Skip to content

Commit

Permalink
fix missing nltk models
Browse files Browse the repository at this point in the history
  • Loading branch information
santteegt committed Nov 26, 2024
1 parent 87b220c commit 441065b
Showing 1 changed file with 3 additions and 3 deletions.
6 changes: 3 additions & 3 deletions gaianet_rag_api_pipeline/processor/parser.py
Original file line number Diff line number Diff line change
Expand Up @@ -48,9 +48,9 @@ def __init__(
# NOTICE: required when using text partition directly
nltk_downloader = Downloader()
logger.info(f"NLTK data folder: {nltk_downloader.default_download_dir()}")
if not nltk_downloader.is_installed("punkt"):
logger.info(f"Downloading punkt NLTK model...")
nltk_downloader.download("punkt")
if not nltk_downloader.is_installed("popular"):
logger.info(f"Downloading NLTK data -> popular collection...")
nltk_downloader.download("popular", quiet=True)
if not nltk_downloader.is_installed("punkt_tab"):
logger.info(f"Downloading punkt_tab NLTK model...")
nltk_downloader.download("punkt_tab")
Expand Down

0 comments on commit 441065b

Please sign in to comment.