From 5a1ef27224bcb5f14319527d33ed81bee4445be0 Mon Sep 17 00:00:00 2001
From: shamoon <4887959+shamoon@users.noreply.github.com>
Date: Thu, 22 Aug 2024 20:32:02 -0700
Subject: [PATCH] Fix: fix nltk tokenizer breaking change (#7522)

---
 Dockerfile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Dockerfile b/Dockerfile
index 57c584327..2a9d7b306 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -246,7 +246,7 @@ RUN --mount=type=cache,target=/root/.cache/pip/,id=pip-cache \
   && echo "Installing NLTK data" \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" snowball_data \
     && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" stopwords \
-    && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" punkt \
+    && python3 -W ignore::RuntimeWarning -m nltk.downloader -d "/usr/share/nltk_data" punkt_tab \
   && echo "Cleaning up image" \
     && apt-get --yes purge ${BUILD_PACKAGES} \
     && apt-get --yes autoremove --purge \