diff --git a/Dockerfile b/Dockerfile
index 88cfc6b9..64a30753 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -4,12 +4,16 @@ FROM node:alpine as build
 
 WORKDIR /app
 
+# wget embedding model weight from alpine (does not exist from slim-buster)
+RUN wget "https://chroma-onnx-models.s3.amazonaws.com/all-MiniLM-L6-v2/onnx.tar.gz"
+
 COPY package.json package-lock.json ./ 
 RUN npm ci
 
 COPY . .
 RUN npm run build
 
+
 FROM python:3.11-slim-bookworm as base
 
 ENV ENV=prod
@@ -22,12 +26,24 @@ ENV OPENAI_API_KEY ""
 ENV WEBUI_JWT_SECRET_KEY "SECRET_KEY"
 
 WORKDIR /app
+
+# copy embedding weight from build
+RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
+COPY --from=build /app/onnx.tar.gz /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
+
+RUN cd /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2 &&\
+    tar -xzf onnx.tar.gz
+
+# copy built frontend files
 COPY --from=build /app/build /app/build
 
 WORKDIR /app/backend
 
 COPY ./backend/requirements.txt ./requirements.txt
+
+RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
 RUN pip3 install -r requirements.txt
+
 # RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('all-MiniLM-L6-v2')"
 
 COPY ./backend .
diff --git a/backend/requirements.txt b/backend/requirements.txt
index 3d5bb396..06af0efc 100644
--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -16,10 +16,6 @@ aiohttp
 peewee
 bcrypt
 
-torch --index-url https://download.pytorch.org/whl/cpu
-torchvision --index-url https://download.pytorch.org/whl/cpu
-torchaudio --index-url https://download.pytorch.org/whl/cpu
-
 langchain
 langchain-community
 chromadb
diff --git a/run.sh b/run.sh
index 0ada65d1..6e2dc611 100644
--- a/run.sh
+++ b/run.sh
@@ -1,5 +1,5 @@
+docker build -t ollama-webui .
 docker stop ollama-webui || true
 docker rm ollama-webui || true
-docker build -t ollama-webui .
 docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama-webui:/app/backend/data --name ollama-webui --restart always ollama-webui
 docker image prune -f
\ No newline at end of file