diff --git a/Dockerfile b/Dockerfile
index 660a485..df5e200 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -28,7 +28,8 @@ COPY . .
 # The embedding model for semantic search (~34 MB), fetched at build time so the
 # server never has to download it.
 ENV MODELS_DIR=/app/models
-RUN node -e "require('./lib/embeddingModel').load().then(() => console.log('embedding model ready'))"
+# (No process.exit: forcing an exit while onnxruntime's threads are up aborts node.)
+RUN node -e "require('./lib/embeddingModel').embed(['test']).then(() => console.log('embedding model ready'), (err) => { console.error(err); process.exitCode = 1; })"
 
 ENV NODE_ENV=production \
     PORT=3000