# Ollama37 Runtime Image - Local Development Build
# Single-stage build: compiles and packages the binary in one image
# This Dockerfile uses LOCAL source code instead of cloning from GitHub
# Use this for testing changes without pushing to GitHub
#
# Usage: docker build -f docker/runtime/Dockerfile.local -t ollama37:latest .
#
# The runtime needs access to the build directory for GGML CUDA libraries
# This ensures the compiled binary can find all required runtime libraries at:
#   /usr/local/src/ollama37/build/lib/ollama

# Base image: ollama37-builder contains GCC 10, CUDA 11.4, and build tools
FROM ollama37-builder

# Copy local source code to container
# Build context should be the repository root
COPY . /usr/local/src/ollama37

# Set working directory for build
WORKDIR /usr/local/src/ollama37

# Configure build with CMake
# Use "CUDA 11" preset for Tesla K80 compute capability 3.7 support
# Set LD_LIBRARY_PATH during build so CMake can locate GCC 10 runtime libraries
# and properly link against them (required for C++ standard library and atomics)
RUN bash -c 'LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib64:/usr/lib64:$LD_LIBRARY_PATH \
    CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ \
    cmake --preset "CUDA 11"'

# Build C/C++/CUDA libraries with CMake
# Compile all GGML CUDA kernels and Ollama native libraries
# Use all available CPU cores (-j) for parallel compilation to speed up build
RUN bash -c 'LD_LIBRARY_PATH=/usr/local/lib:/usr/local/lib64:/usr/lib64:$LD_LIBRARY_PATH \
    CC=/usr/local/bin/gcc CXX=/usr/local/bin/g++ \
    cmake --build build -j$(nproc)'

# Build Go binary
# Build to source directory so binary can find libraries via relative path
# Set version via -ldflags - pass OLLAMA_VERSION as build arg
ARG OLLAMA_VERSION
RUN go build -ldflags "-X github.com/ollama/ollama/version.Version=${OLLAMA_VERSION}" -o ./ollama .

# Create symlink to standard binary location
# The code in ml/path.go uses filepath.EvalSymlinks() which resolves this symlink
# to /usr/local/src/ollama37/ollama, allowing it to find libraries at build/lib/ollama
RUN ln -s /usr/local/src/ollama37/ollama /usr/local/bin/ollama

# Setup library paths for runtime
# The binary expects libraries in these exact paths:
#   /usr/local/src/ollama37/build/lib/ollama - Ollama CUDA/GGML libraries
#   /usr/local/lib64 - GCC 10 runtime libraries (libstdc++, libgcc_s)
#   /usr/local/cuda-11.4/lib64 - CUDA 11.4 runtime libraries
#   /usr/lib64 - System libraries
ENV LD_LIBRARY_PATH=/usr/local/src/ollama37/build/lib/ollama:/usr/local/lib64:/usr/local/cuda-11.4/lib64:/usr/lib64

# Configure Ollama server to listen on all interfaces
ENV OLLAMA_HOST=0.0.0.0:11434

# Expose Ollama API port
EXPOSE 11434

# Create persistent volume for model storage
# Models downloaded by Ollama will be stored here
RUN mkdir -p /root/.ollama
VOLUME ["/root/.ollama"]

# Configure health check to verify Ollama is running
# Uses 'ollama list' command to check if the service is responsive
# This validates both API availability and model registry access
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD /usr/local/bin/ollama list || exit 1

# Set entrypoint and default command
# Container runs 'ollama serve' by default to start the API server
ENTRYPOINT ["/usr/local/bin/ollama"]
CMD ["serve"]