secondme-api / Dockerfile
Gemini
fix: use HF_HOME instead of TRANSFORMERS_CACHE
7b49a15
FROM python:3.12
# Set working directory
WORKDIR /app
# Install system dependencies, Poetry and configure it
RUN apt-get update && apt-get install -y \
build-essential cmake git curl wget lsof vim unzip sqlite3 \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/* \
&& pip install --upgrade pip \
&& pip install poetry \
&& poetry config virtualenvs.create false
# Create directories
RUN mkdir -p /app/dependencies /app/data/sqlite /app/data/chroma_db /app/logs /app/run /app/resources
# Set permissions for writable directories
RUN chmod -R 777 /app/data /app/logs /app/run /app/resources
# Copy dependency files - Files that rarely change
COPY dependencies/graphrag-1.2.1.dev27.tar.gz /app/dependencies/
COPY dependencies/llama.cpp.zip /app/dependencies/
RUN echo "--- Listing dependencies directory ---" && ls -la /app/dependencies
# Copy GPU checker script (only used for status reporting, not rebuilding)
COPY docker/app/check_gpu_support.sh /app/
COPY docker/app/check_torch_cuda.py /app/
RUN chmod +x /app/check_gpu_support.sh
# Build llama.cpp
RUN LLAMA_LOCAL_ZIP="dependencies/llama.cpp.zip" \
&& echo "Using local llama.cpp archive..." \
&& unzip -q "$LLAMA_LOCAL_ZIP" \
&& cd llama.cpp \
&& mkdir -p build && cd build \
&& cmake .. \
&& cmake --build . --config Release \
&& if [ ! -f "bin/llama-server" ]; then \
echo "Build failed: llama-server executable not found" && exit 1; \
else \
echo "Successfully built llama-server"; \
fi
# Mark as CPU-only build for runtime reference
RUN mkdir -p /app/data && \
echo "{ \"gpu_optimized\": false, \"optimized_on\": \"$(date -u +\"%%Y-%%m-%%dT%%H:%%M:%%SZ\")\" }" > /app/data/gpu_optimized.json && \
echo "Created CPU-only marker file"
# Copy project configuration - Files that occasionally change
COPY pyproject.toml README.md /app/
RUN echo "--- Listing /app directory ---" && ls -la /app
RUN poetry install --no-interaction --no-root
RUN pip install --force-reinstall dependencies/graphrag-1.2.1.dev27.tar.gz
# Copy source code - Files that frequently change
COPY docker/ /app/docker/
COPY lpm_kernel/ /app/lpm_kernel/
RUN echo "--- Listing /app/docker directory ---" && ls -la /app/docker
RUN echo "--- Listing /app/lpm_kernel directory ---" && ls -la /app/lpm_kernel
# Copy the start script
COPY start.sh /app/
# Copy .env file
COPY .env /app/.env
# Check module import
RUN python -c "import lpm_kernel; print('Module import check passed')"
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONPATH=/app \
BASE_DIR=/app/data \
LOCAL_LOG_DIR=/app/logs \
RUN_DIR=/app/run \
RESOURCES_DIR=/app/resources \
APP_ROOT=/app \
FLASK_APP=lpm_kernel.app \
HF_HOME=/app/.cache/huggingface
# Expose ports
EXPOSE 8002 8080
# Set the startup command
CMD ["./start.sh"]