Dockerfile

# Multi-stage Dockerfile for ARDA Ingestion Service
# Stage 1: Build the Rust application
FROM rustlang/rust:nightly-bookworm AS builder

WORKDIR /app

# Install build dependencies for pdfium-render static linking
RUN apt-get update && apt-get install -y \
    clang \
    cmake \
    pkg-config \
    && rm -rf /var/lib/apt/lists/*

# Copy the entire project
COPY . .

# Build the application in release mode
RUN cargo build --release

# Stage 2: Create the runtime image
FROM debian:bookworm-slim

# Install runtime dependencies including poppler-utils for PDF processing
RUN apt-get update && \
    apt-get install -y \
    ca-certificates \
    libssl3 \
    curl \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

# Create a non-root user to run the application
RUN useradd -m -u 1000 -s /bin/bash arda && \
    mkdir -p /app/logs && \
    chown -R arda:arda /app

# Set working directory
WORKDIR /app

# Copy the binary from builder stage
COPY --from=builder /app/target/release/arda-ingest /app/arda-ingest

# Change ownership of the binary
RUN chown arda:arda /app/arda-ingest

# Switch to non-root user
USER arda

# Expose the default server port
EXPOSE 5678

# Add health check
HEALTHCHECK --interval=30s --timeout=3s --start-period=10s --retries=3 \
    CMD curl -f http://localhost:5678/health || exit 1

# Set the binary as the entrypoint
CMD ["/app/arda-ingest"]