trait-embeddings-1 / Dockerfile
danieldunderfelt's picture
Add onnx model.
6e3bdfa
Raw History Blame Contribute Delete
2.28 kB
FROM python:3.12-slim as builder
# Install build dependencies
RUN apt-get update && apt-get install -y \
build-essential \
&& rm -rf /var/lib/apt/lists/*
# Create and activate virtual environment
RUN python -m venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"
WORKDIR /app
# Copy and install requirements
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
# Final stage
FROM python:3.12-slim
# Install runtime dependencies and security updates
RUN apt-get update && apt-get upgrade -y && \
apt-get install -y \
curl \
tini \
&& rm -rf /var/lib/apt/lists/*
# Copy virtual environment from builder
COPY --from=builder /opt/venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"
WORKDIR /app
# Create model directory and copy model files
RUN mkdir -p /app/model
COPY config_sentence_transformers.json config.json model.safetensors modules.json sentence_bert_config.json special_tokens_map.json tokenizer_config.json tokenizer.json unigram.json /app/model/
RUN mkdir -p /app/model/1_Pooling
COPY 1_Pooling/config.json /app/model/1_Pooling/config.json
# Copy application code
COPY app.py .
COPY requirements.txt .
# Verify model files exist
RUN python -c "import os; \
assert os.path.exists('/app/model/model.safetensors'), 'Model file not found'; \
assert os.path.exists('/app/model/config.json'), 'Config file not found'; \
print('Model files verified successfully')"
# Runtime configuration for Cloud Run
ENV PORT=8080
ENV WORKERS=2
ENV WORKER_TIMEOUT=300
ENV PYTHONUNBUFFERED=1
ENV PYTORCH_NUM_THREADS=4
# Set Python environment
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONPATH=/app
# Non-root user for security
RUN useradd -r -u 1000 appuser && \
chown -R appuser:appuser /app
USER appuser
# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
CMD curl -f http://localhost:${PORT}/health || exit 1
# Expose the port
EXPOSE ${PORT}
# Use tini as init system
ENTRYPOINT ["/usr/bin/tini", "--"]
# Use uvicorn with multiple workers for better concurrency
CMD exec uvicorn \
app:app \
--host 0.0.0.0 \
--port ${PORT} \
--workers ${WORKERS} \
--timeout-keep-alive 65 \
--log-level info \
--proxy-headers \
--forwarded-allow-ips '*' \
--no-access-log