From eab60e6b82e9913806d9df4c2212616fab42fd26 Mon Sep 17 00:00:00 2001 From: Danny Avila Date: Wed, 23 Sep 2026 17:00:39 -0400 Subject: [PATCH] fix: drop the NLTK data download from both images --- Dockerfile | 4 ---- Dockerfile.lite | 4 ---- 2 files changed, 8 deletions(-) diff --git a/Dockerfile b/Dockerfile index f1b97bc3..6a3e42ff 100644 --- a/Dockerfile +++ b/Dockerfile @@ -13,10 +13,6 @@ RUN apt-get update \ COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt -ENV NLTK_DATA=/app/nltk_data - -# Download standard NLTK data, to prevent unstructured from downloading packages at runtime -RUN python -c "import nltk, sys; packages = ('punkt_tab', 'averaged_perceptron_tagger', 'averaged_perceptron_tagger_eng'); sys.exit(0 if all(nltk.download(package, download_dir='/app/nltk_data') for package in packages) else 1)" # Disable Unstructured analytics ENV SCARF_NO_ANALYTICS=true diff --git a/Dockerfile.lite b/Dockerfile.lite index 229d3179..f0e2f40a 100644 --- a/Dockerfile.lite +++ b/Dockerfile.lite @@ -13,10 +13,6 @@ RUN apt-get update \ COPY requirements.lite.txt . RUN pip install --no-cache-dir -r requirements.lite.txt -ENV NLTK_DATA=/app/nltk_data - -# Download standard NLTK data, to prevent unstructured from downloading packages at runtime -RUN python -c "import nltk, sys; packages = ('punkt_tab', 'averaged_perceptron_tagger', 'averaged_perceptron_tagger_eng'); sys.exit(0 if all(nltk.download(package, download_dir='/app/nltk_data') for package in packages) else 1)" # Disable Unstructured analytics ENV SCARF_NO_ANALYTICS=true