laminou / Dockerfile
lamionx's picture
Deploy AI API with FastAPI + Mistral-7B: streaming, authentication, multi-language support, caching
8a464c3
# ============================================================================
# AI API Dockerfile - Optimized for Hugging Face Spaces
# ============================================================================
# This Dockerfile is configured to run on Hugging Face Spaces with:
# - Port 7860 (HF Spaces default)
# - Non-root user for security
# - CUDA support for GPU acceleration
# - 4-bit quantization for efficient memory usage
# ============================================================================
FROM nvidia/cuda:12.1.0-cudnn8-runtime-ubuntu22.04
# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive \
PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_DISABLE_PIP_VERSION_CHECK=1 \
CUDA_HOME=/usr/local/cuda \
PATH=/usr/local/cuda/bin:${PATH} \
LD_LIBRARY_PATH=/usr/local/cuda/lib64:${LD_LIBRARY_PATH}
# Install system dependencies
RUN apt-get update && apt-get install -y \
python3.10 \
python3-pip \
python3-dev \
build-essential \
git \
wget \
curl \
ca-certificates \
libgomp1 \
&& rm -rf /var/lib/apt/lists/*
# Create non-root user for security
RUN useradd -m -u 1000 -s /bin/bash appuser
# Set working directory
WORKDIR /app
# Copy requirements first (for better caching)
COPY requirements.txt .
# Upgrade pip and install Python dependencies
RUN pip3 install --upgrade pip setuptools wheel && \
pip3 install --no-cache-dir -r requirements.txt
# Copy application code
COPY main.py .
# Create necessary directories
RUN mkdir -p /app/logs && \
chown -R appuser:appuser /app
# Switch to non-root user
USER appuser
# Set default environment variables (can be overridden)
ENV MODEL_NAME="mistralai/Mistral-7B-Instruct-v0.2" \
API_KEY="your-secret-api-key-here" \
MAX_LENGTH="2048" \
TEMPERATURE="0.7" \
TOP_P="0.95" \
CACHE_SIZE="100" \
PORT="7860" \
HOST="0.0.0.0"
# Expose port 7860 (Hugging Face Spaces default)
EXPOSE 7860
# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
CMD curl -f http://localhost:7860/health || exit 1
# Run the application
CMD ["python3", "main.py"]