Skip to content

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

[Fix] Refined the NLTK data usage directory (#17376)

Paul Y Hui5bc8f8a967ce
diff --git a/docker/launch_backend_service.sh b/docker/launch_backend_service.sh
index 017297ecc2..a3ac45ec07 100755
--- a/docker/launch_backend_service.sh
+++ b/docker/launch_backend_service.sh
@@ -68,7 +68,10 @@ STOP=false
PIDS=()
# Set the path to the NLTK data directory
-export NLTK_DATA="./nltk_data"
+# download_deps.py downloads NLTK data into ragflow_deps/nltk_data (see
+# ragflow_deps/download_deps.py); point NLTK_DATA there directly instead of a
+# stale top-level ./nltk_data so this matches what's actually populated.
+export NLTK_DATA="$(pwd)/ragflow_deps/nltk_data"
# Function to handle termination signals
cleanup() {