From 5b8975b7da1eeb89223635085f6249b02844f994 Mon Sep 17 00:00:00 2001 From: Timothy Jaeryang Baek Date: Mon, 10 Aug 2026 00:05:55 -0600 Subject: [PATCH] refac --- Dockerfile | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Dockerfile b/Dockerfile index 07b0e0667d..9345441984 100644 --- a/Dockerfile +++ b/Dockerfile @@ -164,6 +164,11 @@ RUN set -e; \ mkdir -p /app/backend/data; chown -R $UID:$GID /app/backend/data/; \ rm -rf /var/lib/apt/lists/*; +# Optional: PPTX parsing through unstructured may need spaCy's English model. +# Keep this out of the default image to avoid the extra image bloat; deployments +# with read-only site-packages can uncomment it and bake the model in. +# RUN python -m spacy download en_core_web_sm + # Install Ollama if requested RUN if [ "$USE_OLLAMA" = "true" ]; then \ date +%s > /tmp/ollama_build_hash && \