY_LENGTH], results=self.top_k_results
|
|
)
|
|
summaries = []
|
|
for page_title in page_titles[: self.top_k_results]:
|
|
if wiki_page := self._fetch_page(page_title):
|
|
if summary := self._formatted_page_summary(page_title, wiki_page):
|
|
summaries.append(summary)
|
|
if not summaries:
|
|
return "No good Wikipedia Search Result was found"
|
|
return "\n\n".join(summaries)[: self.doc_content_chars_max]
|
|
|
|
@staticmethod
|
|
def _formatted_page_summary(page_title: str, wiki_page: Any) -> Optional[str]:
|
|
return f"Page: {page_title}\nSummary: {wiki_page.summary}"
|
|
|
|
def _page_to_document(self, page_title: str, wiki_page: Any) -> Document:
|
|
main_meta = {
|
|
"title": page_title,
|
|
"summary": wiki_page.summary,
|
|
"source": wiki_page.url,
|
|
}
|
|
add_meta = (
|
|
{
|
|
"categories": wiki_page.categories,
|
|
"page_url": wiki_page.url,
|
|
"image_urls": wiki_page.images,
|
|
"related_titles": wiki_page.links,
|
|
"parent_id": wiki_page.parent_id,
|
|
"references": wiki_page.references,
|
|
"revision_id": wiki_page.revision_id,
|
|
"sections": wiki_page.sections,
|
|
}
|
|
if self.load_all_available_meta
|
|
else {}
|
|
)
|
|
doc = Document(
|
|
page_content=wiki_page.content[: self.doc_content_chars_max],
|
|
metadata={
|
|
**main_meta,
|
|
**add_meta,
|
|
},
|
|
)
|
|
return doc
|
|
|
|
def _fetch_page(self, page: str) -> Optional[str]:
|
|
try:
|
|
return self.wiki_client.page(title=page, auto_suggest=False)
|
|
except (
|
|
self.wiki_client.exceptions.PageError,
|
|
self.wiki_client.exceptions.DisambiguationError,
|
|
):
|
|
return None
|
|
|
|
def load(self, query: str) -> List[Document]:
|
|
"""
|
|
Run Wikipedia search and get the article text plus the meta information.
|
|
See
|
|
|
|
Returns: a list of documents.
|
|
|
|
"""
|
|
return list(self.lazy_load(query))
|
|
|
|
def lazy_load(self, query: str) -> Iterator[Document]:
|
|
"""
|
|
Run Wikipedia search and get the article text plus the meta information.
|
|
See
|
|
|
|
Returns: a list of documents.
|
|
|
|
"""
|
|
page_titles = self.wiki_client.search(
|
|
query[:WIKIPEDIA_MAX_QUERY_LENGTH], results=self.top_k_results
|
|
)
|
|
for page_title in page_titles[: self.top_k_results]:
|
|
if wiki_page := self._fetch_page(page_title):
|
|
if doc := self._page_to_document(page_title, wiki_page):
|
|
yield doc
|