Update Dockerfile

Dockerfile

@@ -1,39 +1,45 @@
-ARG HF_TOKEN
-ENV HF_TOKEN=${HF_TOKEN}
-
-# This diagnostic line checks if HF_TOKEN is set
-RUN if [ -z "$HF_TOKEN" ]; then \
-      echo "ERROR: HF_TOKEN is not set!" && exit 1; \
-    else \
-      echo "HF_TOKEN is set (but not displaying the value for security)." ; \
-    fi
-
-# Use the NVIDIA CUDA runtime image for GPU support
+# syntax=docker/dockerfile:1
 FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
 
 # Set environment variables
 ENV DEBIAN_FRONTEND=noninteractive \
     PIP_NO_CACHE_DIR=off \
     PIP_DISABLE_PIP_VERSION_CHECK=on \
-    PATH="/root/.cargo/bin:${PATH}" \
     PYTHONIOENCODING=utf-8 \
     PYTHONUNBUFFERED=1
 
-# Install system dependencies
+# Install required system packages
 RUN apt-get update && apt-get install -y --no-install-recommends \
     git git-lfs python3 python3-pip curl ca-certificates build-essential && \
     apt-get clean && rm -rf /var/lib/apt/lists/*
 
-# Install Rust (required for compiling tokenizers if needed)
+# Install Rust (if needed for building dependencies)
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
 
-# Set the working directory and install Python dependencies
+# Set working directory and install Python dependencies
 WORKDIR /app
 COPY requirements.txt .
 RUN pip3 install --no-cache-dir --upgrade pip && \
     pip3 install --no-cache-dir -r requirements.txt
 
-# Use build-time argument for Hugging Face token
+# Download the model using BuildKit secret mount.
+# This command uses the secret HF_TOKEN, which is passed only during this RUN and not stored in the image.
+RUN --mount=type=secret,id=HF_TOKEN,env=HF_TOKEN \
+    python3 -c "import os; \
+from huggingface_hub import snapshot_download; \
+token = os.getenv('HF_TOKEN'); \
+assert token, 'HF_TOKEN is not set!'; \
+snapshot_download(repo_id='mistralai/Mistral-7B-Instruct-v0.1', local_dir='/app/model', token=token)"
+
+# Expose port 8000
+EXPOSE 8000
+
+# Healthcheck (optional)
+HEALTHCHECK --interval=20s --timeout=10s --start-period=120s --retries=3 \
+    CMD curl --fail http://localhost:8000/health || exit 1
+
+# Set the entrypoint to run the vLLM API server
+CMD ["python3", "-m", "vllm.entrypoints.openai.api_server", "--model", "/app/model"]
 ARG HF_TOKEN
 
 # Download the model during build