Skip to content

⚡️ Speed up function download_if_not_exists by 76% #79

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
codeflash-ai wants to merge 1 commit into
base: main
Choose a base branch
from
Open

⚡️ Speed up function download_if_not_exists by 76% #79

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 9 additions & 6 deletions graphrag/index/operations/build_noun_graph/np_extractors/resource_loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,13 +3,16 @@

"""Util functions needed for nltk-based noun-phrase extractors (i.e. TextBlob)."""

from functools import lru_cache

import nltk


@lru_cache(maxsize=64)
def download_if_not_exists(resource_name) -> bool:
"""Download nltk resources if they haven't been already."""
# look under all possible categories
root_categories = [
# Precompute all category/resource_name paths for efficiency
root_categories = (
"corpora",
"tokenizers",
"taggers",
Expand All @@ -24,11 +27,11 @@ def download_if_not_exists(resource_name) -> bool:
"mt",
"sentiment",
"similarity",
]
for category in root_categories:
)
resource_paths = [f"{category}/{resource_name}" for category in root_categories]
for path in resource_paths:
try:
# if found, stop looking and avoid downloading
nltk.find(f"{category}/{resource_name}")
nltk.find(path)
return True # noqa: TRY300
except LookupError:
continue
Expand Down