Update Dockerfile

Dockerfile

@@ -1,37 +1,65 @@
-FROM ubuntu:latest
-LABEL authors="Bram Vanroy"
+FROM python:3.11-slim-bookworm
 
+# Metadata as per https://github.com/opencontainers/image-spec/blob/master/annotations.md
+LABEL org.opencontainers.image.authors="Bram Vanroy"
+LABEL org.opencontainers.image.title="MAchine Translation Evaluation Online - Demo"
+
+# Avoid prompts from apt
 ENV DEBIAN_FRONTEND=noninteractive
-RUN apt-get -y update \
-    && apt-get -y install build-essential curl git software-properties-common
 
-RUN add-apt-repository ppa:deadsnakes/ppa \
-    && apt-get -y update \
-    && apt-get -y install python3.10 python3.10-dev python3-pip python3.10-distutils \
-    && ln -s /usr/bin/python3.10 /usr/bin/python \
+# Install dependencies in a single RUN command to reduce image layers
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    curl \
+    git \
+    && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
 
-RUN useradd -m -u 1000 user
-USER user
-ENV HOME /home/user
-ENV PATH $HOME/.local/bin:$PATH
-ENV HF_HUB_ENABLE_HF_TRANSFER=1
+# Create a non-root user
+RUN useradd -m -u 1000 mateo_user
+USER mateo_user
+ENV HOME="/home/mateo_user"
+
+# Environment variables
+ENV PORT=7860 \
+    SERVER="localhost" \
+    BASE="" \
+    DEMO_MODE="" \
+    HF_HUB_ENABLE_HF_TRANSFER=1 \
+    PATH="${HOME}/.local/bin:${PATH}" \
+    USE_CUDA=false
 
-WORKDIR $HOME
+WORKDIR ${HOME}/mateo
+
+# Clone the repository
 RUN git clone https://github.com/BramVanroy/mateo-demo.git
-WORKDIR $HOME/mateo-demo
+WORKDIR mateo-demo
 
-RUN python -m pip install --no-cache-dir --upgrade pip && python -m pip install --no-cache-dir --upgrade .
+# Install Python dependencies with conditional torch installation
+RUN python -m pip install --no-cache-dir --upgrade pip wheel setuptools \
+    && python -m pip install --no-cache-dir torch==2.2.1+cpu -f https://download.pytorch.org/whl/torch \
+    && python -m pip install --no-cache-dir --upgrade .
 
 # Pre-download default models
-RUN python -c "import comet; from comet import download_model; download_model('Unbabel/wmt22-comet-da')"
-RUN python -c "import evaluate; evaluate.load('bleurt', 'BLEURT-20')"
-RUN huggingface-cli download bert-base-multilingual-cased model.safetensors tokenizer.json vocab.txt
-RUN huggingface-cli download facebook/nllb-200-distilled-600M pytorch_model.bin sentencepiece.bpe.model tokenizer.json
+RUN huggingface-cli download bert-base-multilingual-cased model.safetensors tokenizer.json vocab.txt; \
+    huggingface-cli download facebook/nllb-200-distilled-600M pytorch_model.bin sentencepiece.bpe.model tokenizer.json; \
+    python -c "import comet; from comet import download_model; download_model('Unbabel/wmt22-comet-da')"; \
+    python -c "import evaluate; evaluate.load('bleurt', 'BLEURT-20')"
+
+# Expose the port the app runs on
+EXPOSE $PORT
 
-EXPOSE 7860
-HEALTHCHECK CMD curl --fail http://localhost:7860/_stcore/health
+# Healthcheck to ensure the service is running
+HEALTHCHECK CMD curl --fail http://$SERVER:$PORT$BASE/_stcore/health || exit 1
 
-WORKDIR $HOME/mateo-demo/src/mateo_st
+# Set the working directory to the Streamlit app
+WORKDIR src/mateo_st
 
-CMD ["streamlit", "run", "01_🎈_MATEO.py", "--server.port", "7860", "--server.enableXsrfProtection", "false", "--", "--no_cuda"]
+# Simplify the CMD script with conditional --use_cuda flag
+CMD streamlit run 01_🎈_MATEO.py \
+    --server.port $PORT \
+    --server.address $SERVER \
+    $(if [ -n "$BASE" ]; then echo "--server.baseUrlPath $BASE"; fi) \
+    $(if [ "$DEMO_MODE" = "true" ]; then echo "--server.maxUploadSize 1"; fi) \
+    -- \
+    $(if [ "$DEMO_MODE" = "true" ]; then echo "--demo_mode"; fi)