From e850e8c92a8e4825ccbe142279ab70e9ce035ed9 Mon Sep 17 00:00:00 2001 From: "Richard Kuo (Onyx)" Date: Mon, 19 May 2025 10:04:22 -0700 Subject: [PATCH] fix nltk punkt --- backend/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/backend/Dockerfile b/backend/Dockerfile index 2e12d6c3ede..8cb84a0b8cf 100644 --- a/backend/Dockerfile +++ b/backend/Dockerfile @@ -85,7 +85,7 @@ Tokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1')" # Pre-downloading NLTK for setups with limited egress RUN python -c "import nltk; \ nltk.download('stopwords', quiet=True); \ -nltk.download('punkt', quiet=True);" +nltk.download('punkt_tab', quiet=True);" # nltk.download('wordnet', quiet=True); introduce this back if lemmatization is needed # Set up application files